compiler/rustc_middle/src/mir/syntax.rs

//! This defines the syntax of MIR, i.e., the set of available MIR operations, and other definitions
//! closely related to MIR semantics.
//! This is in a dedicated file so that changes to this file can be reviewed more carefully.
//! The intention is that this file only contains datatype declarations, no code.

use rustc_abi::{FieldIdx, VariantIdx};
use rustc_ast::{InlineAsmOptions, InlineAsmTemplatePiece, Mutability};
use rustc_data_structures::packed::Pu128;
use rustc_hir::CoroutineKind;
use rustc_hir::def_id::DefId;
use rustc_index::IndexVec;
use rustc_macros::{HashStable, TyDecodable, TyEncodable, TypeFoldable, TypeVisitable};
use rustc_span::def_id::LocalDefId;
use rustc_span::source_map::Spanned;
use rustc_span::{Span, Symbol};
use rustc_target::asm::InlineAsmRegOrRegClass;
use smallvec::SmallVec;

use super::{BasicBlock, Const, Local, UserTypeProjection};
use crate::mir::coverage::CoverageKind;
use crate::ty::adjustment::PointerCoercion;
use crate::ty::{self, GenericArgsRef, List, Region, Ty, UserTypeAnnotationIndex};

/// Represents the "flavors" of MIR.
///
/// The MIR pipeline is structured into a few major dialects, with one or more phases within each
/// dialect. A MIR flavor is identified by a dialect-phase pair. A single `MirPhase` value
/// specifies such a pair. All flavors of MIR use the same data structure to represent the program.
///
/// Different MIR dialects have different semantics. (The differences between dialects are small,
/// but they do exist.) The progression from one MIR dialect to the next is technically a lowering
/// from one IR to another. In other words, a single well-formed [`Body`](crate::mir::Body) might
/// have different semantic meaning and different behavior at runtime in the different dialects.
/// The specific differences between dialects are described on the variants below.
///
/// Phases exist only to place restrictions on what language constructs are permitted in
/// well-formed MIR, and subsequent phases mostly increase those restrictions. I.e. to convert MIR
/// from one phase to the next might require removing/replacing certain MIR constructs.
///
/// When adding dialects or phases, remember to update [`MirPhase::index`].
#[derive(Copy, Clone, TyEncodable, TyDecodable, Debug, PartialEq, Eq, PartialOrd, Ord)]
#[derive(HashStable)]
pub enum MirPhase {
    /// The "built MIR" dialect, as generated by MIR building.
    ///
    /// The only things that operate on this dialect are unsafeck, the various MIR lints, and const
    /// qualifs.
    ///
    /// This dialect has just the one (implicit) phase, which places few restrictions on what MIR
    /// constructs are allowed.
    Built,

    /// The "analysis MIR" dialect, used for borrowck and friends.
    ///
    /// The only semantic difference between built MIR and analysis MIR relates to constant
    /// promotion. In built MIR, sequences of statements that would generally be subject to
    /// constant promotion are semantically constants, while in analysis MIR all constants are
    /// explicit.
    ///
    /// The result of const promotion is available from the `mir_promoted` and `promoted_mir`
    /// queries.
    ///
    /// The phases of this dialect are described in `AnalysisPhase`.
    Analysis(AnalysisPhase),

    /// The "runtime MIR" dialect, used for CTFE, optimizations, and codegen.
    ///
    /// The semantic differences between analysis MIR and runtime MIR are as follows.
    ///
    /// - Drops: In analysis MIR, `Drop` terminators represent *conditional* drops; roughly
    ///   speaking, if dataflow analysis determines that the place being dropped is uninitialized,
    ///   the drop will not be executed. The exact semantics of this aren't written down anywhere,
    ///   which means they are essentially "what drop elaboration does." In runtime MIR, the drops
    ///   are unconditional; when a `Drop` terminator is reached, if the type has drop glue that
    ///   drop glue is always executed. This may be UB if the underlying place is not initialized.
    /// - Packed drops: Places might in general be misaligned - in most cases this is UB, the
    ///   exception is fields of packed structs. In analysis MIR, `Drop(P)` for a `P` that might be
    ///   misaligned for this reason implicitly moves `P` to a temporary before dropping. Runtime
    ///   MIR has no such rules, and dropping a misaligned place is simply UB.
    /// - Unwinding: in analysis MIR, unwinding from a function which may not unwind aborts. In
    ///   runtime MIR, this is UB.
    /// - Retags: If `-Zmir-emit-retag` is enabled, analysis MIR has "implicit" retags in the same
    ///   way that Rust itself has them. Where exactly these are is generally subject to change,
    ///   and so we don't document this here. Runtime MIR has most retags explicit (though implicit
    ///   retags can still occur at `Rvalue::{Ref,AddrOf}`).
    /// - Coroutine bodies: In analysis MIR, locals may actually be behind a pointer that user code
    ///   has access to. This occurs in coroutine bodies. Such locals do not behave like other
    ///   locals, because they e.g. may be aliased in surprising ways. Runtime MIR has no such
    ///   special locals. All coroutine bodies are lowered and so all places that look like locals
    ///   really are locals.
    ///
    /// Also note that the lint pass which reports eg `200_u8 + 200_u8` as an error is run as a part
    /// of analysis to runtime MIR lowering. To ensure lints are reported reliably, this means that
    /// transformations that can suppress such errors should not run on analysis MIR.
    ///
    /// The phases of this dialect are described in `RuntimePhase`.
    Runtime(RuntimePhase),
}

/// See [`MirPhase::Analysis`].
#[derive(Copy, Clone, TyEncodable, TyDecodable, Debug, PartialEq, Eq, PartialOrd, Ord)]
#[derive(HashStable)]
pub enum AnalysisPhase {
    Initial = 0,
    /// Beginning in this phase, the following variants are disallowed:
    /// * [`TerminatorKind::FalseUnwind`]
    /// * [`TerminatorKind::FalseEdge`]
    /// * [`StatementKind::FakeRead`]
    /// * [`StatementKind::AscribeUserType`]
    /// * [`StatementKind::Coverage`] with [`CoverageKind::BlockMarker`] or
    ///   [`CoverageKind::SpanMarker`]
    /// * [`Rvalue::Ref`] with `BorrowKind::Fake`
    /// * [`CastKind::PointerCoercion`] with any of the following:
    ///   * [`PointerCoercion::ArrayToPointer`]
    ///   * [`PointerCoercion::MutToConstPointer`]
    ///
    /// Furthermore, `Deref` projections must be the first projection within any place (if they
    /// appear at all)
    PostCleanup = 1,
}

/// See [`MirPhase::Runtime`].
#[derive(Copy, Clone, TyEncodable, TyDecodable, Debug, PartialEq, Eq, PartialOrd, Ord)]
#[derive(HashStable)]
pub enum RuntimePhase {
    /// In addition to the semantic changes, beginning with this phase, the following variants are
    /// disallowed:
    /// * [`TerminatorKind::Yield`]
    /// * [`TerminatorKind::CoroutineDrop`]
    /// * [`Rvalue::Aggregate`] for any `AggregateKind` except `Array`
    /// * [`PlaceElem::OpaqueCast`]
    ///
    /// And the following variants are allowed:
    /// * [`StatementKind::Retag`]
    /// * [`StatementKind::SetDiscriminant`]
    /// * [`StatementKind::Deinit`]
    ///
    /// Furthermore, `Copy` operands are allowed for non-`Copy` types.
    Initial = 0,
    /// Beginning with this phase, the following variant is disallowed:
    /// * [`ProjectionElem::Deref`] of `Box`
    PostCleanup = 1,
    Optimized = 2,
}

///////////////////////////////////////////////////////////////////////////
// Borrow kinds

#[derive(Copy, Clone, Debug, PartialEq, Eq, PartialOrd, Ord, TyEncodable, TyDecodable)]
#[derive(Hash, HashStable)]
pub enum BorrowKind {
    /// Data must be immutable and is aliasable.
    Shared,

    /// An immutable, aliasable borrow that is discarded after borrow-checking. Can behave either
    /// like a normal shared borrow or like a special shallow borrow (see [`FakeBorrowKind`]).
    ///
    /// This is used when lowering index expressions and matches. This is used to prevent code like
    /// the following from compiling:
    /// ```compile_fail,E0510
    /// let mut x: &[_] = &[[0, 1]];
    /// let y: &[_] = &[];
    /// let _ = x[0][{x = y; 1}];
    /// ```
    /// ```compile_fail,E0510
    /// let mut x = &Some(0);
    /// match *x {
    ///     None => (),
    ///     Some(_) if { x = &None; false } => (),
    ///     Some(_) => (),
    /// }
    /// ```
    /// We can also report errors with this kind of borrow differently.
    Fake(FakeBorrowKind),

    /// Data is mutable and not aliasable.
    Mut { kind: MutBorrowKind },
}

#[derive(Copy, Clone, Debug, PartialEq, Eq, PartialOrd, Ord, TyEncodable, TyDecodable)]
#[derive(Hash, HashStable)]
pub enum RawPtrKind {
    Mut,
    Const,
    /// Creates a raw pointer to a place that will only be used to access its metadata,
    /// not the data behind the pointer. Note that this limitation is *not* enforced
    /// by the validator.
    ///
    /// The borrow checker allows overlap of these raw pointers with references to the
    /// data. This is sound even if the pointer is "misused" since any such use is anyway
    /// unsafe. In terms of the operational semantics (i.e., Miri), this is equivalent
    /// to `RawPtrKind::Mut`, but will never incur a retag.
    FakeForPtrMetadata,
}

#[derive(Copy, Clone, Debug, PartialEq, Eq, PartialOrd, Ord, TyEncodable, TyDecodable)]
#[derive(Hash, HashStable)]
pub enum MutBorrowKind {
    Default,
    /// This borrow arose from method-call auto-ref. (i.e., `adjustment::Adjust::Borrow`)
    TwoPhaseBorrow,
    /// Data must be immutable but not aliasable. This kind of borrow
    /// cannot currently be expressed by the user and is used only in
    /// implicit closure bindings. It is needed when the closure is
    /// borrowing or mutating a mutable referent, e.g.:
    /// ```
    /// let mut z = 3;
    /// let x: &mut isize = &mut z;
    /// let y = || *x += 5;
    /// ```
    /// If we were to try to translate this closure into a more explicit
    /// form, we'd encounter an error with the code as written:
    /// ```compile_fail,E0594
    /// struct Env<'a> { x: &'a &'a mut isize }
    /// let mut z = 3;
    /// let x: &mut isize = &mut z;
    /// let y = (&mut Env { x: &x }, fn_ptr);  // Closure is pair of env and fn
    /// fn fn_ptr(env: &mut Env) { **env.x += 5; }
    /// ```
    /// This is then illegal because you cannot mutate an `&mut` found
    /// in an aliasable location. To solve, you'd have to translate with
    /// an `&mut` borrow:
    /// ```compile_fail,E0596
    /// struct Env<'a> { x: &'a mut &'a mut isize }
    /// let mut z = 3;
    /// let x: &mut isize = &mut z;
    /// let y = (&mut Env { x: &mut x }, fn_ptr); // changed from &x to &mut x
    /// fn fn_ptr(env: &mut Env) { **env.x += 5; }
    /// ```
    /// Now the assignment to `**env.x` is legal, but creating a
    /// mutable pointer to `x` is not because `x` is not mutable. We
    /// could fix this by declaring `x` as `let mut x`. This is ok in
    /// user code, if awkward, but extra weird for closures, since the
    /// borrow is hidden.
    ///
    /// So we introduce a `ClosureCapture` borrow -- user will not have to mark the variable
    /// containing the mutable reference as `mut`, as they didn't ever
    /// intend to mutate the mutable reference itself. We still mutable capture it in order to
    /// mutate the pointed value through it (but not mutating the reference itself).
    ///
    /// This solves the problem. For simplicity, we don't give users the way to express this
    /// borrow, it's just used when translating closures.
    ClosureCapture,
}

#[derive(Copy, Clone, Debug, PartialEq, Eq, PartialOrd, Ord, TyEncodable, TyDecodable)]
#[derive(Hash, HashStable)]
pub enum FakeBorrowKind {
    /// A shared shallow borrow. The immediately borrowed place must be immutable, but projections
    /// from it don't need to be. For example, a shallow borrow of `a.b` doesn't conflict with a
    /// mutable borrow of `a.b.c`.
    ///
    /// This is used when lowering matches: when matching on a place we want to ensure that place
    /// have the same value from the start of the match until an arm is selected. This prevents this
    /// code from compiling:
    /// ```compile_fail,E0510
    /// let mut x = &Some(0);
    /// match *x {
    ///     None => (),
    ///     Some(_) if { x = &None; false } => (),
    ///     Some(_) => (),
    /// }
    /// ```
    /// This can't be a shared borrow because mutably borrowing `(*x as Some).0` should not checking
    /// the discriminant or accessing other variants, because the mutating `(*x as Some).0` can't
    /// affect the discriminant of `x`. E.g. the following is allowed:
    /// ```rust
    /// let mut x = Some(0);
    /// match x {
    ///     Some(_)
    ///         if {
    ///             if let Some(ref mut y) = x {
    ///                 *y += 1;
    ///             };
    ///             true
    ///         } => {}
    ///     _ => {}
    /// }
    /// ```
    Shallow,
    /// A shared (deep) borrow. Data must be immutable and is aliasable.
    ///
    /// This is used when lowering deref patterns, where shallow borrows wouldn't prevent something
    /// like:
    // ```compile_fail
    // let mut b = Box::new(false);
    // match b {
    //     deref!(true) => {} // not reached because `*b == false`
    //     _ if { *b = true; false } => {} // not reached because the guard is `false`
    //     deref!(false) => {} // not reached because the guard changed it
    //     // UB because we reached the unreachable.
    // }
    // ```
    Deep,
}

///////////////////////////////////////////////////////////////////////////
// Statements

/// The various kinds of statements that can appear in MIR.
///
/// Not all of these are allowed at every [`MirPhase`]. Check the documentation there to see which
/// ones you do not have to worry about. The MIR validator will generally enforce such restrictions,
/// causing an ICE if they are violated.
#[derive(Clone, Debug, PartialEq, TyEncodable, TyDecodable, Hash, HashStable)]
#[derive(TypeFoldable, TypeVisitable)]
pub enum StatementKind<'tcx> {
    /// Assign statements roughly correspond to an assignment in Rust proper (`x = ...`) except
    /// without the possibility of dropping the previous value (that must be done separately, if at
    /// all). The *exact* way this works is undecided. It probably does something like evaluating
    /// the LHS to a place and the RHS to a value, and then storing the value to the place. Various
    /// parts of this may do type specific things that are more complicated than simply copying
    /// bytes.
    ///
    /// **Needs clarification**: The implication of the above idea would be that assignment implies
    /// that the resulting value is initialized. I believe we could commit to this separately from
    /// committing to whatever part of the memory model we would need to decide on to make the above
    /// paragraph precise. Do we want to?
    ///
    /// Assignments in which the types of the place and rvalue differ are not well-formed.
    ///
    /// **Needs clarification**: Do we ever want to worry about non-free (in the body) lifetimes for
    /// the typing requirement in post drop-elaboration MIR? I think probably not - I'm not sure we
    /// could meaningfully require this anyway. How about free lifetimes? Is ignoring this
    /// interesting for optimizations? Do we want to allow such optimizations?
    ///
    /// **Needs clarification**: We currently require that the LHS place not overlap with any place
    /// read as part of computation of the RHS for some rvalues (generally those not producing
    /// primitives). This requirement is under discussion in [#68364]. As a part of this discussion,
    /// it is also unclear in what order the components are evaluated.
    ///
    /// [#68364]: https://github.com/rust-lang/rust/issues/68364
    ///
    /// See [`Rvalue`] documentation for details on each of those.
    Assign(Box<(Place<'tcx>, Rvalue<'tcx>)>),

    /// This represents all the reading that a pattern match may do (e.g., inspecting constants and
    /// discriminant values), and the kind of pattern it comes from. This is in order to adapt
    /// potential error messages to these specific patterns.
    ///
    /// Note that this also is emitted for regular `let` bindings to ensure that locals that are
    /// never accessed still get some sanity checks for, e.g., `let x: ! = ..;`
    ///
    /// When executed at runtime this is a nop.
    ///
    /// Disallowed after drop elaboration.
    FakeRead(Box<(FakeReadCause, Place<'tcx>)>),

    /// Write the discriminant for a variant to the enum Place.
    ///
    /// This is permitted for both coroutines and ADTs. This does not necessarily write to the
    /// entire place; instead, it writes to the minimum set of bytes as required by the layout for
    /// the type.
    SetDiscriminant { place: Box<Place<'tcx>>, variant_index: VariantIdx },

    /// Deinitializes the place.
    ///
    /// This writes `uninit` bytes to the entire place.
    Deinit(Box<Place<'tcx>>),

    /// `StorageLive` and `StorageDead` statements mark the live range of a local.
    ///
    /// At any point during the execution of a function, each local is either allocated or
    /// unallocated. Except as noted below, all locals except function parameters are initially
    /// unallocated. `StorageLive` statements cause memory to be allocated for the local while
    /// `StorageDead` statements cause the memory to be freed. In other words,
    /// `StorageLive`/`StorageDead` act like the heap operations `allocate`/`deallocate`, but for
    /// stack-allocated local variables. Using a local in any way (not only reading/writing from it)
    /// while it is unallocated is UB.
    ///
    /// Some locals have no `StorageLive` or `StorageDead` statements within the entire MIR body.
    /// These locals are implicitly allocated for the full duration of the function. There is a
    /// convenience method at `rustc_mir_dataflow::storage::always_storage_live_locals` for
    /// computing these locals.
    ///
    /// If the local is already allocated, calling `StorageLive` again will implicitly free the
    /// local and then allocate fresh uninitilized memory. If a local is already deallocated,
    /// calling `StorageDead` again is a NOP.
    StorageLive(Local),

    /// See `StorageLive` above.
    StorageDead(Local),

    /// Retag references in the given place, ensuring they got fresh tags.
    ///
    /// This is part of the Stacked Borrows model. These statements are currently only interpreted
    /// by miri and only generated when `-Z mir-emit-retag` is passed. See
    /// <https://internals.rust-lang.org/t/stacked-borrows-an-aliasing-model-for-rust/8153/> for
    /// more details.
    ///
    /// For code that is not specific to stacked borrows, you should consider retags to read and
    /// modify the place in an opaque way.
    ///
    /// Only `RetagKind::Default` and `RetagKind::FnEntry` are permitted.
    Retag(RetagKind, Box<Place<'tcx>>),

    /// This statement exists to preserve a trace of a scrutinee matched against a wildcard binding.
    /// This is especially useful for `let _ = PLACE;` bindings that desugar to a single
    /// `PlaceMention(PLACE)`.
    ///
    /// When executed at runtime, this computes the given place, but then discards
    /// it without doing a load. `let _ = *ptr;` is fine even if the pointer is dangling.
    PlaceMention(Box<Place<'tcx>>),

    /// Encodes a user's type ascription. These need to be preserved
    /// intact so that NLL can respect them. For example:
    /// ```ignore (illustrative)
    /// let a: T = y;
    /// ```
    /// The effect of this annotation is to relate the type `T_y` of the place `y`
    /// to the user-given type `T`. The effect depends on the specified variance:
    ///
    /// - `Covariant` -- requires that `T_y <: T`
    /// - `Contravariant` -- requires that `T_y :> T`
    /// - `Invariant` -- requires that `T_y == T`
    /// - `Bivariant` -- no effect
    ///
    /// When executed at runtime this is a nop.
    ///
    /// Disallowed after drop elaboration.
    AscribeUserType(Box<(Place<'tcx>, UserTypeProjection)>, ty::Variance),

    /// Carries control-flow-sensitive information injected by `-Cinstrument-coverage`,
    /// such as where to generate physical coverage-counter-increments during codegen.
    ///
    /// Coverage statements are used in conjunction with the coverage mappings and other
    /// information stored in the function's
    /// [`mir::Body::function_coverage_info`](crate::mir::Body::function_coverage_info).
    /// (For inlined MIR, take care to look up the *original function's* coverage info.)
    ///
    /// Interpreters and codegen backends that don't support coverage instrumentation
    /// can usually treat this as a no-op.
    Coverage(
        // Coverage statements are unlikely to ever contain type information in
        // the foreseeable future, so excluding them from TypeFoldable/TypeVisitable
        // avoids some unhelpful derive boilerplate.
        #[type_foldable(identity)]
        #[type_visitable(ignore)]
        CoverageKind,
    ),

    /// Denotes a call to an intrinsic that does not require an unwind path and always returns.
    /// This avoids adding a new block and a terminator for simple intrinsics.
    Intrinsic(Box<NonDivergingIntrinsic<'tcx>>),

    /// Instructs the const eval interpreter to increment a counter; this counter is used to track
    /// how many steps the interpreter has taken. It is used to prevent the user from writing const
    /// code that runs for too long or infinitely. Other than in the const eval interpreter, this
    /// is a no-op.
    ConstEvalCounter,

    /// No-op. Useful for deleting instructions without affecting statement indices.
    Nop,

    /// Marker statement indicating where `place` would be dropped.
    /// This is semantically equivalent to `Nop`, so codegen and MIRI should interpret this
    /// statement as such.
    /// The only use case of this statement is for linting in MIR to detect temporary lifetime
    /// changes.
    BackwardIncompatibleDropHint {
        /// Place to drop
        place: Box<Place<'tcx>>,
        /// Reason for backward incompatibility
        reason: BackwardIncompatibleDropReason,
    },
}

#[derive(
    Clone,
    TyEncodable,
    TyDecodable,
    Debug,
    PartialEq,
    Hash,
    HashStable,
    TypeFoldable,
    TypeVisitable
)]
pub enum NonDivergingIntrinsic<'tcx> {
    /// Denotes a call to the intrinsic function `assume`.
    ///
    /// The operand must be a boolean. Optimizers may use the value of the boolean to backtrack its
    /// computation to infer information about other variables. So if the boolean came from a
    /// `x < y` operation, subsequent operations on `x` and `y` could elide various bound checks.
    /// If the argument is `false`, this operation is equivalent to `TerminatorKind::Unreachable`.
    Assume(Operand<'tcx>),

    /// Denotes a call to the intrinsic function `copy_nonoverlapping`.
    ///
    /// First, all three operands are evaluated. `src` and `dest` must each be a reference, pointer,
    /// or `Box` pointing to the same type `T`. `count` must evaluate to a `usize`. Then, `src` and
    /// `dest` are dereferenced, and `count * size_of::<T>()` bytes beginning with the first byte of
    /// the `src` place are copied to the contiguous range of bytes beginning with the first byte
    /// of `dest`.
    ///
    /// **Needs clarification**: In what order are operands computed and dereferenced? It should
    /// probably match the order for assignment, but that is also undecided.
    ///
    /// **Needs clarification**: Is this typed or not, ie is there a typed load and store involved?
    /// I vaguely remember Ralf saying somewhere that he thought it should not be.
    CopyNonOverlapping(CopyNonOverlapping<'tcx>),
}

/// Describes what kind of retag is to be performed.
#[derive(Copy, Clone, TyEncodable, TyDecodable, Debug, PartialEq, Eq, Hash, HashStable)]
#[rustc_pass_by_value]
pub enum RetagKind {
    /// The initial retag of arguments when entering a function.
    FnEntry,
    /// Retag preparing for a two-phase borrow.
    TwoPhase,
    /// Retagging raw pointers.
    Raw,
    /// A "normal" retag.
    Default,
}

/// The `FakeReadCause` describes the type of pattern why a FakeRead statement exists.
#[derive(Copy, Clone, TyEncodable, TyDecodable, Debug, Hash, HashStable, PartialEq)]
pub enum FakeReadCause {
    /// Inject a fake read of the borrowed input at the end of each guards
    /// code.
    ///
    /// This should ensure that you cannot change the variant for an enum while
    /// you are in the midst of matching on it.
    ForMatchGuard,

    /// `let x: !; match x {}` doesn't generate any read of x so we need to
    /// generate a read of x to check that it is initialized and safe.
    ///
    /// If a closure pattern matches a Place starting with an Upvar, then we introduce a
    /// FakeRead for that Place outside the closure, in such a case this option would be
    /// Some(closure_def_id).
    /// Otherwise, the value of the optional LocalDefId will be None.
    //
    // We can use LocalDefId here since fake read statements are removed
    // before codegen in the `CleanupNonCodegenStatements` pass.
    ForMatchedPlace(Option<LocalDefId>),

    /// A fake read of the RefWithinGuard version of a bind-by-value variable
    /// in a match guard to ensure that its value hasn't change by the time
    /// we create the OutsideGuard version.
    ForGuardBinding,

    /// Officially, the semantics of
    ///
    /// `let pattern = <expr>;`
    ///
    /// is that `<expr>` is evaluated into a temporary and then this temporary is
    /// into the pattern.
    ///
    /// However, if we see the simple pattern `let var = <expr>`, we optimize this to
    /// evaluate `<expr>` directly into the variable `var`. This is mostly unobservable,
    /// but in some cases it can affect the borrow checker, as in #53695.
    /// Therefore, we insert a "fake read" here to ensure that we get
    /// appropriate errors.
    ///
    /// If a closure pattern matches a Place starting with an Upvar, then we introduce a
    /// FakeRead for that Place outside the closure, in such a case this option would be
    /// Some(closure_def_id).
    /// Otherwise, the value of the optional DefId will be None.
    ForLet(Option<LocalDefId>),

    /// If we have an index expression like
    ///
    /// (*x)[1][{ x = y; 4}]
    ///
    /// then the first bounds check is invalidated when we evaluate the second
    /// index expression. Thus we create a fake borrow of `x` across the second
    /// indexer, which will cause a borrow check error.
    ForIndex,
}

#[derive(Clone, Debug, PartialEq, TyEncodable, TyDecodable, Hash, HashStable)]
#[derive(TypeFoldable, TypeVisitable)]
pub struct CopyNonOverlapping<'tcx> {
    pub src: Operand<'tcx>,
    pub dst: Operand<'tcx>,
    /// Number of elements to copy from src to dest, not bytes.
    pub count: Operand<'tcx>,
}

/// Represents how a [`TerminatorKind::Call`] was constructed.
/// Used only for diagnostics.
#[derive(Clone, Copy, TyEncodable, TyDecodable, Debug, PartialEq, Hash, HashStable)]
#[derive(TypeFoldable, TypeVisitable)]
pub enum CallSource {
    /// This came from something such as `a > b` or `a + b`. In THIR, if `from_hir_call`
    /// is false then this is the desugaring.
    OverloadedOperator,
    /// This was from comparison generated by a match, used by const-eval for better errors
    /// when the comparison cannot be done in compile time.
    ///
    /// (see <https://github.com/rust-lang/rust/issues/90237>)
    MatchCmp,
    /// Other types of desugaring that did not come from the HIR, but we don't care about
    /// for diagnostics (yet).
    Misc,
    /// Normal function call, no special source
    Normal,
}

#[derive(Clone, Copy, Debug, TyEncodable, TyDecodable, Hash, HashStable, PartialEq)]
#[derive(TypeFoldable, TypeVisitable)]
/// The macro that an inline assembly block was created by
pub enum InlineAsmMacro {
    /// The `asm!` macro
    Asm,
    /// The `naked_asm!` macro
    NakedAsm,
}

///////////////////////////////////////////////////////////////////////////
// Terminators

/// The various kinds of terminators, representing ways of exiting from a basic block.
///
/// A note on unwinding: Panics may occur during the execution of some terminators. Depending on the
/// `-C panic` flag, this may either cause the program to abort or the call stack to unwind. Such
/// terminators have a `unwind: UnwindAction` field on them. If stack unwinding occurs, then
/// once the current function is reached, an action will be taken based on the `unwind` field.
/// If the action is `Cleanup`, then the execution continues at the given basic block. If the
/// action is `Continue` then no cleanup is performed, and the stack continues unwinding.
///
/// The basic block pointed to by a `Cleanup` unwind action must have its `cleanup` flag set.
/// `cleanup` basic blocks have a couple restrictions:
///  1. All `unwind` fields in them must be `UnwindAction::Terminate` or `UnwindAction::Unreachable`.
///  2. `Return` terminators are not allowed in them. `Terminate` and `Resume` terminators are.
///  3. All other basic blocks (in the current body) that are reachable from `cleanup` basic blocks
///     must also be `cleanup`. This is a part of the type system and checked statically, so it is
///     still an error to have such an edge in the CFG even if it's known that it won't be taken at
///     runtime.
///  4. The control flow between cleanup blocks must look like an upside down tree. Roughly
///     speaking, this means that control flow that looks like a V is allowed, while control flow
///     that looks like a W is not. This is necessary to ensure that landing pad information can be
///     correctly codegened on MSVC. More precisely:
///
///     Begin with the standard control flow graph `G`. Modify `G` as follows: for any two cleanup
///     vertices `u` and `v` such that `u` dominates `v`, contract `u` and `v` into a single vertex,
///     deleting self edges and duplicate edges in the process. Now remove all vertices from `G`
///     that are not cleanup vertices or are not reachable. The resulting graph must be an inverted
///     tree, that is each vertex may have at most one successor and there may be no cycles.
#[derive(Clone, TyEncodable, TyDecodable, Hash, HashStable, PartialEq, TypeFoldable, TypeVisitable)]
pub enum TerminatorKind<'tcx> {
    /// Block has one successor; we continue execution there.
    Goto { target: BasicBlock },

    /// Switches based on the computed value.
    ///
    /// First, evaluates the `discr` operand. The type of the operand must be a signed or unsigned
    /// integer, char, or bool, and must match the given type. Then, if the list of switch targets
    /// contains the computed value, continues execution at the associated basic block. Otherwise,
    /// continues execution at the "otherwise" basic block.
    ///
    /// Target values may not appear more than once.
    SwitchInt {
        /// The discriminant value being tested.
        discr: Operand<'tcx>,
        targets: SwitchTargets,
    },

    /// Indicates that the landing pad is finished and that the process should continue unwinding.
    ///
    /// Like a return, this marks the end of this invocation of the function.
    ///
    /// Only permitted in cleanup blocks. `Resume` is not permitted with `-C unwind=abort` after
    /// deaggregation runs.
    UnwindResume,

    /// Indicates that the landing pad is finished and that the process should terminate.
    ///
    /// Used to prevent unwinding for foreign items or with `-C unwind=abort`. Only permitted in
    /// cleanup blocks.
    UnwindTerminate(UnwindTerminateReason),

    /// Returns from the function.
    ///
    /// Like function calls, the exact semantics of returns in Rust are unclear. Returning very
    /// likely at least assigns the value currently in the return place (`_0`) to the place
    /// specified in the associated `Call` terminator in the calling function, as if assigned via
    /// `dest = move _0`. It might additionally do other things, like have side-effects in the
    /// aliasing model.
    ///
    /// If the body is a coroutine body, this has slightly different semantics; it instead causes a
    /// `CoroutineState::Returned(_0)` to be created (as if by an `Aggregate` rvalue) and assigned
    /// to the return place.
    Return,

    /// Indicates a terminator that can never be reached.
    ///
    /// Executing this terminator is UB.
    Unreachable,

    /// The behavior of this statement differs significantly before and after drop elaboration.
    ///
    /// After drop elaboration: `Drop` terminators are a complete nop for types that have no drop
    /// glue. For other types, `Drop` terminators behave exactly like a call to
    /// `core::mem::drop_in_place` with a pointer to the given place.
    ///
    /// `Drop` before drop elaboration is a *conditional* execution of the drop glue. Specifically,
    /// the `Drop` will be executed if...
    ///
    /// **Needs clarification**: End of that sentence. This in effect should document the exact
    /// behavior of drop elaboration. The following sounds vaguely right, but I'm not quite sure:
    ///
    /// > The drop glue is executed if, among all statements executed within this `Body`, an assignment to
    /// > the place or one of its "parents" occurred more recently than a move out of it. This does not
    /// > consider indirect assignments.
    ///
    /// The `replace` flag indicates whether this terminator was created as part of an assignment.
    /// This should only be used for diagnostic purposes, and does not have any operational
    /// meaning.
    Drop { place: Place<'tcx>, target: BasicBlock, unwind: UnwindAction, replace: bool },

    /// Roughly speaking, evaluates the `func` operand and the arguments, and starts execution of
    /// the referred to function. The operand types must match the argument types of the function.
    /// The return place type must match the return type. The type of the `func` operand must be
    /// callable, meaning either a function pointer, a function type, or a closure type.
    ///
    /// **Needs clarification**: The exact semantics of this. Current backends rely on `move`
    /// operands not aliasing the return place. It is unclear how this is justified in MIR, see
    /// [#71117].
    ///
    /// [#71117]: https://github.com/rust-lang/rust/issues/71117
    Call {
        /// The function that’s being called.
        func: Operand<'tcx>,
        /// Arguments the function is called with.
        /// These are owned by the callee, which is free to modify them.
        /// This allows the memory occupied by "by-value" arguments to be
        /// reused across function calls without duplicating the contents.
        /// The span for each arg is also included
        /// (e.g. `a` and `b` in `x.foo(a, b)`).
        args: Box<[Spanned<Operand<'tcx>>]>,
        /// Where the returned value will be written
        destination: Place<'tcx>,
        /// Where to go after this call returns. If none, the call necessarily diverges.
        target: Option<BasicBlock>,
        /// Action to be taken if the call unwinds.
        unwind: UnwindAction,
        /// Where this call came from in HIR/THIR.
        call_source: CallSource,
        /// This `Span` is the span of the function, without the dot and receiver
        /// e.g. `foo(a, b)` in `x.foo(a, b)`
        fn_span: Span,
    },

    /// Tail call.
    ///
    /// Roughly speaking this is a chimera of [`Call`] and [`Return`], with some caveats.
    /// Semantically tail calls consists of two actions:
    /// - pop of the current stack frame
    /// - a call to the `func`, with the return address of the **current** caller
    ///   - so that a `return` inside `func` returns to the caller of the caller
    ///     of the function that is currently being executed
    ///
    /// Note that in difference with [`Call`] this is missing
    /// - `destination` (because it's always the return place)
    /// - `target` (because it's always taken from the current stack frame)
    /// - `unwind` (because it's always taken from the current stack frame)
    ///
    /// [`Call`]: TerminatorKind::Call
    /// [`Return`]: TerminatorKind::Return
    TailCall {
        /// The function that’s being called.
        func: Operand<'tcx>,
        /// Arguments the function is called with.
        /// These are owned by the callee, which is free to modify them.
        /// This allows the memory occupied by "by-value" arguments to be
        /// reused across function calls without duplicating the contents.
        args: Box<[Spanned<Operand<'tcx>>]>,
        // FIXME(explicit_tail_calls): should we have the span for `become`? is this span accurate? do we need it?
        /// This `Span` is the span of the function, without the dot and receiver
        /// (e.g. `foo(a, b)` in `x.foo(a, b)`
        fn_span: Span,
    },

    /// Evaluates the operand, which must have type `bool`. If it is not equal to `expected`,
    /// initiates a panic. Initiating a panic corresponds to a `Call` terminator with some
    /// unspecified constant as the function to call, all the operands stored in the `AssertMessage`
    /// as parameters, and `None` for the destination. Keep in mind that the `cleanup` path is not
    /// necessarily executed even in the case of a panic, for example in `-C panic=abort`. If the
    /// assertion does not fail, execution continues at the specified basic block.
    ///
    /// When overflow checking is disabled and this is run-time MIR (as opposed to compile-time MIR
    /// that is used for CTFE), the following variants of this terminator behave as `goto target`:
    /// - `OverflowNeg(..)`,
    /// - `Overflow(op, ..)` if op is add, sub, mul, shl, shr, but NOT div or rem.
    Assert {
        cond: Operand<'tcx>,
        expected: bool,
        msg: Box<AssertMessage<'tcx>>,
        target: BasicBlock,
        unwind: UnwindAction,
    },

    /// Marks a suspend point.
    ///
    /// Like `Return` terminators in coroutine bodies, this computes `value` and then a
    /// `CoroutineState::Yielded(value)` as if by `Aggregate` rvalue. That value is then assigned to
    /// the return place of the function calling this one, and execution continues in the calling
    /// function. When next invoked with the same first argument, execution of this function
    /// continues at the `resume` basic block, with the second argument written to the `resume_arg`
    /// place. If the coroutine is dropped before then, the `drop` basic block is invoked.
    ///
    /// Note that coroutines can be (unstably) cloned under certain conditions, which means that
    /// this terminator can **return multiple times**! MIR optimizations that reorder code into
    /// different basic blocks needs to be aware of that.
    /// See <https://github.com/rust-lang/rust/issues/95360>.
    ///
    /// Not permitted in bodies that are not coroutine bodies, or after coroutine lowering.
    ///
    /// **Needs clarification**: What about the evaluation order of the `resume_arg` and `value`?
    Yield {
        /// The value to return.
        value: Operand<'tcx>,
        /// Where to resume to.
        resume: BasicBlock,
        /// The place to store the resume argument in.
        resume_arg: Place<'tcx>,
        /// Cleanup to be done if the coroutine is dropped at this suspend point.
        drop: Option<BasicBlock>,
    },

    /// Indicates the end of dropping a coroutine.
    ///
    /// Semantically just a `return` (from the coroutines drop glue). Only permitted in the same situations
    /// as `yield`.
    ///
    /// **Needs clarification**: Is that even correct? The coroutine drop code is always confusing
    /// to me, because it's not even really in the current body.
    ///
    /// **Needs clarification**: Are there type system constraints on these terminators? Should
    /// there be a "block type" like `cleanup` blocks for them?
    CoroutineDrop,

    /// A block where control flow only ever takes one real path, but borrowck needs to be more
    /// conservative.
    ///
    /// At runtime this is semantically just a goto.
    ///
    /// Disallowed after drop elaboration.
    FalseEdge {
        /// The target normal control flow will take.
        real_target: BasicBlock,
        /// A block control flow could conceptually jump to, but won't in
        /// practice.
        imaginary_target: BasicBlock,
    },

    /// A terminator for blocks that only take one path in reality, but where we reserve the right
    /// to unwind in borrowck, even if it won't happen in practice. This can arise in infinite loops
    /// with no function calls for example.
    ///
    /// At runtime this is semantically just a goto.
    ///
    /// Disallowed after drop elaboration.
    FalseUnwind {
        /// The target normal control flow will take.
        real_target: BasicBlock,
        /// The imaginary cleanup block link. This particular path will never be taken
        /// in practice, but in order to avoid fragility we want to always
        /// consider it in borrowck. We don't want to accept programs which
        /// pass borrowck only when `panic=abort` or some assertions are disabled
        /// due to release vs. debug mode builds.
        unwind: UnwindAction,
    },

    /// Block ends with an inline assembly block. This is a terminator since
    /// inline assembly is allowed to diverge.
    InlineAsm {
        /// Macro used to create this inline asm: one of `asm!` or `naked_asm!`
        asm_macro: InlineAsmMacro,

        /// The template for the inline assembly, with placeholders.
        template: &'tcx [InlineAsmTemplatePiece],

        /// The operands for the inline assembly, as `Operand`s or `Place`s.
        operands: Box<[InlineAsmOperand<'tcx>]>,

        /// Miscellaneous options for the inline assembly.
        options: InlineAsmOptions,

        /// Source spans for each line of the inline assembly code. These are
        /// used to map assembler errors back to the line in the source code.
        line_spans: &'tcx [Span],

        /// Valid targets for the inline assembly.
        /// The first element is the fallthrough destination, unless
        /// asm_macro == InlineAsmMacro::NakedAsm or InlineAsmOptions::NORETURN is set.
        targets: Box<[BasicBlock]>,

        /// Action to be taken if the inline assembly unwinds. This is present
        /// if and only if InlineAsmOptions::MAY_UNWIND is set.
        unwind: UnwindAction,
    },
}

#[derive(
    Clone,
    Debug,
    TyEncodable,
    TyDecodable,
    Hash,
    HashStable,
    PartialEq,
    TypeFoldable,
    TypeVisitable
)]
pub enum BackwardIncompatibleDropReason {
    Edition2024,
}

#[derive(Debug, Clone, TyEncodable, TyDecodable, Hash, HashStable, PartialEq)]
pub struct SwitchTargets {
    /// Possible values. For each value, the location to branch to is found in
    /// the corresponding element in the `targets` vector.
    pub(super) values: SmallVec<[Pu128; 1]>,

    /// Possible branch targets. The last element of this vector is used for
    /// the "otherwise" branch, so `targets.len() == values.len() + 1` always
    /// holds.
    //
    // Note: This invariant is non-obvious and easy to violate. This would be a
    // more rigorous representation:
    //
    //   normal: SmallVec<[(Pu128, BasicBlock); 1]>,
    //   otherwise: BasicBlock,
    //
    // But it's important to have the targets in a sliceable type, because
    // target slices show up elsewhere. E.g. `TerminatorKind::InlineAsm` has a
    // boxed slice, and `TerminatorKind::FalseEdge` has a single target that
    // can be converted to a slice with `slice::from_ref`.
    //
    // Why does this matter? In functions like `TerminatorKind::successors` we
    // return `impl Iterator` and a non-slice-of-targets representation here
    // causes problems because multiple different concrete iterator types would
    // be involved and we would need a boxed trait object, which requires an
    // allocation, which is expensive if done frequently.
    pub(super) targets: SmallVec<[BasicBlock; 2]>,
}

/// Action to be taken when a stack unwind happens.
#[derive(Copy, Clone, Debug, PartialEq, Eq, TyEncodable, TyDecodable, Hash, HashStable)]
#[derive(TypeFoldable, TypeVisitable)]
pub enum UnwindAction {
    /// No action is to be taken. Continue unwinding.
    ///
    /// This is similar to `Cleanup(bb)` where `bb` does nothing but `Resume`, but they are not
    /// equivalent, as presence of `Cleanup(_)` will make a frame non-POF.
    Continue,
    /// Triggers undefined behavior if unwind happens.
    Unreachable,
    /// Terminates the execution if unwind happens.
    ///
    /// Depending on the platform and situation this may cause a non-unwindable panic or abort.
    Terminate(UnwindTerminateReason),
    /// Cleanups to be done.
    Cleanup(BasicBlock),
}

/// The reason we are terminating the process during unwinding.
#[derive(Copy, Clone, Debug, PartialEq, Eq, TyEncodable, TyDecodable, Hash, HashStable)]
#[derive(TypeFoldable, TypeVisitable)]
pub enum UnwindTerminateReason {
    /// Unwinding is just not possible given the ABI of this function.
    Abi,
    /// We were already cleaning up for an ongoing unwind, and a *second*, *nested* unwind was
    /// triggered by the drop glue.
    InCleanup,
}

/// Information about an assertion failure.
#[derive(Clone, Hash, HashStable, PartialEq, Debug)]
#[derive(TyEncodable, TyDecodable, TypeFoldable, TypeVisitable)]
pub enum AssertKind<O> {
    BoundsCheck { len: O, index: O },
    Overflow(BinOp, O, O),
    OverflowNeg(O),
    DivisionByZero(O),
    RemainderByZero(O),
    ResumedAfterReturn(CoroutineKind),
    ResumedAfterPanic(CoroutineKind),
    MisalignedPointerDereference { required: O, found: O },
    NullPointerDereference,
}

#[derive(Clone, Debug, PartialEq, TyEncodable, TyDecodable, Hash, HashStable)]
#[derive(TypeFoldable, TypeVisitable)]
pub enum InlineAsmOperand<'tcx> {
    In {
        reg: InlineAsmRegOrRegClass,
        value: Operand<'tcx>,
    },
    Out {
        reg: InlineAsmRegOrRegClass,
        late: bool,
        place: Option<Place<'tcx>>,
    },
    InOut {
        reg: InlineAsmRegOrRegClass,
        late: bool,
        in_value: Operand<'tcx>,
        out_place: Option<Place<'tcx>>,
    },
    Const {
        value: Box<ConstOperand<'tcx>>,
    },
    SymFn {
        value: Box<ConstOperand<'tcx>>,
    },
    SymStatic {
        def_id: DefId,
    },
    Label {
        /// This represents the index into the `targets` array in `TerminatorKind::InlineAsm`.
        target_index: usize,
    },
}

/// Type for MIR `Assert` terminator error messages.
pub type AssertMessage<'tcx> = AssertKind<Operand<'tcx>>;

///////////////////////////////////////////////////////////////////////////
// Places

/// Places roughly correspond to a "location in memory." Places in MIR are the same mathematical
/// object as places in Rust. This of course means that what exactly they are is undecided and part
/// of the Rust memory model. However, they will likely contain at least the following pieces of
/// information in some form:
///
///  1. The address in memory that the place refers to.
///  2. The provenance with which the place is being accessed.
///  3. The type of the place and an optional variant index. See [`PlaceTy`][super::PlaceTy].
///  4. Optionally, some metadata. This exists if and only if the type of the place is not `Sized`.
///
/// We'll give a description below of how all pieces of the place except for the provenance are
/// calculated. We cannot give a description of the provenance, because that is part of the
/// undecided aliasing model - we only include it here at all to acknowledge its existence.
///
/// Each local naturally corresponds to the place `Place { local, projection: [] }`. This place has
/// the address of the local's allocation and the type of the local.
///
/// **Needs clarification:** Unsized locals seem to present a bit of an issue. Their allocation
/// can't actually be created on `StorageLive`, because it's unclear how big to make the allocation.
/// Furthermore, MIR produces assignments to unsized locals, although that is not permitted under
/// `#![feature(unsized_locals)]` in Rust. Besides just putting "unsized locals are special and
/// different" in a bunch of places, I (JakobDegen) don't know how to incorporate this behavior into
/// the current MIR semantics in a clean way - possibly this needs some design work first.
///
/// For places that are not locals, ie they have a non-empty list of projections, we define the
/// values as a function of the parent place, that is the place with its last [`ProjectionElem`]
/// stripped. The way this is computed of course depends on the kind of that last projection
/// element:
///
///  - [`Downcast`](ProjectionElem::Downcast): This projection sets the place's variant index to the
///    given one, and makes no other changes. A `Downcast` projection must always be followed
///    immediately by a `Field` projection.
///  - [`Field`](ProjectionElem::Field): `Field` projections take their parent place and create a
///    place referring to one of the fields of the type. The resulting address is the parent
///    address, plus the offset of the field. The type becomes the type of the field. If the parent
///    was unsized and so had metadata associated with it, then the metadata is retained if the
///    field is unsized and thrown out if it is sized.
///
///    These projections are only legal for tuples, ADTs, closures, and coroutines. If the ADT or
///    coroutine has more than one variant, the parent place's variant index must be set, indicating
///    which variant is being used. If it has just one variant, the variant index may or may not be
///    included - the single possible variant is inferred if it is not included.
///  - [`OpaqueCast`](ProjectionElem::OpaqueCast): This projection changes the place's type to the
///    given one, and makes no other changes. A `OpaqueCast` projection on any type other than an
///    opaque type from the current crate is not well-formed.
///  - [`ConstantIndex`](ProjectionElem::ConstantIndex): Computes an offset in units of `T` into the
///    place as described in the documentation for the `ProjectionElem`. The resulting address is
///    the parent's address plus that offset, and the type is `T`. This is only legal if the parent
///    place has type `[T;  N]` or `[T]` (*not* `&[T]`). Since such a `T` is always sized, any
///    resulting metadata is thrown out.
///  - [`Subslice`](ProjectionElem::Subslice): This projection calculates an offset and a new
///    address in a similar manner as `ConstantIndex`. It is also only legal on `[T; N]` and `[T]`.
///    However, this yields a `Place` of type `[T]`, and additionally sets the metadata to be the
///    length of the subslice.
///  - [`Index`](ProjectionElem::Index): Like `ConstantIndex`, only legal on `[T; N]` or `[T]`.
///    However, `Index` additionally takes a local from which the value of the index is computed at
///    runtime. Computing the value of the index involves interpreting the `Local` as a
///    `Place { local, projection: [] }`, and then computing its value as if done via
///    [`Operand::Copy`]. The array/slice is then indexed with the resulting value. The local must
///    have type `usize`.
///  - [`Deref`](ProjectionElem::Deref): Derefs are the last type of projection, and the most
///    complicated. They are only legal on parent places that are references, pointers, or `Box`. A
///    `Deref` projection begins by loading a value from the parent place, as if by
///    [`Operand::Copy`]. It then dereferences the resulting pointer, creating a place of the
///    pointee's type. The resulting address is the address that was stored in the pointer. If the
///    pointee type is unsized, the pointer additionally stored the value of the metadata.
///
/// The "validity invariant" of places is the same as that of raw pointers, meaning that e.g.
/// `*ptr` on a dangling or unaligned pointer is never UB. (Later doing a load/store on that place
/// or turning it into a reference can be UB though!) The only ways for a place computation can
/// cause UB are:
/// - On a `Deref` projection, we do an actual load of the inner place, with all the usual
///   consequences (the inner place must be based on an aligned pointer, it must point to allocated
///   memory, the aliasig model must allow reads, this must not be a data race).
/// - For the projections that perform pointer arithmetic, the offset must in-bounds of an
///   allocation (i.e., the preconditions of `ptr::offset` must be met).
#[derive(Copy, Clone, PartialEq, Eq, Hash, TyEncodable, HashStable, TypeFoldable, TypeVisitable)]
pub struct Place<'tcx> {
    pub local: Local,

    /// projection out of a place (access a field, deref a pointer, etc)
    pub projection: &'tcx List<PlaceElem<'tcx>>,
}

#[derive(Copy, Clone, Debug, PartialEq, Eq, Hash)]
#[derive(TyEncodable, TyDecodable, HashStable, TypeFoldable, TypeVisitable)]
pub enum ProjectionElem<V, T> {
    Deref,

    /// A field (e.g., `f` in `_1.f`) is one variant of [`ProjectionElem`]. Conceptually,
    /// rustc can identify that a field projection refers to either two different regions of memory
    /// or the same one between the base and the 'projection element'.
    /// Read more about projections in the [rustc-dev-guide][mir-datatypes]
    ///
    /// [mir-datatypes]: https://rustc-dev-guide.rust-lang.org/mir/index.html#mir-data-types
    Field(FieldIdx, T),

    /// Index into a slice/array.
    ///
    /// Note that this does not also dereference, and so it does not exactly correspond to slice
    /// indexing in Rust. In other words, in the below Rust code:
    ///
    /// ```rust
    /// let x = &[1, 2, 3, 4];
    /// let i = 2;
    /// x[i];
    /// ```
    ///
    /// The `x[i]` is turned into a `Deref` followed by an `Index`, not just an `Index`. The same
    /// thing is true of the `ConstantIndex` and `Subslice` projections below.
    Index(V),

    /// These indices are generated by slice patterns. Easiest to explain
    /// by example:
    ///
    /// ```ignore (illustrative)
    /// [X, _, .._, _, _] => { offset: 0, min_length: 4, from_end: false },
    /// [_, X, .._, _, _] => { offset: 1, min_length: 4, from_end: false },
    /// [_, _, .._, X, _] => { offset: 2, min_length: 4, from_end: true },
    /// [_, _, .._, _, X] => { offset: 1, min_length: 4, from_end: true },
    /// ```
    ConstantIndex {
        /// index or -index (in Python terms), depending on from_end
        offset: u64,
        /// The thing being indexed must be at least this long -- otherwise, the
        /// projection is UB.
        ///
        /// For arrays this is always the exact length.
        min_length: u64,
        /// Counting backwards from end? This is always false when indexing an
        /// array.
        from_end: bool,
    },

    /// These indices are generated by slice patterns.
    ///
    /// If `from_end` is true `slice[from..slice.len() - to]`.
    /// Otherwise `array[from..to]`.
    Subslice {
        from: u64,
        to: u64,
        /// Whether `to` counts from the start or end of the array/slice.
        /// For `PlaceElem`s this is `true` if and only if the base is a slice.
        /// For `ProjectionKind`, this can also be `true` for arrays.
        from_end: bool,
    },

    /// "Downcast" to a variant of an enum or a coroutine.
    ///
    /// The included Symbol is the name of the variant, used for printing MIR.
    ///
    /// This operation itself is never UB, all it does is change the type of the place.
    Downcast(Option<Symbol>, VariantIdx),

    /// Like an explicit cast from an opaque type to a concrete type, but without
    /// requiring an intermediate variable.
    OpaqueCast(T),

    /// A transmute from an unsafe binder to the type that it wraps. This is a projection
    /// of a place, so it doesn't necessarily constitute a move out of the binder.
    UnwrapUnsafeBinder(T),

    /// A `Subtype(T)` projection is applied to any `StatementKind::Assign` where
    /// type of lvalue doesn't match the type of rvalue, the primary goal is making subtyping
    /// explicit during optimizations and codegen.
    ///
    /// This projection doesn't impact the runtime behavior of the program except for potentially changing
    /// some type metadata of the interpreter or codegen backend.
    ///
    /// This goal is achieved with mir_transform pass `Subtyper`, which runs right after
    /// borrowchecker, as we only care about subtyping that can affect trait selection and
    /// `TypeId`.
    Subtype(T),
}

/// Alias for projections as they appear in places, where the base is a place
/// and the index is a local.
pub type PlaceElem<'tcx> = ProjectionElem<Local, Ty<'tcx>>;

///////////////////////////////////////////////////////////////////////////
// Operands

/// An operand in MIR represents a "value" in Rust, the definition of which is undecided and part of
/// the memory model. One proposal for a definition of values can be found [on UCG][value-def].
///
/// [value-def]: https://github.com/rust-lang/unsafe-code-guidelines/blob/master/wip/value-domain.md
///
/// The most common way to create values is via loading a place. Loading a place is an operation
/// which reads the memory of the place and converts it to a value. This is a fundamentally *typed*
/// operation. The nature of the value produced depends on the type of the conversion. Furthermore,
/// there may be other effects: if the type has a validity constraint loading the place might be UB
/// if the validity constraint is not met.
///
/// **Needs clarification:** Is loading a place that has its variant index set well-formed? Miri
/// currently implements it, but it seems like this may be something to check against in the
/// validator.
#[derive(Clone, PartialEq, TyEncodable, TyDecodable, Hash, HashStable, TypeFoldable, TypeVisitable)]
pub enum Operand<'tcx> {
    /// Creates a value by loading the given place.
    ///
    /// Before drop elaboration, the type of the place must be `Copy`. After drop elaboration there
    /// is no such requirement.
    Copy(Place<'tcx>),

    /// Creates a value by performing loading the place, just like the `Copy` operand.
    ///
    /// This *may* additionally overwrite the place with `uninit` bytes, depending on how we decide
    /// in [UCG#188]. You should not emit MIR that may attempt a subsequent second load of this
    /// place without first re-initializing it.
    ///
    /// **Needs clarification:** The operational impact of `Move` is unclear. Currently (both in
    /// Miri and codegen) it has no effect at all unless it appears in an argument to `Call`; for
    /// `Call` it allows the argument to be passed to the callee "in-place", i.e. the callee might
    /// just get a reference to this place instead of a full copy. Miri implements this with a
    /// combination of aliasing model "protectors" and putting `uninit` into the place. Ralf
    /// proposes that we don't want these semantics for `Move` in regular assignments, because
    /// loading a place should not have side-effects, and the aliasing model "protectors" are
    /// inherently tied to a function call. Are these the semantics we want for MIR? Is this
    /// something we can even decide without knowing more about Rust's memory model?
    ///
    /// [UCG#188]: https://github.com/rust-lang/unsafe-code-guidelines/issues/188
    Move(Place<'tcx>),

    /// Constants are already semantically values, and remain unchanged.
    Constant(Box<ConstOperand<'tcx>>),
}

#[derive(Clone, Copy, PartialEq, TyEncodable, TyDecodable, Hash, HashStable)]
#[derive(TypeFoldable, TypeVisitable)]
pub struct ConstOperand<'tcx> {
    pub span: Span,

    /// Optional user-given type: for something like
    /// `collect::<Vec<_>>`, this would be present and would
    /// indicate that `Vec<_>` was explicitly specified.
    ///
    /// Needed for NLL to impose user-given type constraints.
    pub user_ty: Option<UserTypeAnnotationIndex>,

    pub const_: Const<'tcx>,
}

///////////////////////////////////////////////////////////////////////////
// Rvalues

/// The various kinds of rvalues that can appear in MIR.
///
/// Not all of these are allowed at every [`MirPhase`] - when this is the case, it's stated below.
///
/// Computing any rvalue begins by evaluating the places and operands in some order (**Needs
/// clarification**: Which order?). These are then used to produce a "value" - the same kind of
/// value that an [`Operand`] produces.
#[derive(Clone, TyEncodable, TyDecodable, Hash, HashStable, PartialEq, TypeFoldable, TypeVisitable)]
pub enum Rvalue<'tcx> {
    /// Yields the operand unchanged
    Use(Operand<'tcx>),

    /// Creates an array where each element is the value of the operand.
    ///
    /// This is the cause of a bug in the case where the repetition count is zero because the value
    /// is not dropped, see [#74836].
    ///
    /// Corresponds to source code like `[x; 32]`.
    ///
    /// [#74836]: https://github.com/rust-lang/rust/issues/74836
    Repeat(Operand<'tcx>, ty::Const<'tcx>),

    /// Creates a reference of the indicated kind to the place.
    ///
    /// There is not much to document here, because besides the obvious parts the semantics of this
    /// are essentially entirely a part of the aliasing model. There are many UCG issues discussing
    /// exactly what the behavior of this operation should be.
    ///
    /// `Shallow` borrows are disallowed after drop lowering.
    Ref(Region<'tcx>, BorrowKind, Place<'tcx>),

    /// Creates a pointer/reference to the given thread local.
    ///
    /// The yielded type is a `*mut T` if the static is mutable, otherwise if the static is extern a
    /// `*const T`, and if neither of those apply a `&T`.
    ///
    /// **Note:** This is a runtime operation that actually executes code and is in this sense more
    /// like a function call. Also, eliminating dead stores of this rvalue causes `fn main() {}` to
    /// SIGILL for some reason that I (JakobDegen) never got a chance to look into.
    ///
    /// **Needs clarification**: Are there weird additional semantics here related to the runtime
    /// nature of this operation?
    ThreadLocalRef(DefId),

    /// Creates a raw pointer with the indicated mutability to the place.
    ///
    /// This is generated by pointer casts like `&v as *const _` or raw borrow expressions like
    /// `&raw const v`.
    ///
    /// Like with references, the semantics of this operation are heavily dependent on the aliasing
    /// model.
    RawPtr(RawPtrKind, Place<'tcx>),

    /// Yields the length of the place, as a `usize`.
    ///
    /// If the type of the place is an array, this is the array length. For slices (`[T]`, not
    /// `&[T]`) this accesses the place's metadata to determine the length. This rvalue is
    /// ill-formed for places of other types.
    ///
    /// This cannot be a `UnOp(PtrMetadata, _)` because that expects a value, and we only
    /// have a place, and `UnOp(PtrMetadata, RawPtr(place))` is not a thing.
    Len(Place<'tcx>),

    /// Performs essentially all of the casts that can be performed via `as`.
    ///
    /// This allows for casts from/to a variety of types.
    ///
    /// **FIXME**: Document exactly which `CastKind`s allow which types of casts.
    Cast(CastKind, Operand<'tcx>, Ty<'tcx>),

    /// * `Offset` has the same semantics as [`offset`](pointer::offset), except that the second
    ///   parameter may be a `usize` as well.
    /// * The comparison operations accept `bool`s, `char`s, signed or unsigned integers, floats,
    ///   raw pointers, or function pointers and return a `bool`. The types of the operands must be
    ///   matching, up to the usual caveat of the lifetimes in function pointers.
    /// * Left and right shift operations accept signed or unsigned integers not necessarily of the
    ///   same type and return a value of the same type as their LHS. Like in Rust, the RHS is
    ///   truncated as needed.
    /// * The `Bit*` operations accept signed integers, unsigned integers, or bools with matching
    ///   types and return a value of that type.
    /// * The `FooWithOverflow` are like the `Foo`, but returning `(T, bool)` instead of just `T`,
    ///   where the `bool` is true if the result is not equal to the infinite-precision result.
    /// * The remaining operations accept signed integers, unsigned integers, or floats with
    ///   matching types and return a value of that type.
    BinaryOp(BinOp, Box<(Operand<'tcx>, Operand<'tcx>)>),

    /// Computes a value as described by the operation.
    NullaryOp(NullOp<'tcx>, Ty<'tcx>),

    /// Exactly like `BinaryOp`, but less operands.
    ///
    /// Also does two's-complement arithmetic. Negation requires a signed integer or a float;
    /// bitwise not requires a signed integer, unsigned integer, or bool. Both operation kinds
    /// return a value with the same type as their operand.
    UnaryOp(UnOp, Operand<'tcx>),

    /// Computes the discriminant of the place, returning it as an integer of type
    /// [`discriminant_ty`]. Returns zero for types without discriminant.
    ///
    /// The validity requirements for the underlying value are undecided for this rvalue, see
    /// [#91095]. Note too that the value of the discriminant is not the same thing as the
    /// variant index; use [`discriminant_for_variant`] to convert.
    ///
    /// [`discriminant_ty`]: crate::ty::Ty::discriminant_ty
    /// [#91095]: https://github.com/rust-lang/rust/issues/91095
    /// [`discriminant_for_variant`]: crate::ty::Ty::discriminant_for_variant
    Discriminant(Place<'tcx>),

    /// Creates an aggregate value, like a tuple or struct.
    ///
    /// This is needed because dataflow analysis needs to distinguish
    /// `dest = Foo { x: ..., y: ... }` from `dest.x = ...; dest.y = ...;` in the case that `Foo`
    /// has a destructor.
    ///
    /// Disallowed after deaggregation for all aggregate kinds except `Array` and `Coroutine`. After
    /// coroutine lowering, `Coroutine` aggregate kinds are disallowed too.
    Aggregate(Box<AggregateKind<'tcx>>, IndexVec<FieldIdx, Operand<'tcx>>),

    /// Transmutes a `*mut u8` into shallow-initialized `Box<T>`.
    ///
    /// This is different from a normal transmute because dataflow analysis will treat the box as
    /// initialized but its content as uninitialized. Like other pointer casts, this in general
    /// affects alias analysis.
    ShallowInitBox(Operand<'tcx>, Ty<'tcx>),

    /// A CopyForDeref is equivalent to a read from a place at the
    /// codegen level, but is treated specially by drop elaboration. When such a read happens, it
    /// is guaranteed (via nature of the mir_opt `Derefer` in rustc_mir_transform/src/deref_separator)
    /// that the only use of the returned value is a deref operation, immediately
    /// followed by one or more projections. Drop elaboration treats this rvalue as if the
    /// read never happened and just projects further. This allows simplifying various MIR
    /// optimizations and codegen backends that previously had to handle deref operations anywhere
    /// in a place.
    CopyForDeref(Place<'tcx>),

    /// Wraps a value in an unsafe binder.
    WrapUnsafeBinder(Operand<'tcx>, Ty<'tcx>),
}

#[derive(Clone, Copy, Debug, PartialEq, Eq, TyEncodable, TyDecodable, Hash, HashStable)]
pub enum CastKind {
    /// An exposing pointer to address cast. A cast between a pointer and an integer type, or
    /// between a function pointer and an integer type.
    /// See the docs on `expose_provenance` for more details.
    PointerExposeProvenance,
    /// An address-to-pointer cast that picks up an exposed provenance.
    /// See the docs on `with_exposed_provenance` for more details.
    PointerWithExposedProvenance,
    /// Pointer related casts that are done by coercions. Note that reference-to-raw-ptr casts are
    /// translated into `&raw mut/const *r`, i.e., they are not actually casts.
    ///
    /// The following are allowed in [`AnalysisPhase::Initial`] as they're needed for borrowck,
    /// but after that are forbidden (including in all phases of runtime MIR):
    /// * [`PointerCoercion::ArrayToPointer`]
    /// * [`PointerCoercion::MutToConstPointer`]
    ///
    /// Both are runtime nops, so should be [`CastKind::PtrToPtr`] instead in runtime MIR.
    PointerCoercion(PointerCoercion, CoercionSource),
    IntToInt,
    FloatToInt,
    FloatToFloat,
    IntToFloat,
    PtrToPtr,
    FnPtrToPtr,
    /// Reinterpret the bits of the input as a different type.
    ///
    /// MIR is well-formed if the input and output types have different sizes,
    /// but running a transmute between differently-sized types is UB.
    ///
    /// Allowed only in [`MirPhase::Runtime`]; Earlier it's a [`TerminatorKind::Call`].
    Transmute,
}

/// Represents how a [`CastKind::PointerCoercion`] was constructed.
/// Used only for diagnostics.
#[derive(Clone, Copy, Debug, PartialEq, Eq, TyEncodable, TyDecodable, Hash, HashStable)]
pub enum CoercionSource {
    /// The coercion was manually written by the user with an `as` cast.
    AsCast,
    /// The coercion was automatically inserted by the compiler.
    Implicit,
}

#[derive(Clone, Debug, PartialEq, Eq, TyEncodable, TyDecodable, Hash, HashStable)]
#[derive(TypeFoldable, TypeVisitable)]
pub enum AggregateKind<'tcx> {
    /// The type is of the element
    Array(Ty<'tcx>),
    Tuple,

    /// The second field is the variant index. It's equal to 0 for struct
    /// and union expressions. The last field is the
    /// active field number and is present only for union expressions
    /// -- e.g., for a union expression `SomeUnion { c: .. }`, the
    /// active field index would identity the field `c`
    Adt(DefId, VariantIdx, GenericArgsRef<'tcx>, Option<UserTypeAnnotationIndex>, Option<FieldIdx>),

    Closure(DefId, GenericArgsRef<'tcx>),
    Coroutine(DefId, GenericArgsRef<'tcx>),
    CoroutineClosure(DefId, GenericArgsRef<'tcx>),

    /// Construct a raw pointer from the data pointer and metadata.
    ///
    /// The `Ty` here is the type of the *pointee*, not the pointer itself.
    /// The `Mutability` indicates whether this produces a `*const` or `*mut`.
    ///
    /// The [`Rvalue::Aggregate`] operands for thus must be
    ///
    /// 0. A raw pointer of matching mutability with any [`core::ptr::Thin`] pointee
    /// 1. A value of the appropriate [`core::ptr::Pointee::Metadata`] type
    ///
    /// *Both* operands must always be included, even the unit value if this is
    /// creating a thin pointer. If you're just converting between thin pointers,
    /// you may want an [`Rvalue::Cast`] with [`CastKind::PtrToPtr`] instead.
    RawPtr(Ty<'tcx>, Mutability),
}

#[derive(Copy, Clone, Debug, PartialEq, Eq, TyEncodable, TyDecodable, Hash, HashStable)]
pub enum NullOp<'tcx> {
    /// Returns the size of a value of that type
    SizeOf,
    /// Returns the minimum alignment of a type
    AlignOf,
    /// Returns the offset of a field
    OffsetOf(&'tcx List<(VariantIdx, FieldIdx)>),
    /// Returns whether we should perform some UB-checking at runtime.
    /// See the `ub_checks` intrinsic docs for details.
    UbChecks,
    /// Returns whether we should perform contract-checking at runtime.
    /// See the `contract_checks` intrinsic docs for details.
    ContractChecks,
}

#[derive(Copy, Clone, Debug, PartialEq, Eq, Hash)]
#[derive(HashStable, TyEncodable, TyDecodable, TypeFoldable, TypeVisitable)]
pub enum UnOp {
    /// The `!` operator for logical inversion
    Not,
    /// The `-` operator for negation
    Neg,
    /// Gets the metadata `M` from a `*const`/`*mut`/`&`/`&mut` to
    /// `impl Pointee<Metadata = M>`.
    ///
    /// For example, this will give a `()` from `*const i32`, a `usize` from
    /// `&mut [u8]`, or a `ptr::DynMetadata<dyn Foo>` (internally a pointer)
    /// from a `*mut dyn Foo`.
    ///
    /// Allowed only in [`MirPhase::Runtime`]; earlier it's an intrinsic.
    PtrMetadata,
}

#[derive(Copy, Clone, Debug, PartialEq, Eq, Hash)]
#[derive(TyEncodable, TyDecodable, HashStable, TypeFoldable, TypeVisitable)]
pub enum BinOp {
    /// The `+` operator (addition)
    Add,
    /// Like `Add`, but with UB on overflow.  (Integers only.)
    AddUnchecked,
    /// Like `Add`, but returns `(T, bool)` of both the wrapped result
    /// and a bool indicating whether it overflowed.
    AddWithOverflow,
    /// The `-` operator (subtraction)
    Sub,
    /// Like `Sub`, but with UB on overflow.  (Integers only.)
    SubUnchecked,
    /// Like `Sub`, but returns `(T, bool)` of both the wrapped result
    /// and a bool indicating whether it overflowed.
    SubWithOverflow,
    /// The `*` operator (multiplication)
    Mul,
    /// Like `Mul`, but with UB on overflow.  (Integers only.)
    MulUnchecked,
    /// Like `Mul`, but returns `(T, bool)` of both the wrapped result
    /// and a bool indicating whether it overflowed.
    MulWithOverflow,
    /// The `/` operator (division)
    ///
    /// For integer types, division by zero is UB, as is `MIN / -1` for signed.
    /// The compiler should have inserted checks prior to this.
    ///
    /// Floating-point division by zero is safe, and does not need guards.
    Div,
    /// The `%` operator (modulus)
    ///
    /// For integer types, using zero as the modulus (second operand) is UB,
    /// as is `MIN % -1` for signed.
    /// The compiler should have inserted checks prior to this.
    ///
    /// Floating-point remainder by zero is safe, and does not need guards.
    Rem,
    /// The `^` operator (bitwise xor)
    BitXor,
    /// The `&` operator (bitwise and)
    BitAnd,
    /// The `|` operator (bitwise or)
    BitOr,
    /// The `<<` operator (shift left)
    ///
    /// The offset is given by `RHS.rem_euclid(LHS::BITS)`.
    /// In other words, it is (uniquely) determined as follows:
    /// - it is "equal modulo LHS::BITS" to the RHS
    /// - it is in the range `0..LHS::BITS`
    Shl,
    /// Like `Shl`, but is UB if the RHS >= LHS::BITS or RHS < 0
    ShlUnchecked,
    /// The `>>` operator (shift right)
    ///
    /// The offset is given by `RHS.rem_euclid(LHS::BITS)`.
    /// In other words, it is (uniquely) determined as follows:
    /// - it is "equal modulo LHS::BITS" to the RHS
    /// - it is in the range `0..LHS::BITS`
    ///
    /// This is an arithmetic shift if the LHS is signed
    /// and a logical shift if the LHS is unsigned.
    Shr,
    /// Like `Shl`, but is UB if the RHS >= LHS::BITS or RHS < 0
    ShrUnchecked,
    /// The `==` operator (equality)
    Eq,
    /// The `<` operator (less than)
    Lt,
    /// The `<=` operator (less than or equal to)
    Le,
    /// The `!=` operator (not equal to)
    Ne,
    /// The `>=` operator (greater than or equal to)
    Ge,
    /// The `>` operator (greater than)
    Gt,
    /// The `<=>` operator (three-way comparison, like `Ord::cmp`)
    ///
    /// This is supported only on the integer types and `char`, always returning
    /// [`rustc_hir::LangItem::OrderingEnum`] (aka [`std::cmp::Ordering`]).
    ///
    /// [`Rvalue::BinaryOp`]`(BinOp::Cmp, A, B)` returns
    /// - `Ordering::Less` (`-1_i8`, as a Scalar) if `A < B`
    /// - `Ordering::Equal` (`0_i8`, as a Scalar) if `A == B`
    /// - `Ordering::Greater` (`+1_i8`, as a Scalar) if `A > B`
    Cmp,
    /// The `ptr.offset` operator
    Offset,
}

// Some nodes are used a lot. Make sure they don't unintentionally get bigger.
#[cfg(target_pointer_width = "64")]
mod size_asserts {
    use rustc_data_structures::static_assert_size;

    use super::*;
    // tidy-alphabetical-start
    static_assert_size!(AggregateKind<'_>, 32);
    static_assert_size!(Operand<'_>, 24);
    static_assert_size!(Place<'_>, 16);
    static_assert_size!(PlaceElem<'_>, 24);
    static_assert_size!(Rvalue<'_>, 40);
    static_assert_size!(StatementKind<'_>, 16);
    static_assert_size!(TerminatorKind<'_>, 80);
    // tidy-alphabetical-end
}