Rollup merge of #112717 - celinval:stable-mir-rvalue-1, r=oli-obk

Implement a few more rvalue translation to smir

Add the implementation for a few more RValue variants. For now, I simplified the stable version of `RValue::Ref` by removing the notion of Region.

r? `@oli-obk`

Cargo.lock

@@ -4233,6 +4233,7 @@ dependencies = [
  "rustc_hir",
  "rustc_middle",
  "rustc_span",
+ "rustc_target",
  "scoped-tls",
  "tracing",
 ]

compiler/rustc_smir/Cargo.toml

@@ -4,14 +4,18 @@ version = "0.0.0"
 edition = "2021"
 
 [dependencies]
-rustc_hir = { path = "../rustc_hir" }
+# Use optional dependencies for rustc_* in order to support building this crate separately.
+rustc_hir = { path = "../rustc_hir", optional = true }
 rustc_middle = { path = "../rustc_middle", optional = true }
 rustc_span = { path = "../rustc_span", optional = true }
+rustc_target = { path = "../rustc_target", optional = true }
 tracing = "0.1"
 scoped-tls = "1.0"
 
 [features]
 default = [
+    "rustc_hir",
     "rustc_middle",
     "rustc_span",
+    "rustc_target",
 ]

compiler/rustc_smir/rust-toolchain.toml

@@ -1,3 +1,3 @@
 [toolchain]
-channel = "nightly-2023-02-28"
+channel = "nightly-2023-06-14"
 components = [ "rustfmt", "rustc-dev" ]

compiler/rustc_smir/src/lib.rs

@@ -13,6 +13,17 @@
 #![cfg_attr(not(feature = "default"), feature(rustc_private))]
 #![feature(local_key_cell_methods)]
 #![feature(ptr_metadata)]
+#![feature(type_alias_impl_trait)] // Used to define opaque types.
+
+// Declare extern rustc_* crates to enable building this crate separately from the compiler.
+#[cfg(not(feature = "default"))]
+extern crate rustc_hir;
+#[cfg(not(feature = "default"))]
+extern crate rustc_middle;
+#[cfg(not(feature = "default"))]
+extern crate rustc_span;
+#[cfg(not(feature = "default"))]
+extern crate rustc_target;
 
 pub mod rustc_internal;
 pub mod stable_mir;

compiler/rustc_smir/src/rustc_internal/mod.rs

@@ -3,6 +3,9 @@
 //! For that, we define APIs that will temporarily be public to 3P that exposes rustc internal APIs
 //! until stable MIR is complete.
 
+use std::fmt::Debug;
+use std::string::ToString;
+
 use crate::{
     rustc_smir::Tables,
     stable_mir::{self, with},
@@ -49,3 +52,10 @@ pub fn crate_num(item: &stable_mir::Crate) -> CrateNum {
 pub fn run(tcx: TyCtxt<'_>, f: impl FnOnce()) {
     crate::stable_mir::run(Tables { tcx, def_ids: vec![], types: vec![] }, f);
 }
+
+/// A type that provides internal information but that can still be used for debug purpose.
+pub type Opaque = impl Debug + ToString + Clone;
+
+pub(crate) fn opaque<T: Debug>(value: &T) -> Opaque {
+    format!("{value:?}")
+}

compiler/rustc_smir/src/rustc_smir/mod.rs

@@ -7,11 +7,13 @@
 //!
 //! For now, we are developing everything inside `rustc`, thus, we keep this module private.
 
+use crate::rustc_internal::{self, opaque};
 use crate::stable_mir::ty::{FloatTy, IntTy, RigidTy, TyKind, UintTy};
 use crate::stable_mir::{self, Context};
 use rustc_middle::mir;
 use rustc_middle::ty::{self, Ty, TyCtxt};
 use rustc_span::def_id::{CrateNum, DefId, LOCAL_CRATE};
+use rustc_target::abi::FieldIdx;
 use tracing::debug;
 
 impl<'tcx> Context for Tables<'tcx> {
@@ -137,11 +139,21 @@ fn smir_crate(tcx: TyCtxt<'_>, crate_num: CrateNum) -> stable_mir::Crate {
     stable_mir::Crate { id: crate_num.into(), name: crate_name, is_local }
 }
 
-pub trait Stable {
+/// Trait used to convert between an internal MIR type to a Stable MIR type.
+pub(crate) trait Stable {
+    /// The stable representation of the type implementing Stable.
     type T;
+    /// Converts an object to the equivalent Stable MIR representation.
     fn stable(&self) -> Self::T;
 }
 
+impl Stable for DefId {
+    type T = stable_mir::CrateItem;
+    fn stable(&self) -> Self::T {
+        rustc_internal::crate_item(*self)
+    }
+}
+
 impl<'tcx> Stable for mir::Statement<'tcx> {
     type T = stable_mir::mir::Statement;
     fn stable(&self) -> Self::T {
@@ -173,12 +185,18 @@ impl<'tcx> Stable for mir::Rvalue<'tcx> {
         match self {
             Use(op) => stable_mir::mir::Rvalue::Use(op.stable()),
             Repeat(_, _) => todo!(),
-            Ref(_, _, _) => todo!(),
-            ThreadLocalRef(_) => todo!(),
-            AddressOf(_, _) => todo!(),
-            Len(_) => todo!(),
+            Ref(region, kind, place) => {
+                stable_mir::mir::Rvalue::Ref(opaque(region), kind.stable(), place.stable())
+            }
+            ThreadLocalRef(def_id) => stable_mir::mir::Rvalue::ThreadLocalRef(def_id.stable()),
+            AddressOf(mutability, place) => {
+                stable_mir::mir::Rvalue::AddressOf(mutability.stable(), place.stable())
+            }
+            Len(place) => stable_mir::mir::Rvalue::Len(place.stable()),
             Cast(_, _, _) => todo!(),
-            BinaryOp(_, _) => todo!(),
+            BinaryOp(bin_op, ops) => {
+                stable_mir::mir::Rvalue::BinaryOp(bin_op.stable(), ops.0.stable(), ops.1.stable())
+            }
             CheckedBinaryOp(bin_op, ops) => stable_mir::mir::Rvalue::CheckedBinaryOp(
                 bin_op.stable(),
                 ops.0.stable(),
@@ -186,14 +204,119 @@ impl<'tcx> Stable for mir::Rvalue<'tcx> {
             ),
             NullaryOp(_, _) => todo!(),
             UnaryOp(un_op, op) => stable_mir::mir::Rvalue::UnaryOp(un_op.stable(), op.stable()),
-            Discriminant(_) => todo!(),
+            Discriminant(place) => stable_mir::mir::Rvalue::Discriminant(place.stable()),
             Aggregate(_, _) => todo!(),
             ShallowInitBox(_, _) => todo!(),
-            CopyForDeref(_) => todo!(),
+            CopyForDeref(place) => stable_mir::mir::Rvalue::CopyForDeref(place.stable()),
         }
     }
 }
 
+impl Stable for mir::Mutability {
+    type T = stable_mir::mir::Mutability;
+    fn stable(&self) -> Self::T {
+        use mir::Mutability::*;
+        match *self {
+            Not => stable_mir::mir::Mutability::Not,
+            Mut => stable_mir::mir::Mutability::Mut,
+        }
+    }
+}
+
+impl Stable for mir::BorrowKind {
+    type T = stable_mir::mir::BorrowKind;
+    fn stable(&self) -> Self::T {
+        use mir::BorrowKind::*;
+        match *self {
+            Shared => stable_mir::mir::BorrowKind::Shared,
+            Shallow => stable_mir::mir::BorrowKind::Shallow,
+            Mut { kind } => stable_mir::mir::BorrowKind::Mut { kind: kind.stable() },
+        }
+    }
+}
+
+impl Stable for mir::MutBorrowKind {
+    type T = stable_mir::mir::MutBorrowKind;
+    fn stable(&self) -> Self::T {
+        use mir::MutBorrowKind::*;
+        match *self {
+            Default => stable_mir::mir::MutBorrowKind::Default,
+            TwoPhaseBorrow => stable_mir::mir::MutBorrowKind::TwoPhaseBorrow,
+            ClosureCapture => stable_mir::mir::MutBorrowKind::ClosureCapture,
+        }
+    }
+}
+
+impl<'tcx> Stable for mir::NullOp<'tcx> {
+    type T = stable_mir::mir::NullOp;
+    fn stable(&self) -> Self::T {
+        use mir::NullOp::*;
+        match self {
+            SizeOf => stable_mir::mir::NullOp::SizeOf,
+            AlignOf => stable_mir::mir::NullOp::AlignOf,
+            OffsetOf(indices) => {
+                stable_mir::mir::NullOp::OffsetOf(indices.iter().map(|idx| idx.stable()).collect())
+            }
+        }
+    }
+}
+
+impl Stable for mir::CastKind {
+    type T = stable_mir::mir::CastKind;
+    fn stable(&self) -> Self::T {
+        use mir::CastKind::*;
+        match self {
+            PointerExposeAddress => stable_mir::mir::CastKind::PointerExposeAddress,
+            PointerFromExposedAddress => stable_mir::mir::CastKind::PointerFromExposedAddress,
+            PointerCoercion(c) => stable_mir::mir::CastKind::PointerCoercion(c.stable()),
+            DynStar => stable_mir::mir::CastKind::DynStar,
+            IntToInt => stable_mir::mir::CastKind::IntToInt,
+            FloatToInt => stable_mir::mir::CastKind::FloatToInt,
+            FloatToFloat => stable_mir::mir::CastKind::FloatToFloat,
+            IntToFloat => stable_mir::mir::CastKind::IntToFloat,
+            PtrToPtr => stable_mir::mir::CastKind::PtrToPtr,
+            FnPtrToPtr => stable_mir::mir::CastKind::FnPtrToPtr,
+            Transmute => stable_mir::mir::CastKind::Transmute,
+        }
+    }
+}
+
+impl Stable for ty::adjustment::PointerCoercion {
+    type T = stable_mir::mir::PointerCoercion;
+    fn stable(&self) -> Self::T {
+        use ty::adjustment::PointerCoercion;
+        match self {
+            PointerCoercion::ReifyFnPointer => stable_mir::mir::PointerCoercion::ReifyFnPointer,
+            PointerCoercion::UnsafeFnPointer => stable_mir::mir::PointerCoercion::UnsafeFnPointer,
+            PointerCoercion::ClosureFnPointer(unsafety) => {
+                stable_mir::mir::PointerCoercion::ClosureFnPointer(unsafety.stable())
+            }
+            PointerCoercion::MutToConstPointer => {
+                stable_mir::mir::PointerCoercion::MutToConstPointer
+            }
+            PointerCoercion::ArrayToPointer => stable_mir::mir::PointerCoercion::ArrayToPointer,
+            PointerCoercion::Unsize => stable_mir::mir::PointerCoercion::Unsize,
+        }
+    }
+}
+
+impl Stable for rustc_hir::Unsafety {
+    type T = stable_mir::mir::Safety;
+    fn stable(&self) -> Self::T {
+        match self {
+            rustc_hir::Unsafety::Unsafe => stable_mir::mir::Safety::Unsafe,
+            rustc_hir::Unsafety::Normal => stable_mir::mir::Safety::Normal,
+        }
+    }
+}
+
+impl Stable for FieldIdx {
+    type T = usize;
+    fn stable(&self) -> Self::T {
+        self.as_usize()
+    }
+}
+
 impl<'tcx> Stable for mir::Operand<'tcx> {
     type T = stable_mir::mir::Operand;
     fn stable(&self) -> Self::T {
@@ -229,34 +352,38 @@ impl Stable for mir::UnwindAction {
     }
 }
 
-fn rustc_assert_msg_to_msg<'tcx>(
-    assert_message: &rustc_middle::mir::AssertMessage<'tcx>,
-) -> stable_mir::mir::AssertMessage {
-    use rustc_middle::mir::AssertKind;
-    match assert_message {
-        AssertKind::BoundsCheck { len, index } => {
-            stable_mir::mir::AssertMessage::BoundsCheck { len: len.stable(), index: index.stable() }
-        }
-        AssertKind::Overflow(bin_op, op1, op2) => {
-            stable_mir::mir::AssertMessage::Overflow(bin_op.stable(), op1.stable(), op2.stable())
-        }
-        AssertKind::OverflowNeg(op) => stable_mir::mir::AssertMessage::OverflowNeg(op.stable()),
-        AssertKind::DivisionByZero(op) => {
-            stable_mir::mir::AssertMessage::DivisionByZero(op.stable())
-        }
-        AssertKind::RemainderByZero(op) => {
-            stable_mir::mir::AssertMessage::RemainderByZero(op.stable())
-        }
-        AssertKind::ResumedAfterReturn(generator) => {
-            stable_mir::mir::AssertMessage::ResumedAfterReturn(generator.stable())
-        }
-        AssertKind::ResumedAfterPanic(generator) => {
-            stable_mir::mir::AssertMessage::ResumedAfterPanic(generator.stable())
-        }
-        AssertKind::MisalignedPointerDereference { required, found } => {
-            stable_mir::mir::AssertMessage::MisalignedPointerDereference {
-                required: required.stable(),
-                found: found.stable(),
+impl<'tcx> Stable for mir::AssertMessage<'tcx> {
+    type T = stable_mir::mir::AssertMessage;
+    fn stable(&self) -> Self::T {
+        use rustc_middle::mir::AssertKind;
+        match self {
+            AssertKind::BoundsCheck { len, index } => stable_mir::mir::AssertMessage::BoundsCheck {
+                len: len.stable(),
+                index: index.stable(),
+            },
+            AssertKind::Overflow(bin_op, op1, op2) => stable_mir::mir::AssertMessage::Overflow(
+                bin_op.stable(),
+                op1.stable(),
+                op2.stable(),
+            ),
+            AssertKind::OverflowNeg(op) => stable_mir::mir::AssertMessage::OverflowNeg(op.stable()),
+            AssertKind::DivisionByZero(op) => {
+                stable_mir::mir::AssertMessage::DivisionByZero(op.stable())
+            }
+            AssertKind::RemainderByZero(op) => {
+                stable_mir::mir::AssertMessage::RemainderByZero(op.stable())
+            }
+            AssertKind::ResumedAfterReturn(generator) => {
+                stable_mir::mir::AssertMessage::ResumedAfterReturn(generator.stable())
+            }
+            AssertKind::ResumedAfterPanic(generator) => {
+                stable_mir::mir::AssertMessage::ResumedAfterPanic(generator.stable())
+            }
+            AssertKind::MisalignedPointerDereference { required, found } => {
+                stable_mir::mir::AssertMessage::MisalignedPointerDereference {
+                    required: required.stable(),
+                    found: found.stable(),
+                }
             }
         }
     }
@@ -381,7 +508,7 @@ impl<'tcx> Stable for mir::Terminator<'tcx> {
             Assert { cond, expected, msg, target, unwind } => Terminator::Assert {
                 cond: cond.stable(),
                 expected: *expected,
-                msg: rustc_assert_msg_to_msg(msg),
+                msg: msg.stable(),
                 target: target.as_usize(),
                 unwind: unwind.stable(),
             },

compiler/rustc_smir/src/stable_mir/mir/body.rs

@@ -1,4 +1,5 @@
-use crate::stable_mir::ty::Ty;
+use crate::rustc_internal::Opaque;
+use crate::stable_mir::{self, ty::Ty};
 
 #[derive(Clone, Debug)]
 pub struct Body {
@@ -136,12 +137,98 @@ pub enum Statement {
     Nop,
 }
 
+type Region = Opaque;
+
 // FIXME this is incomplete
 #[derive(Clone, Debug)]
 pub enum Rvalue {
-    Use(Operand),
+    /// Creates a pointer with the indicated mutability to the place.
+    ///
+    /// This is generated by pointer casts like `&v as *const _` or raw address of expressions like
+    /// `&raw v` or `addr_of!(v)`.
+    AddressOf(Mutability, Place),
+
+    /// * `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 remaining operations accept signed integers, unsigned integers, or floats with
+    ///   matching types and return a value of that type.
+    BinaryOp(BinOp, Operand, Operand),
+
+    /// Performs essentially all of the casts that can be performed via `as`.
+    ///
+    /// This allows for casts from/to a variety of types.
+    Cast(CastKind, Operand, Ty),
+
+    /// Same as `BinaryOp`, but yields `(T, bool)` with a `bool` indicating an error condition.
+    ///
+    /// For addition, subtraction, and multiplication on integers the error condition is set when
+    /// the infinite precision result would not be equal to the actual result.
     CheckedBinaryOp(BinOp, Operand, Operand),
+
+    /// A CopyForDeref is equivalent to a read from a place.
+    /// When such a read happens, it is guaranteed that the only use of the returned value is a
+    /// deref operation, immediately followed by one or more projections.
+    CopyForDeref(Place),
+
+    /// 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),
+
+    /// 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.
+    Len(Place),
+
+    /// Creates a reference to the place.
+    Ref(Region, BorrowKind, Place),
+
+    /// 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, Ty),
+
+    /// 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(stable_mir::CrateItem),
+
+    /// 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),
+
+    /// Yields the operand unchanged
+    Use(Operand),
 }
 
 #[derive(Clone, Debug)]
@@ -157,8 +244,98 @@ pub struct Place {
     pub projection: String,
 }
 
+type FieldIdx = usize;
+
 #[derive(Clone, Debug)]
 pub struct SwitchTarget {
     pub value: u128,
     pub target: usize,
 }
+
+#[derive(Clone, Debug)]
+pub enum BorrowKind {
+    /// Data must be immutable and is aliasable.
+    Shared,
+
+    /// 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`.
+    Shallow,
+
+    /// Data is mutable and not aliasable.
+    Mut {
+        /// `true` if this borrow arose from method-call auto-ref
+        kind: MutBorrowKind,
+    },
+}
+
+#[derive(Clone, Debug)]
+pub enum MutBorrowKind {
+    Default,
+    TwoPhaseBorrow,
+    ClosureCapture,
+}
+
+#[derive(Clone, Debug)]
+pub enum Mutability {
+    Not,
+    Mut,
+}
+
+#[derive(Clone, Debug)]
+pub enum Safety {
+    Unsafe,
+    Normal,
+}
+
+#[derive(Clone, Debug)]
+pub enum PointerCoercion {
+    /// Go from a fn-item type to a fn-pointer type.
+    ReifyFnPointer,
+
+    /// Go from a safe fn pointer to an unsafe fn pointer.
+    UnsafeFnPointer,
+
+    /// Go from a non-capturing closure to an fn pointer or an unsafe fn pointer.
+    /// It cannot convert a closure that requires unsafe.
+    ClosureFnPointer(Safety),
+
+    /// Go from a mut raw pointer to a const raw pointer.
+    MutToConstPointer,
+
+    /// Go from `*const [T; N]` to `*const T`
+    ArrayToPointer,
+
+    /// Unsize a pointer/reference value, e.g., `&[T; n]` to
+    /// `&[T]`. Note that the source could be a thin or fat pointer.
+    /// This will do things like convert thin pointers to fat
+    /// pointers, or convert structs containing thin pointers to
+    /// structs containing fat pointers, or convert between fat
+    /// pointers.
+    Unsize,
+}
+
+#[derive(Clone, Debug)]
+pub enum CastKind {
+    PointerExposeAddress,
+    PointerFromExposedAddress,
+    PointerCoercion(PointerCoercion),
+    DynStar,
+    IntToInt,
+    FloatToInt,
+    FloatToFloat,
+    IntToFloat,
+    PtrToPtr,
+    FnPtrToPtr,
+    Transmute,
+}
+
+#[derive(Clone, Debug)]
+pub enum NullOp {
+    /// 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(Vec<FieldIdx>),
+}