Auto merge of #128506 - compiler-errors:by-move-body, r=cjgillot

Stop storing a special inner body for the coroutine by-move body for async closures

...and instead, just synthesize an item which is treated mostly normally by the MIR pipeline.

This PR does a few things:
* We synthesize a new `DefId` for the by-move body of a closure, which has its `mir_built` fed with the output of the `ByMoveBody` MIR transformation, and some other relevant queries.
* This has the `DefKind::ByMoveBody`, which we use to distinguish it from "real" bodies (that come from HIR) which need to be borrowck'd. Introduce `TyCtxt::is_synthetic_mir` to skip over `mir_borrowck` which is called by `mir_promoted`; borrowck isn't really possible to make work ATM since it heavily relies being called on a body generated from HIR, and is redundant by the construction of the by-move-body.
* Remove the special `PassManager` hacks for handling the inner `by_move_body` stored within the coroutine's mir body. Instead, this body is fed like a regular MIR body, so it's goes through all of the `tcx.*_mir` stages normally (build -> promoted -> ...etc... -> optimized) ✨.
* Remove the `InstanceKind::ByMoveBody` shim, since now we have a "regular" def id, we can just use `InstanceKind::Item`. This also allows us to remove the corresponding hacks from codegen, such as in `fn_sig_for_fn_abi` ✨.

Notable remarks:
* ~~I know it's kind of weird to be using `DefKind::Closure` here, since it's not a distinct closure but just a new MIR body. I don't believe it really matters, but I could also use a different `DefKind`... maybe one that we could use for synthetic MIR bodies in general?~~ edit: We're doing this now.

compiler/rustc_const_eval/src/interpret/call.rs

@@ -576,7 +576,6 @@ impl<'tcx, M: Machine<'tcx>> InterpCx<'tcx, M> {
             | ty::InstanceKind::ReifyShim(..)
             | ty::InstanceKind::ClosureOnceShim { .. }
             | ty::InstanceKind::ConstructCoroutineInClosureShim { .. }
-            | ty::InstanceKind::CoroutineKindShim { .. }
             | ty::InstanceKind::FnPtrShim(..)
             | ty::InstanceKind::DropGlue(..)
             | ty::InstanceKind::CloneShim(..)

compiler/rustc_hir/src/def.rs

@@ -133,6 +133,9 @@ pub enum DefKind {
     /// we treat them all the same, and code which needs to distinguish them can match
     /// or `hir::ClosureKind` or `type_of`.
     Closure,
+    /// The definition of a synthetic coroutine body created by the lowering of a
+    /// coroutine-closure, such as an async closure.
+    SyntheticCoroutineBody,
 }
 
 impl DefKind {
@@ -177,6 +180,7 @@ impl DefKind {
             DefKind::Closure => "closure",
             DefKind::ExternCrate => "extern crate",
             DefKind::GlobalAsm => "global assembly block",
+            DefKind::SyntheticCoroutineBody => "synthetic mir body",
         }
     }
 
@@ -236,7 +240,8 @@ impl DefKind {
             | DefKind::ForeignMod
             | DefKind::GlobalAsm
             | DefKind::Impl { .. }
-            | DefKind::OpaqueTy => None,
+            | DefKind::OpaqueTy
+            | DefKind::SyntheticCoroutineBody => None,
         }
     }
 
@@ -276,6 +281,7 @@ impl DefKind {
             DefKind::GlobalAsm => DefPathData::GlobalAsm,
             DefKind::Impl { .. } => DefPathData::Impl,
             DefKind::Closure => DefPathData::Closure,
+            DefKind::SyntheticCoroutineBody => DefPathData::Closure,
         }
     }
 
@@ -291,7 +297,8 @@ impl DefKind {
             | DefKind::AssocFn
             | DefKind::Ctor(..)
             | DefKind::Closure
-            | DefKind::Static { .. } => true,
+            | DefKind::Static { .. }
+            | DefKind::SyntheticCoroutineBody => true,
             DefKind::Mod
             | DefKind::Struct
             | DefKind::Union

compiler/rustc_hir_analysis/src/check/wfcheck.rs

@@ -2174,7 +2174,8 @@ fn lint_redundant_lifetimes<'tcx>(
         | DefKind::Field
         | DefKind::LifetimeParam
         | DefKind::GlobalAsm
-        | DefKind::Closure => return,
+        | DefKind::Closure
+        | DefKind::SyntheticCoroutineBody => return,
     }
 
     // The ordering of this lifetime map is a bit subtle.

compiler/rustc_hir_analysis/src/lib.rs

@@ -200,10 +200,6 @@ pub fn check_crate(tcx: TyCtxt<'_>) {
         }
     });
 
-    // Freeze definitions as we don't add new ones at this point. This improves performance by
-    // allowing lock-free access to them.
-    tcx.untracked().definitions.freeze();
-
     // FIXME: Remove this when we implement creating `DefId`s
     // for anon constants during their parents' typeck.
     // Typeck all body owners in parallel will produce queries

compiler/rustc_interface/src/passes.rs

@@ -784,7 +784,20 @@ fn run_required_analyses(tcx: TyCtxt<'_>) {
             }
         );
     });
+
     rustc_hir_analysis::check_crate(tcx);
+    sess.time("MIR_coroutine_by_move_body", || {
+        tcx.hir().par_body_owners(|def_id| {
+            if tcx.needs_coroutine_by_move_body_def_id(def_id) {
+                tcx.ensure_with_value().coroutine_by_move_body_def_id(def_id);
+            }
+        });
+    });
+    // Freeze definitions as we don't add new ones at this point.
+    // We need to wait until now since we synthesize a by-move body
+    // This improves performance by allowing lock-free access to them.
+    tcx.untracked().definitions.freeze();
+
     sess.time("MIR_borrow_checking", || {
         tcx.hir().par_body_owners(|def_id| {
             // Run unsafety check because it's responsible for stealing and
@@ -816,6 +829,7 @@ fn run_required_analyses(tcx: TyCtxt<'_>) {
             );
         }
     });
+
     sess.time("layout_testing", || layout_test::test_layout(tcx));
     sess.time("abi_testing", || abi_test::test_abi(tcx));
 

compiler/rustc_metadata/src/rmeta/encoder.rs

@@ -872,7 +872,8 @@ fn should_encode_span(def_kind: DefKind) -> bool {
         | DefKind::OpaqueTy
         | DefKind::Field
         | DefKind::Impl { .. }
-        | DefKind::Closure => true,
+        | DefKind::Closure
+        | DefKind::SyntheticCoroutineBody => true,
         DefKind::ForeignMod | DefKind::GlobalAsm => false,
     }
 }
@@ -902,6 +903,7 @@ fn should_encode_attrs(def_kind: DefKind) -> bool {
         // https://github.com/model-checking/kani and is not a performance
         // or maintenance issue for us.
         DefKind::Closure => true,
+        DefKind::SyntheticCoroutineBody => false,
         DefKind::TyParam
         | DefKind::ConstParam
         | DefKind::Ctor(..)
@@ -948,7 +950,8 @@ fn should_encode_expn_that_defined(def_kind: DefKind) -> bool {
         | DefKind::Field
         | DefKind::LifetimeParam
         | DefKind::GlobalAsm
-        | DefKind::Closure => false,
+        | DefKind::Closure
+        | DefKind::SyntheticCoroutineBody => false,
     }
 }
 
@@ -984,7 +987,8 @@ fn should_encode_visibility(def_kind: DefKind) -> bool {
         | DefKind::GlobalAsm
         | DefKind::Impl { .. }
         | DefKind::Closure
-        | DefKind::ExternCrate => false,
+        | DefKind::ExternCrate
+        | DefKind::SyntheticCoroutineBody => false,
     }
 }
 
@@ -1019,7 +1023,8 @@ fn should_encode_stability(def_kind: DefKind) -> bool {
         | DefKind::InlineConst
         | DefKind::GlobalAsm
         | DefKind::Closure
-        | DefKind::ExternCrate => false,
+        | DefKind::ExternCrate
+        | DefKind::SyntheticCoroutineBody => false,
     }
 }
 
@@ -1061,6 +1066,7 @@ fn should_encode_mir(
         }
         // Coroutines require optimized MIR to compute layout.
         DefKind::Closure if tcx.is_coroutine(def_id.to_def_id()) => (false, true),
+        DefKind::SyntheticCoroutineBody => (false, true),
         // Full-fledged functions + closures
         DefKind::AssocFn | DefKind::Fn | DefKind::Closure => {
             let generics = tcx.generics_of(def_id);
@@ -1109,7 +1115,8 @@ fn should_encode_variances<'tcx>(tcx: TyCtxt<'tcx>, def_id: DefId, def_kind: Def
         | DefKind::InlineConst
         | DefKind::GlobalAsm
         | DefKind::Closure
-        | DefKind::ExternCrate => false,
+        | DefKind::ExternCrate
+        | DefKind::SyntheticCoroutineBody => false,
         DefKind::TyAlias => tcx.type_alias_is_lazy(def_id),
     }
 }
@@ -1137,7 +1144,8 @@ fn should_encode_generics(def_kind: DefKind) -> bool {
         | DefKind::Impl { .. }
         | DefKind::Field
         | DefKind::TyParam
-        | DefKind::Closure => true,
+        | DefKind::Closure
+        | DefKind::SyntheticCoroutineBody => true,
         DefKind::Mod
         | DefKind::ForeignMod
         | DefKind::ConstParam
@@ -1168,7 +1176,8 @@ fn should_encode_type(tcx: TyCtxt<'_>, def_id: LocalDefId, def_kind: DefKind) ->
         | DefKind::Closure
         | DefKind::ConstParam
         | DefKind::AnonConst
-        | DefKind::InlineConst => true,
+        | DefKind::InlineConst
+        | DefKind::SyntheticCoroutineBody => true,
 
         DefKind::OpaqueTy => {
             let origin = tcx.opaque_type_origin(def_id);
@@ -1240,7 +1249,8 @@ fn should_encode_fn_sig(def_kind: DefKind) -> bool {
         | DefKind::Use
         | DefKind::LifetimeParam
         | DefKind::GlobalAsm
-        | DefKind::ExternCrate => false,
+        | DefKind::ExternCrate
+        | DefKind::SyntheticCoroutineBody => false,
     }
 }
 
@@ -1277,7 +1287,8 @@ fn should_encode_constness(def_kind: DefKind) -> bool {
         | DefKind::Use
         | DefKind::LifetimeParam
         | DefKind::GlobalAsm
-        | DefKind::ExternCrate => false,
+        | DefKind::ExternCrate
+        | DefKind::SyntheticCoroutineBody => false,
     }
 }
 
@@ -1310,7 +1321,8 @@ fn should_encode_const(def_kind: DefKind) -> bool {
         | DefKind::Use
         | DefKind::LifetimeParam
         | DefKind::GlobalAsm
-        | DefKind::ExternCrate => false,
+        | DefKind::ExternCrate
+        | DefKind::SyntheticCoroutineBody => false,
     }
 }
 
@@ -1458,7 +1470,7 @@ impl<'a, 'tcx> EncodeContext<'a, 'tcx> {
                     record!(self.tables.associated_type_for_effects[def_id] <- assoc_def_id);
                 }
             }
-            if def_kind == DefKind::Closure
+            if let DefKind::Closure | DefKind::SyntheticCoroutineBody = def_kind
                 && let Some(coroutine_kind) = self.tcx.coroutine_kind(def_id)
             {
                 self.tables.coroutine_kind.set(def_id.index, Some(coroutine_kind))

compiler/rustc_metadata/src/rmeta/table.rs

@@ -171,6 +171,7 @@ fixed_size_enum! {
         ( Macro(MacroKind::Bang)                   )
         ( Macro(MacroKind::Attr)                   )
         ( Macro(MacroKind::Derive)                 )
+        ( SyntheticCoroutineBody                   )
     }
 }
 

compiler/rustc_middle/src/hir/map/mod.rs

@@ -307,7 +307,7 @@ impl<'hir> Map<'hir> {
             }
             DefKind::InlineConst => BodyOwnerKind::Const { inline: true },
             DefKind::Ctor(..) | DefKind::Fn | DefKind::AssocFn => BodyOwnerKind::Fn,
-            DefKind::Closure => BodyOwnerKind::Closure,
+            DefKind::Closure | DefKind::SyntheticCoroutineBody => BodyOwnerKind::Closure,
             DefKind::Static { safety: _, mutability, nested: false } => {
                 BodyOwnerKind::Static(mutability)
             }

compiler/rustc_middle/src/mir/mod.rs

@@ -267,18 +267,6 @@ pub struct CoroutineInfo<'tcx> {
     /// Coroutine drop glue. This field is populated after the state transform pass.
     pub coroutine_drop: Option<Body<'tcx>>,
 
-    /// The body of the coroutine, modified to take its upvars by move rather than by ref.
-    ///
-    /// This is used by coroutine-closures, which must return a different flavor of coroutine
-    /// when called using `AsyncFnOnce::call_once`. It is produced by the `ByMoveBody` pass which
-    /// is run right after building the initial MIR, and will only be populated for coroutines
-    /// which come out of the async closure desugaring.
-    ///
-    /// This body should be processed in lockstep with the containing body -- any optimization
-    /// passes, etc, should be applied to this body as well. This is done automatically if
-    /// using `run_passes`.
-    pub by_move_body: Option<Body<'tcx>>,
-
     /// The layout of a coroutine. This field is populated after the state transform pass.
     pub coroutine_layout: Option<CoroutineLayout<'tcx>>,
 
@@ -298,7 +286,6 @@ impl<'tcx> CoroutineInfo<'tcx> {
             coroutine_kind,
             yield_ty: Some(yield_ty),
             resume_ty: Some(resume_ty),
-            by_move_body: None,
             coroutine_drop: None,
             coroutine_layout: None,
         }
@@ -665,10 +652,6 @@ impl<'tcx> Body<'tcx> {
         self.coroutine.as_ref().and_then(|coroutine| coroutine.coroutine_drop.as_ref())
     }
 
-    pub fn coroutine_by_move_body(&self) -> Option<&Body<'tcx>> {
-        self.coroutine.as_ref()?.by_move_body.as_ref()
-    }
-
     #[inline]
     pub fn coroutine_kind(&self) -> Option<CoroutineKind> {
         self.coroutine.as_ref().map(|coroutine| coroutine.coroutine_kind)

compiler/rustc_middle/src/mir/mono.rs

@@ -415,7 +415,6 @@ impl<'tcx> CodegenUnit<'tcx> {
                             | InstanceKind::Virtual(..)
                             | InstanceKind::ClosureOnceShim { .. }
                             | InstanceKind::ConstructCoroutineInClosureShim { .. }
-                            | InstanceKind::CoroutineKindShim { .. }
                             | InstanceKind::DropGlue(..)
                             | InstanceKind::CloneShim(..)
                             | InstanceKind::ThreadLocalShim(..)

compiler/rustc_middle/src/mir/visit.rs

@@ -349,7 +349,6 @@ macro_rules! make_mir_visitor {
                             coroutine_closure_def_id: _def_id,
                             receiver_by_ref: _,
                         } |
-                        ty::InstanceKind::CoroutineKindShim { coroutine_def_id: _def_id } |
                         ty::InstanceKind::AsyncDropGlueCtorShim(_def_id, None) |
                         ty::InstanceKind::DropGlue(_def_id, None) => {}
 

compiler/rustc_middle/src/query/mod.rs

@@ -326,6 +326,7 @@ rustc_queries! {
     query predicates_of(key: DefId) -> ty::GenericPredicates<'tcx> {
         desc { |tcx| "computing predicates of `{}`", tcx.def_path_str(key) }
         cache_on_disk_if { key.is_local() }
+        feedable
     }
 
     query opaque_types_defined_by(
@@ -498,6 +499,7 @@ rustc_queries! {
     /// [rustc dev guide]: https://rustc-dev-guide.rust-lang.org/mir/construction.html
     query mir_built(key: LocalDefId) -> &'tcx Steal<mir::Body<'tcx>> {
         desc { |tcx| "building MIR for `{}`", tcx.def_path_str(key) }
+        feedable
     }
 
     /// Try to build an abstract representation of the given constant.
@@ -742,6 +744,7 @@ rustc_queries! {
     query constness(key: DefId) -> hir::Constness {
         desc { |tcx| "checking if item is const: `{}`", tcx.def_path_str(key) }
         separate_provide_extern
+        feedable
     }
 
     query asyncness(key: DefId) -> ty::Asyncness {
@@ -760,10 +763,22 @@ rustc_queries! {
         desc { |tcx| "checking if item is promotable: `{}`", tcx.def_path_str(key) }
     }
 
+    /// The body of the coroutine, modified to take its upvars by move rather than by ref.
+    ///
+    /// This is used by coroutine-closures, which must return a different flavor of coroutine
+    /// when called using `AsyncFnOnce::call_once`. It is produced by the `ByMoveBody` pass which
+    /// is run right after building the initial MIR, and will only be populated for coroutines
+    /// which come out of the async closure desugaring.
+    query coroutine_by_move_body_def_id(def_id: DefId) -> DefId {
+        desc { |tcx| "looking up the coroutine by-move body for `{}`", tcx.def_path_str(def_id) }
+        separate_provide_extern
+    }
+
     /// Returns `Some(coroutine_kind)` if the node pointed to by `def_id` is a coroutine.
     query coroutine_kind(def_id: DefId) -> Option<hir::CoroutineKind> {
         desc { |tcx| "looking up coroutine kind of `{}`", tcx.def_path_str(def_id) }
         separate_provide_extern
+        feedable
     }
 
     query coroutine_for_closure(def_id: DefId) -> DefId {

compiler/rustc_middle/src/ty/context.rs

@@ -1579,6 +1579,12 @@ impl<'tcx> TyCtxt<'tcx> {
         )
     }
 
+    // Whether the body owner is synthetic, which in this case means it does not correspond to
+    // meaningful HIR. This is currently used to skip over MIR borrowck.
+    pub fn is_synthetic_mir(self, def_id: impl Into<DefId>) -> bool {
+        matches!(self.def_kind(def_id.into()), DefKind::SyntheticCoroutineBody)
+    }
+
     /// Returns `true` if the node pointed to by `def_id` is a general coroutine that implements `Coroutine`.
     /// This means it is neither an `async` or `gen` construct.
     pub fn is_general_coroutine(self, def_id: DefId) -> bool {
@@ -3168,6 +3174,18 @@ impl<'tcx> TyCtxt<'tcx> {
         self.impl_trait_header(def_id).map_or(ty::ImplPolarity::Positive, |h| h.polarity)
     }
 
+    pub fn needs_coroutine_by_move_body_def_id(self, def_id: LocalDefId) -> bool {
+        if let Some(hir::CoroutineKind::Desugared(_, hir::CoroutineSource::Closure)) =
+            self.coroutine_kind(def_id)
+            && let ty::Coroutine(_, args) = self.type_of(def_id).instantiate_identity().kind()
+            && args.as_coroutine().kind_ty().to_opt_closure_kind() != Some(ty::ClosureKind::FnOnce)
+        {
+            true
+        } else {
+            false
+        }
+    }
+
     /// Whether this is a trait implementation that has `#[diagnostic::do_not_recommend]`
     pub fn do_not_recommend_impl(self, def_id: DefId) -> bool {
         matches!(self.def_kind(def_id), DefKind::Impl { of_trait: true })