Auto merge of rust-lang#101710 - jyn514:move-dep-kind-node, r=cjgillot

Move DepKindStruct from rustc_middle to rustc_query_system

Helps with rust-lang#96524. cc https://rust-lang.zulipchat.com/#narrow/stream/241847-t-compiler.2Fwg-incr-comp/topic/Moving.20.60DepKindStruct.60.20to.20rustc_query_system.20.2396524

r? `@cjgillot`

Author: bors

compiler/rustc_middle/src/dep_graph/dep_node.rs

@@ -69,79 +69,6 @@ use std::hash::Hash;
 
 pub use rustc_query_system::dep_graph::{DepContext, DepNodeParams};
 
-/// This struct stores metadata about each DepKind.
-///
-/// Information is retrieved by indexing the `DEP_KINDS` array using the integer value
-/// of the `DepKind`. Overall, this allows to implement `DepContext` using this manual
-/// jump table instead of large matches.
-pub struct DepKindStruct<'tcx> {
-    /// Anonymous queries cannot be replayed from one compiler invocation to the next.
-    /// When their result is needed, it is recomputed. They are useful for fine-grained
-    /// dependency tracking, and caching within one compiler invocation.
-    pub is_anon: bool,
-
-    /// Eval-always queries do not track their dependencies, and are always recomputed, even if
-    /// their inputs have not changed since the last compiler invocation. The result is still
-    /// cached within one compiler invocation.
-    pub is_eval_always: bool,
-
-    /// Whether the query key can be recovered from the hashed fingerprint.
-    /// See [DepNodeParams] trait for the behaviour of each key type.
-    pub fingerprint_style: FingerprintStyle,
-
-    /// The red/green evaluation system will try to mark a specific DepNode in the
-    /// dependency graph as green by recursively trying to mark the dependencies of
-    /// that `DepNode` as green. While doing so, it will sometimes encounter a `DepNode`
-    /// where we don't know if it is red or green and we therefore actually have
-    /// to recompute its value in order to find out. Since the only piece of
-    /// information that we have at that point is the `DepNode` we are trying to
-    /// re-evaluate, we need some way to re-run a query from just that. This is what
-    /// `force_from_dep_node()` implements.
-    ///
-    /// In the general case, a `DepNode` consists of a `DepKind` and an opaque
-    /// GUID/fingerprint that will uniquely identify the node. This GUID/fingerprint
-    /// is usually constructed by computing a stable hash of the query-key that the
-    /// `DepNode` corresponds to. Consequently, it is not in general possible to go
-    /// back from hash to query-key (since hash functions are not reversible). For
-    /// this reason `force_from_dep_node()` is expected to fail from time to time
-    /// because we just cannot find out, from the `DepNode` alone, what the
-    /// corresponding query-key is and therefore cannot re-run the query.
-    ///
-    /// The system deals with this case letting `try_mark_green` fail which forces
-    /// the root query to be re-evaluated.
-    ///
-    /// Now, if `force_from_dep_node()` would always fail, it would be pretty useless.
-    /// Fortunately, we can use some contextual information that will allow us to
-    /// reconstruct query-keys for certain kinds of `DepNode`s. In particular, we
-    /// enforce by construction that the GUID/fingerprint of certain `DepNode`s is a
-    /// valid `DefPathHash`. Since we also always build a huge table that maps every
-    /// `DefPathHash` in the current codebase to the corresponding `DefId`, we have
-    /// everything we need to re-run the query.
-    ///
-    /// Take the `mir_promoted` query as an example. Like many other queries, it
-    /// just has a single parameter: the `DefId` of the item it will compute the
-    /// validated MIR for. Now, when we call `force_from_dep_node()` on a `DepNode`
-    /// with kind `MirValidated`, we know that the GUID/fingerprint of the `DepNode`
-    /// is actually a `DefPathHash`, and can therefore just look up the corresponding
-    /// `DefId` in `tcx.def_path_hash_to_def_id`.
-    pub force_from_dep_node: Option<fn(tcx: TyCtxt<'tcx>, dep_node: DepNode) -> bool>,
-
-    /// Invoke a query to put the on-disk cached value in memory.
-    pub try_load_from_on_disk_cache: Option<fn(TyCtxt<'tcx>, DepNode)>,
-}
-
-impl DepKind {
-    #[inline(always)]
-    pub fn fingerprint_style(self, tcx: TyCtxt<'_>) -> FingerprintStyle {
-        // Only fetch the DepKindStruct once.
-        let data = tcx.query_kind(self);
-        if data.is_anon {
-            return FingerprintStyle::Opaque;
-        }
-        data.fingerprint_style
-    }
-}
-
 macro_rules! define_dep_nodes {
     (
      $($(#[$attr:meta])*
@@ -159,7 +86,7 @@ macro_rules! define_dep_nodes {
             $( $( #[$attr] )* $variant),*
         }
 
-        fn dep_kind_from_label_string(label: &str) -> Result<DepKind, ()> {
+        pub(super) fn dep_kind_from_label_string(label: &str) -> Result<DepKind, ()> {
             match label {
                 $(stringify!($variant) => Ok(DepKind::$variant),)*
                 _ => Err(()),
@@ -214,11 +141,6 @@ static_assert_size!(DepNode, 18);
 static_assert_size!(DepNode, 24);
 
 pub trait DepNodeExt: Sized {
-    /// Construct a DepNode from the given DepKind and DefPathHash. This
-    /// method will assert that the given DepKind actually requires a
-    /// single DefId/DefPathHash parameter.
-    fn from_def_path_hash(tcx: TyCtxt<'_>, def_path_hash: DefPathHash, kind: DepKind) -> Self;
-
     /// Extracts the DefId corresponding to this DepNode. This will work
     /// if two conditions are met:
     ///
@@ -243,14 +165,6 @@ pub trait DepNodeExt: Sized {
 }
 
 impl DepNodeExt for DepNode {
-    /// Construct a DepNode from the given DepKind and DefPathHash. This
-    /// method will assert that the given DepKind actually requires a
-    /// single DefId/DefPathHash parameter.
-    fn from_def_path_hash(tcx: TyCtxt<'_>, def_path_hash: DefPathHash, kind: DepKind) -> DepNode {
-        debug_assert!(kind.fingerprint_style(tcx) == FingerprintStyle::DefPathHash);
-        DepNode { kind, hash: def_path_hash.0.into() }
-    }
-
     /// Extracts the DefId corresponding to this DepNode. This will work
     /// if two conditions are met:
     ///
@@ -262,7 +176,7 @@ impl DepNodeExt for DepNode {
     /// refers to something from the previous compilation session that
     /// has been removed.
     fn extract_def_id<'tcx>(&self, tcx: TyCtxt<'tcx>) -> Option<DefId> {
-        if self.kind.fingerprint_style(tcx) == FingerprintStyle::DefPathHash {
+        if tcx.fingerprint_style(self.kind) == FingerprintStyle::DefPathHash {
             Some(tcx.def_path_hash_to_def_id(DefPathHash(self.hash.into()), &mut || {
                 panic!("Failed to extract DefId: {:?} {}", self.kind, self.hash)
             }))
@@ -279,7 +193,7 @@ impl DepNodeExt for DepNode {
     ) -> Result<DepNode, ()> {
         let kind = dep_kind_from_label_string(label)?;
 
-        match kind.fingerprint_style(tcx) {
+        match tcx.fingerprint_style(kind) {
             FingerprintStyle::Opaque => Err(()),
             FingerprintStyle::Unit => Ok(DepNode::new_no_params(tcx, kind)),
             FingerprintStyle::DefPathHash => {

compiler/rustc_middle/src/dep_graph/mod.rs

@@ -11,15 +11,17 @@ pub use rustc_query_system::dep_graph::{
     SerializedDepNodeIndex, WorkProduct, WorkProductId,
 };
 
-pub use dep_node::{label_strs, DepKind, DepKindStruct, DepNode, DepNodeExt};
+pub use dep_node::{label_strs, DepKind, DepNode, DepNodeExt};
 pub(crate) use dep_node::{make_compile_codegen_unit, make_compile_mono_item};
 
 pub type DepGraph = rustc_query_system::dep_graph::DepGraph<DepKind>;
+
 pub type TaskDeps = rustc_query_system::dep_graph::TaskDeps<DepKind>;
 pub type TaskDepsRef<'a> = rustc_query_system::dep_graph::TaskDepsRef<'a, DepKind>;
 pub type DepGraphQuery = rustc_query_system::dep_graph::DepGraphQuery<DepKind>;
 pub type SerializedDepGraph = rustc_query_system::dep_graph::SerializedDepGraph<DepKind>;
 pub type EdgeFilter = rustc_query_system::dep_graph::debug::EdgeFilter<DepKind>;
+pub type DepKindStruct<'tcx> = rustc_query_system::dep_graph::DepKindStruct<TyCtxt<'tcx>>;
 
 impl rustc_query_system::dep_graph::DepKind for DepKind {
     const NULL: Self = DepKind::Null;
@@ -91,50 +93,8 @@ impl<'tcx> DepContext for TyCtxt<'tcx> {
         self.sess
     }
 
-    #[inline(always)]
-    fn fingerprint_style(&self, kind: DepKind) -> rustc_query_system::dep_graph::FingerprintStyle {
-        kind.fingerprint_style(*self)
-    }
-
-    #[inline(always)]
-    fn is_eval_always(&self, kind: DepKind) -> bool {
-        self.query_kind(kind).is_eval_always
-    }
-
-    fn try_force_from_dep_node(&self, dep_node: DepNode) -> bool {
-        debug!("try_force_from_dep_node({:?}) --- trying to force", dep_node);
-
-        // We must avoid ever having to call `force_from_dep_node()` for a
-        // `DepNode::codegen_unit`:
-        // Since we cannot reconstruct the query key of a `DepNode::codegen_unit`, we
-        // would always end up having to evaluate the first caller of the
-        // `codegen_unit` query that *is* reconstructible. This might very well be
-        // the `compile_codegen_unit` query, thus re-codegenning the whole CGU just
-        // to re-trigger calling the `codegen_unit` query with the right key. At
-        // that point we would already have re-done all the work we are trying to
-        // avoid doing in the first place.
-        // The solution is simple: Just explicitly call the `codegen_unit` query for
-        // each CGU, right after partitioning. This way `try_mark_green` will always
-        // hit the cache instead of having to go through `force_from_dep_node`.
-        // This assertion makes sure, we actually keep applying the solution above.
-        debug_assert!(
-            dep_node.kind != DepKind::codegen_unit,
-            "calling force_from_dep_node() on DepKind::codegen_unit"
-        );
-
-        let cb = self.query_kind(dep_node.kind);
-        if let Some(f) = cb.force_from_dep_node {
-            f(*self, dep_node);
-            true
-        } else {
-            false
-        }
-    }
-
-    fn try_load_from_on_disk_cache(&self, dep_node: DepNode) {
-        let cb = self.query_kind(dep_node.kind);
-        if let Some(f) = cb.try_load_from_on_disk_cache {
-            f(*self, dep_node)
-        }
+    #[inline]
+    fn dep_kind_info(&self, dep_kind: DepKind) -> &DepKindStruct<'tcx> {
+        &self.query_kinds[dep_kind as usize]
     }
 }

compiler/rustc_middle/src/ty/context.rs

@@ -1,7 +1,7 @@
 //! Type context book-keeping.
 
 use crate::arena::Arena;
-use crate::dep_graph::{DepGraph, DepKind, DepKindStruct};
+use crate::dep_graph::{DepGraph, DepKindStruct};
 use crate::hir::place::Place as HirPlace;
 use crate::infer::canonical::{Canonical, CanonicalVarInfo, CanonicalVarInfos};
 use crate::lint::{struct_lint_level, LintLevelSource};
@@ -1085,7 +1085,7 @@ pub struct GlobalCtxt<'tcx> {
 
     pub queries: &'tcx dyn query::QueryEngine<'tcx>,
     pub query_caches: query::QueryCaches<'tcx>,
-    query_kinds: &'tcx [DepKindStruct<'tcx>],
+    pub(crate) query_kinds: &'tcx [DepKindStruct<'tcx>],
 
     // Internal caches for metadata decoding. No need to track deps on this.
     pub ty_rcache: Lock<FxHashMap<ty::CReaderCacheKey, Ty<'tcx>>>,
@@ -1292,10 +1292,6 @@ impl<'tcx> TyCtxt<'tcx> {
         }
     }
 
-    pub(crate) fn query_kind(self, k: DepKind) -> &'tcx DepKindStruct<'tcx> {
-        &self.query_kinds[k as usize]
-    }
-
     /// Constructs a `TyKind::Error` type and registers a `delay_span_bug` to ensure it gets used.
     #[track_caller]
     pub fn ty_error(self) -> Ty<'tcx> {

compiler/rustc_query_impl/src/plumbing.rs

@@ -380,6 +380,24 @@ where
     Q::Key: DepNodeParams<TyCtxt<'tcx>>,
     Q::Value: Value<TyCtxt<'tcx>>,
 {
+    // We must avoid ever having to call `force_from_dep_node()` for a
+    // `DepNode::codegen_unit`:
+    // Since we cannot reconstruct the query key of a `DepNode::codegen_unit`, we
+    // would always end up having to evaluate the first caller of the
+    // `codegen_unit` query that *is* reconstructible. This might very well be
+    // the `compile_codegen_unit` query, thus re-codegenning the whole CGU just
+    // to re-trigger calling the `codegen_unit` query with the right key. At
+    // that point we would already have re-done all the work we are trying to
+    // avoid doing in the first place.
+    // The solution is simple: Just explicitly call the `codegen_unit` query for
+    // each CGU, right after partitioning. This way `try_mark_green` will always
+    // hit the cache instead of having to go through `force_from_dep_node`.
+    // This assertion makes sure, we actually keep applying the solution above.
+    debug_assert!(
+        dep_node.kind != DepKind::codegen_unit,
+        "calling force_from_dep_node() on DepKind::codegen_unit"
+    );
+
     if let Some(key) = Q::Key::recover(tcx, &dep_node) {
         #[cfg(debug_assertions)]
         let _guard = tracing::span!(tracing::Level::TRACE, stringify!($name), ?key).entered();

compiler/rustc_query_system/src/dep_graph/dep_node.rs

@@ -47,6 +47,7 @@ use crate::ich::StableHashingContext;
 
 use rustc_data_structures::fingerprint::{Fingerprint, PackedFingerprint};
 use rustc_data_structures::stable_hasher::{HashStable, StableHasher};
+use rustc_hir::definitions::DefPathHash;
 use std::fmt;
 use std::hash::Hash;
 
@@ -88,6 +89,17 @@ impl<K: DepKind> DepNode<K> {
 
         dep_node
     }
+
+    /// Construct a DepNode from the given DepKind and DefPathHash. This
+    /// method will assert that the given DepKind actually requires a
+    /// single DefId/DefPathHash parameter.
+    pub fn from_def_path_hash<Ctxt>(tcx: Ctxt, def_path_hash: DefPathHash, kind: K) -> Self
+    where
+        Ctxt: super::DepContext<DepKind = K>,
+    {
+        debug_assert!(tcx.fingerprint_style(kind) == FingerprintStyle::DefPathHash);
+        DepNode { kind, hash: def_path_hash.0.into() }
+    }
 }
 
 impl<K: DepKind> fmt::Debug for DepNode<K> {
@@ -149,6 +161,67 @@ where
     }
 }
 
+/// This struct stores metadata about each DepKind.
+///
+/// Information is retrieved by indexing the `DEP_KINDS` array using the integer value
+/// of the `DepKind`. Overall, this allows to implement `DepContext` using this manual
+/// jump table instead of large matches.
+pub struct DepKindStruct<CTX: DepContext> {
+    /// Anonymous queries cannot be replayed from one compiler invocation to the next.
+    /// When their result is needed, it is recomputed. They are useful for fine-grained
+    /// dependency tracking, and caching within one compiler invocation.
+    pub is_anon: bool,
+
+    /// Eval-always queries do not track their dependencies, and are always recomputed, even if
+    /// their inputs have not changed since the last compiler invocation. The result is still
+    /// cached within one compiler invocation.
+    pub is_eval_always: bool,
+
+    /// Whether the query key can be recovered from the hashed fingerprint.
+    /// See [DepNodeParams] trait for the behaviour of each key type.
+    pub fingerprint_style: FingerprintStyle,
+
+    /// The red/green evaluation system will try to mark a specific DepNode in the
+    /// dependency graph as green by recursively trying to mark the dependencies of
+    /// that `DepNode` as green. While doing so, it will sometimes encounter a `DepNode`
+    /// where we don't know if it is red or green and we therefore actually have
+    /// to recompute its value in order to find out. Since the only piece of
+    /// information that we have at that point is the `DepNode` we are trying to
+    /// re-evaluate, we need some way to re-run a query from just that. This is what
+    /// `force_from_dep_node()` implements.
+    ///
+    /// In the general case, a `DepNode` consists of a `DepKind` and an opaque
+    /// GUID/fingerprint that will uniquely identify the node. This GUID/fingerprint
+    /// is usually constructed by computing a stable hash of the query-key that the
+    /// `DepNode` corresponds to. Consequently, it is not in general possible to go
+    /// back from hash to query-key (since hash functions are not reversible). For
+    /// this reason `force_from_dep_node()` is expected to fail from time to time
+    /// because we just cannot find out, from the `DepNode` alone, what the
+    /// corresponding query-key is and therefore cannot re-run the query.
+    ///
+    /// The system deals with this case letting `try_mark_green` fail which forces
+    /// the root query to be re-evaluated.
+    ///
+    /// Now, if `force_from_dep_node()` would always fail, it would be pretty useless.
+    /// Fortunately, we can use some contextual information that will allow us to
+    /// reconstruct query-keys for certain kinds of `DepNode`s. In particular, we
+    /// enforce by construction that the GUID/fingerprint of certain `DepNode`s is a
+    /// valid `DefPathHash`. Since we also always build a huge table that maps every
+    /// `DefPathHash` in the current codebase to the corresponding `DefId`, we have
+    /// everything we need to re-run the query.
+    ///
+    /// Take the `mir_promoted` query as an example. Like many other queries, it
+    /// just has a single parameter: the `DefId` of the item it will compute the
+    /// validated MIR for. Now, when we call `force_from_dep_node()` on a `DepNode`
+    /// with kind `MirValidated`, we know that the GUID/fingerprint of the `DepNode`
+    /// is actually a `DefPathHash`, and can therefore just look up the corresponding
+    /// `DefId` in `tcx.def_path_hash_to_def_id`.
+    pub force_from_dep_node: Option<fn(tcx: CTX, dep_node: DepNode<CTX::DepKind>) -> bool>,
+
+    /// Invoke a query to put the on-disk cached value in memory.
+    pub try_load_from_on_disk_cache: Option<fn(CTX, DepNode<CTX::DepKind>)>,
+}
+
 /// A "work product" corresponds to a `.o` (or other) file that we
 /// save in between runs. These IDs do not have a `DefId` but rather
 /// some independent path or string that persists between runs without