Auto merge of #108638 - Zoxc:erase-query-values-map, r=cjgillot

Use dynamic dispatch for queries

This replaces most concrete query values `V` with `MaybeUninit<[u8; { size_of::<V>() }]>` reducing the code instantiated by queries. The compile time of `rustc_query_impl` is reduced by 27%. It is an alternative to #107937 which uses unstable const generics while this uses a `EraseType` trait which maps query values to their erased variant.

This is achieved by introducing an `Erased` type which does sanity check with `cfg(debug_assertions)`. The query caches gets instantiated with these erased types leaving the code in `rustc_query_system` unaware of them. `rustc_query_system` is changed to use instances of `QueryConfig` so that `rustc_query_impl` can pass in `DynamicConfig` which holds a pointer to a virtual table.

<table><tr><td rowspan="2">Benchmark</td><td colspan="1"><b>Before</b></th><td colspan="2"><b>After</b></th></tr><tr><td align="right">Time</td><td align="right">Time</td><td align="right">%</th></tr><tr><td>🟣 <b>clap</b>:check</td><td align="right">1.7055s</td><td align="right">1.6949s</td><td align="right"> -0.62%</td></tr><tr><td>🟣 <b>hyper</b>:check</td><td align="right">0.2547s</td><td align="right">0.2528s</td><td align="right"> -0.73%</td></tr><tr><td>🟣 <b>regex</b>:check</td><td align="right">0.9590s</td><td align="right">0.9553s</td><td align="right"> -0.39%</td></tr><tr><td>🟣 <b>syn</b>:check</td><td align="right">1.5457s</td><td align="right">1.5440s</td><td align="right"> -0.11%</td></tr><tr><td>🟣 <b>syntex_syntax</b>:check</td><td align="right">5.9092s</td><td align="right">5.9009s</td><td align="right"> -0.14%</td></tr><tr><td>Total</td><td align="right">10.3741s</td><td align="right">10.3479s</td><td align="right"> -0.25%</td></tr><tr><td>Summary</td><td align="right">1.0000s</td><td align="right">0.9960s</td><td align="right"> -0.40%</td></tr></table>

<table><tr><td rowspan="2">Benchmark</td><td colspan="1"><b>Before</b></th><td colspan="2"><b>After</b></th></tr><tr><td align="right">Time</td><td align="right">Time</td><td align="right">%</th></tr><tr><td>🟣 <b>clap</b>:check:initial</td><td align="right">2.0605s</td><td align="right">2.0575s</td><td align="right"> -0.15%</td></tr><tr><td>🟣 <b>hyper</b>:check:initial</td><td align="right">0.3218s</td><td align="right">0.3216s</td><td align="right"> -0.07%</td></tr><tr><td>🟣 <b>regex</b>:check:initial</td><td align="right">1.1848s</td><td align="right">1.1839s</td><td align="right"> -0.07%</td></tr><tr><td>🟣 <b>syn</b>:check:initial</td><td align="right">1.9409s</td><td align="right">1.9376s</td><td align="right"> -0.17%</td></tr><tr><td>🟣 <b>syntex_syntax</b>:check:initial</td><td align="right">7.3105s</td><td align="right">7.2928s</td><td align="right"> -0.24%</td></tr><tr><td>Total</td><td align="right">12.8185s</td><td align="right">12.7935s</td><td align="right"> -0.20%</td></tr><tr><td>Summary</td><td align="right">1.0000s</td><td align="right">0.9986s</td><td align="right"> -0.14%</td></tr></table>

<table><tr><td rowspan="2">Benchmark</td><td colspan="1"><b>Before</b></th><td colspan="2"><b>After</b></th></tr><tr><td align="right">Time</td><td align="right">Time</td><td align="right">%</th></tr><tr><td>🟣 <b>clap</b>:check:unchanged</td><td align="right">0.4606s</td><td align="right">0.4617s</td><td align="right"> 0.24%</td></tr><tr><td>🟣 <b>hyper</b>:check:unchanged</td><td align="right">0.1335s</td><td align="right">0.1336s</td><td align="right"> 0.08%</td></tr><tr><td>🟣 <b>regex</b>:check:unchanged</td><td align="right">0.3324s</td><td align="right">0.3346s</td><td align="right"> 0.65%</td></tr><tr><td>🟣 <b>syn</b>:check:unchanged</td><td align="right">0.6268s</td><td align="right">0.6307s</td><td align="right"> 0.64%</td></tr><tr><td>🟣 <b>syntex_syntax</b>:check:unchanged</td><td align="right">1.8248s</td><td align="right">1.8508s</td><td align="right">💔  1.43%</td></tr><tr><td>Total</td><td align="right">3.3779s</td><td align="right">3.4113s</td><td align="right"> 0.99%</td></tr><tr><td>Summary</td><td align="right">1.0000s</td><td align="right">1.0061s</td><td align="right"> 0.61%</td></tr></table>

It's based on #108167.

r? `@cjgillot`

Cargo.lock

@@ -854,7 +854,7 @@ dependencies = [
  "autocfg",
  "cfg-if",
  "crossbeam-utils",
- "memoffset",
+ "memoffset 0.7.1",
  "scopeguard",
 ]
 
@@ -1241,6 +1241,16 @@ dependencies = [
  "instant",
 ]
 
+[[package]]
+name = "field-offset"
+version = "0.3.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "a3cf3a800ff6e860c863ca6d4b16fd999db8b752819c1606884047b73e468535"
+dependencies = [
+ "memoffset 0.8.0",
+ "rustc_version",
+]
+
 [[package]]
 name = "filetime"
 version = "0.2.20"
@@ -2188,6 +2198,15 @@ dependencies = [
  "libc",
 ]
 
+[[package]]
+name = "memoffset"
+version = "0.6.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "5aa361d4faea93603064a027415f07bd8e1d5c88c9fbf68bf56a285428fd79ce"
+dependencies = [
+ "autocfg",
+]
+
 [[package]]
 name = "memoffset"
 version = "0.7.1"
@@ -2197,6 +2216,15 @@ dependencies = [
  "autocfg",
 ]
 
+[[package]]
+name = "memoffset"
+version = "0.8.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "d61c719bcfbcf5d62b3a09efa6088de8c54bc0bfcd3ea7ae39fcc186108b8de1"
+dependencies = [
+ "autocfg",
+]
+
 [[package]]
 name = "mime"
 version = "0.3.16"
@@ -3782,6 +3810,7 @@ dependencies = [
  "chalk-ir",
  "derive_more",
  "either",
+ "field-offset",
  "gsgdt",
  "measureme",
  "polonius-engine",
@@ -3996,7 +4025,9 @@ dependencies = [
 name = "rustc_query_impl"
 version = "0.0.0"
 dependencies = [
+ "field-offset",
  "measureme",
+ "memoffset 0.6.5",
  "rustc-rayon-core",
  "rustc_ast",
  "rustc_data_structures",

compiler/rustc_interface/src/interface.rs

@@ -352,7 +352,7 @@ pub fn try_print_query_stack(handler: &Handler, num_frames: Option<usize>) {
     // state if it was responsible for triggering the panic.
     let i = ty::tls::with_context_opt(|icx| {
         if let Some(icx) = icx {
-            print_query_stack(QueryCtxt { tcx: icx.tcx }, icx.query, handler, num_frames)
+            print_query_stack(QueryCtxt::new(icx.tcx), icx.query, handler, num_frames)
         } else {
             0
         }

compiler/rustc_interface/src/passes.rs

@@ -700,9 +700,12 @@ pub fn create_global_ctxt<'tcx>(
                 hir_arena,
                 untracked,
                 dep_graph,
-                query_result_on_disk_cache,
                 rustc_query_impl::query_callbacks(arena),
-                rustc_query_impl::query_system_fns(local_providers, extern_providers),
+                rustc_query_impl::query_system(
+                    local_providers,
+                    extern_providers,
+                    query_result_on_disk_cache,
+                ),
             )
         })
     })

compiler/rustc_middle/Cargo.toml

@@ -11,6 +11,7 @@ chalk-ir = "0.87.0"
 derive_more = "0.99.17"
 either = "1.5.0"
 gsgdt = "0.1.2"
+field-offset = "0.3.5"
 measureme = "10.0.0"
 polonius-engine = "0.13.0"
 rustc_apfloat = { path = "../rustc_apfloat" }

compiler/rustc_middle/src/ty/context.rs

@@ -14,14 +14,12 @@ use crate::middle::resolve_bound_vars;
 use crate::middle::stability;
 use crate::mir::interpret::{self, Allocation, ConstAllocation};
 use crate::mir::{Body, Local, Place, PlaceElem, ProjectionKind, Promoted};
-use crate::query::on_disk_cache::OnDiskCache;
 use crate::query::LocalCrate;
 use crate::thir::Thir;
 use crate::traits;
 use crate::traits::solve;
 use crate::traits::solve::{ExternalConstraints, ExternalConstraintsData};
 use crate::ty::query::QuerySystem;
-use crate::ty::query::QuerySystemFns;
 use crate::ty::query::{self, TyCtxtAt};
 use crate::ty::{
     self, AdtDef, AdtDefData, AdtKind, Binder, Const, ConstData, FloatTy, FloatVar, FloatVid,
@@ -653,9 +651,8 @@ impl<'tcx> TyCtxt<'tcx> {
         hir_arena: &'tcx WorkerLocal<hir::Arena<'tcx>>,
         untracked: Untracked,
         dep_graph: DepGraph,
-        on_disk_cache: Option<OnDiskCache<'tcx>>,
         query_kinds: &'tcx [DepKindStruct<'tcx>],
-        query_system_fns: QuerySystemFns<'tcx>,
+        query_system: QuerySystem<'tcx>,
     ) -> GlobalCtxt<'tcx> {
         let data_layout = s.target.parse_data_layout().unwrap_or_else(|err| {
             s.emit_fatal(err);
@@ -677,7 +674,7 @@ impl<'tcx> TyCtxt<'tcx> {
             lifetimes: common_lifetimes,
             consts: common_consts,
             untracked,
-            query_system: QuerySystem::new(query_system_fns, on_disk_cache),
+            query_system,
             query_kinds,
             ty_rcache: Default::default(),
             pred_rcache: Default::default(),

compiler/rustc_middle/src/ty/query.rs

@@ -43,6 +43,7 @@ use crate::ty::subst::{GenericArg, SubstsRef};
 use crate::ty::util::AlwaysRequiresDrop;
 use crate::ty::GeneratorDiagnosticData;
 use crate::ty::{self, CrateInherentImpls, ParamEnvAnd, Ty, TyCtxt, UnusedGenericParams};
+use field_offset::FieldOffset;
 use measureme::StringId;
 use rustc_arena::TypedArena;
 use rustc_ast as ast;
@@ -66,9 +67,12 @@ use rustc_hir::hir_id::OwnerId;
 use rustc_hir::lang_items::{LangItem, LanguageItems};
 use rustc_hir::{Crate, ItemLocalId, TraitCandidate};
 use rustc_index::IndexVec;
+use rustc_query_system::dep_graph::DepNodeIndex;
+use rustc_query_system::dep_graph::SerializedDepNodeIndex;
 use rustc_query_system::ich::StableHashingContext;
 pub(crate) use rustc_query_system::query::QueryJobId;
 use rustc_query_system::query::*;
+use rustc_query_system::HandleCycleError;
 use rustc_session::config::{EntryFnType, OptLevel, OutputFilenames, SymbolManglingVersion};
 use rustc_session::cstore::{CrateDepKind, CrateSource};
 use rustc_session::cstore::{ExternCrate, ForeignModule, LinkagePreference, NativeLib};
@@ -78,8 +82,6 @@ use rustc_span::symbol::Symbol;
 use rustc_span::{Span, DUMMY_SP};
 use rustc_target::abi;
 use rustc_target::spec::PanicStrategy;
-
-use std::marker::PhantomData;
 use std::mem;
 use std::ops::Deref;
 use std::path::PathBuf;
@@ -103,6 +105,31 @@ pub struct QueryStruct<'tcx> {
         Option<fn(TyCtxt<'tcx>, &mut CacheEncoder<'_, 'tcx>, &mut EncodedDepNodeIndex)>,
 }
 
+pub struct DynamicQuery<'tcx, C: QueryCache> {
+    pub name: &'static str,
+    pub eval_always: bool,
+    pub dep_kind: rustc_middle::dep_graph::DepKind,
+    pub handle_cycle_error: HandleCycleError,
+    pub query_state: FieldOffset<QueryStates<'tcx>, QueryState<C::Key, crate::dep_graph::DepKind>>,
+    pub query_cache: FieldOffset<QueryCaches<'tcx>, C>,
+    pub cache_on_disk: fn(tcx: TyCtxt<'tcx>, key: &C::Key) -> bool,
+    pub execute_query: fn(tcx: TyCtxt<'tcx>, k: C::Key) -> C::Value,
+    pub compute: fn(tcx: TyCtxt<'tcx>, key: C::Key) -> C::Value,
+    pub can_load_from_disk: bool,
+    pub try_load_from_disk: fn(
+        tcx: TyCtxt<'tcx>,
+        key: &C::Key,
+        prev_index: SerializedDepNodeIndex,
+        index: DepNodeIndex,
+    ) -> Option<C::Value>,
+    pub loadable_from_disk:
+        fn(tcx: TyCtxt<'tcx>, key: &C::Key, index: SerializedDepNodeIndex) -> bool,
+    pub hash_result: HashResult<C::Value>,
+    pub value_from_cycle_error:
+        fn(tcx: TyCtxt<'tcx>, cycle: &[QueryInfo<crate::dep_graph::DepKind>]) -> C::Value,
+    pub format_value: fn(&C::Value) -> String,
+}
+
 pub struct QuerySystemFns<'tcx> {
     pub engine: QueryEngine,
     pub local_providers: Providers,
@@ -120,6 +147,7 @@ pub struct QuerySystem<'tcx> {
     pub states: QueryStates<'tcx>,
     pub arenas: QueryArenas<'tcx>,
     pub caches: QueryCaches<'tcx>,
+    pub dynamic_queries: DynamicQueries<'tcx>,
 
     /// This provides access to the incremental compilation on-disk cache for query results.
     /// Do not access this directly. It is only meant to be used by
@@ -130,23 +158,6 @@ pub struct QuerySystem<'tcx> {
     pub fns: QuerySystemFns<'tcx>,
 
     pub jobs: AtomicU64,
-
-    // Since we erase query value types we tell the typesystem about them with `PhantomData`.
-    _phantom_values: QueryPhantomValues<'tcx>,
-}
-
-impl<'tcx> QuerySystem<'tcx> {
-    pub fn new(fns: QuerySystemFns<'tcx>, on_disk_cache: Option<OnDiskCache<'tcx>>) -> Self {
-        QuerySystem {
-            states: Default::default(),
-            arenas: Default::default(),
-            caches: Default::default(),
-            on_disk_cache,
-            fns,
-            jobs: AtomicU64::new(1),
-            _phantom_values: Default::default(),
-        }
-    }
 }
 
 #[derive(Copy, Clone)]
@@ -427,11 +438,6 @@ macro_rules! define_callbacks {
             }
         }
 
-        #[derive(Default)]
-        pub struct QueryPhantomValues<'tcx> {
-            $($(#[$attr])* pub $name: PhantomData<query_values::$name<'tcx>>,)*
-        }
-
         #[derive(Default)]
         pub struct QueryCaches<'tcx> {
             $($(#[$attr])* pub $name: query_storage::$name<'tcx>,)*
@@ -490,6 +496,12 @@ macro_rules! define_callbacks {
             })*
         }
 
+        pub struct DynamicQueries<'tcx> {
+            $(
+                pub $name: DynamicQuery<'tcx, query_storage::$name<'tcx>>,
+            )*
+        }
+
         #[derive(Default)]
         pub struct QueryStates<'tcx> {
             $(

compiler/rustc_query_impl/Cargo.toml

@@ -7,6 +7,8 @@ edition = "2021"
 
 
 [dependencies]
+memoffset = { version = "0.6.0", features = ["unstable_const"] }
+field-offset = "0.3.5"
 measureme = "10.0.0"
 rustc_ast = { path = "../rustc_ast" }
 rustc_data_structures = { path = "../rustc_data_structures" }