Auto merge of #127779 - momvart:should_codegen_hook, r=<try>

Add a hook for `should_codegen_locally`

This PR lifts the module-local function `should_codegen_locally` to `TyCtxt` as a hook.
In addition to monomorphization, this function is used for checking the dependency of `compiler_builtins` on other libraries. Moving this function to the hooks also makes overriding it possible for the tools that use the rustc interface.

Author: bors

compiler/rustc_codegen_cranelift/src/abi/mod.rs

@@ -10,12 +10,12 @@ use std::mem;
 use cranelift_codegen::ir::{ArgumentPurpose, SigRef};
 use cranelift_codegen::isa::CallConv;
 use cranelift_module::ModuleError;
+use rustc_codegen_ssa::base::is_call_from_compiler_builtins_to_upstream_monomorphization;
 use rustc_codegen_ssa::errors::CompilerBuiltinsCannotCall;
 use rustc_middle::middle::codegen_fn_attrs::CodegenFnAttrFlags;
 use rustc_middle::ty::layout::FnAbiOf;
 use rustc_middle::ty::print::with_no_trimmed_paths;
 use rustc_middle::ty::TypeVisitableExt;
-use rustc_monomorphize::is_call_from_compiler_builtins_to_upstream_monomorphization;
 use rustc_session::Session;
 use rustc_span::source_map::Spanned;
 use rustc_target::abi::call::{Conv, FnAbi, PassMode};

compiler/rustc_codegen_cranelift/src/base.rs

@@ -5,13 +5,13 @@ use cranelift_codegen::CodegenError;
 use cranelift_frontend::{FunctionBuilder, FunctionBuilderContext};
 use cranelift_module::ModuleError;
 use rustc_ast::InlineAsmOptions;
+use rustc_codegen_ssa::base::is_call_from_compiler_builtins_to_upstream_monomorphization;
 use rustc_index::IndexVec;
 use rustc_middle::middle::codegen_fn_attrs::CodegenFnAttrFlags;
 use rustc_middle::ty::adjustment::PointerCoercion;
 use rustc_middle::ty::layout::FnAbiOf;
 use rustc_middle::ty::print::with_no_trimmed_paths;
 use rustc_middle::ty::TypeVisitableExt;
-use rustc_monomorphize::is_call_from_compiler_builtins_to_upstream_monomorphization;
 
 use crate::constant::ConstantCx;
 use crate::debuginfo::{FunctionDebugContext, TypeDebugContext};

compiler/rustc_codegen_cranelift/src/lib.rs

@@ -24,7 +24,6 @@ extern crate rustc_hir;
 extern crate rustc_incremental;
 extern crate rustc_index;
 extern crate rustc_metadata;
-extern crate rustc_monomorphize;
 extern crate rustc_session;
 extern crate rustc_span;
 extern crate rustc_target;

compiler/rustc_codegen_ssa/src/base.rs

@@ -806,6 +806,34 @@ pub fn codegen_crate<B: ExtraBackendMethods>(
     ongoing_codegen
 }
 
+/// Returns whether a call from the current crate to the [`Instance`] would produce a call
+/// from `compiler_builtins` to a symbol the linker must resolve.
+///
+/// Such calls from `compiler_bultins` are effectively impossible for the linker to handle. Some
+/// linkers will optimize such that dead calls to unresolved symbols are not an error, but this is
+/// not guaranteed. So we used this function in codegen backends to ensure we do not generate any
+/// unlinkable calls.
+///
+/// Note that calls to LLVM intrinsics are uniquely okay because they won't make it to the linker.
+pub fn is_call_from_compiler_builtins_to_upstream_monomorphization<'tcx>(
+    tcx: TyCtxt<'tcx>,
+    instance: Instance<'tcx>,
+) -> bool {
+    fn is_llvm_intrinsic(tcx: TyCtxt<'_>, def_id: DefId) -> bool {
+        if let Some(name) = tcx.codegen_fn_attrs(def_id).link_name {
+            name.as_str().starts_with("llvm.")
+        } else {
+            false
+        }
+    }
+
+    let def_id = instance.def_id();
+    !def_id.is_local()
+        && tcx.is_compiler_builtins(LOCAL_CRATE)
+        && !is_llvm_intrinsic(tcx, def_id)
+        && !tcx.should_codegen_locally(instance)
+}
+
 impl CrateInfo {
     pub fn new(tcx: TyCtxt<'_>, target_cpu: String) -> CrateInfo {
         let crate_types = tcx.crate_types().to_vec();

compiler/rustc_codegen_ssa/src/mir/block.rs

@@ -3,7 +3,7 @@ use super::operand::OperandValue::{Immediate, Pair, Ref, ZeroSized};
 use super::place::{PlaceRef, PlaceValue};
 use super::{CachedLlbb, FunctionCx, LocalRef};
 
-use crate::base;
+use crate::base::{self, is_call_from_compiler_builtins_to_upstream_monomorphization};
 use crate::common::{self, IntPredicate};
 use crate::errors::CompilerBuiltinsCannotCall;
 use crate::meth;
@@ -18,7 +18,6 @@ use rustc_middle::ty::layout::{HasTyCtxt, LayoutOf, ValidityRequirement};
 use rustc_middle::ty::print::{with_no_trimmed_paths, with_no_visible_paths};
 use rustc_middle::ty::{self, Instance, Ty};
 use rustc_middle::{bug, span_bug};
-use rustc_monomorphize::is_call_from_compiler_builtins_to_upstream_monomorphization;
 use rustc_session::config::OptLevel;
 use rustc_span::{source_map::Spanned, sym, Span};
 use rustc_target::abi::call::{ArgAbi, FnAbi, PassMode, Reg};

compiler/rustc_middle/src/hooks/mod.rs

@@ -103,6 +103,10 @@ declare_hooks! {
 
     /// Create a list-like THIR representation for debugging.
     hook thir_flat(key: LocalDefId) -> String;
+
+    /// Returns `true` if we should codegen an instance in the local crate, or returns `false` if we
+    /// can just link to the upstream crate and therefore don't need a mono item.
+    hook should_codegen_locally(instance: crate::ty::Instance<'tcx>) -> bool;
 }
 
 #[cold]

compiler/rustc_monomorphize/src/collector.rs

@@ -228,6 +228,7 @@ use rustc_middle::ty::{
     self, AssocKind, GenericParamDefKind, Instance, InstanceKind, Ty, TyCtxt, TypeFoldable,
     TypeVisitableExt, VtblEntry,
 };
+use rustc_middle::util::Providers;
 use rustc_middle::{bug, span_bug};
 use rustc_session::config::EntryFnType;
 use rustc_session::Limit;
@@ -399,7 +400,7 @@ fn collect_items_rec<'tcx>(
                 let instance = Instance::mono(tcx, def_id);
 
                 // Sanity check whether this ended up being collected accidentally
-                debug_assert!(should_codegen_locally(tcx, instance));
+                debug_assert!(tcx.should_codegen_locally(instance));
 
                 let DefKind::Static { nested, .. } = tcx.def_kind(def_id) else { bug!() };
                 // Nested statics have no type.
@@ -431,7 +432,7 @@ fn collect_items_rec<'tcx>(
         }
         MonoItem::Fn(instance) => {
             // Sanity check whether this ended up being collected accidentally
-            debug_assert!(should_codegen_locally(tcx, instance));
+            debug_assert!(tcx.should_codegen_locally(instance));
 
             // Keep track of the monomorphization recursion depth
             recursion_depth_reset = Some(check_recursion_limit(
@@ -475,7 +476,7 @@ fn collect_items_rec<'tcx>(
                         }
                         hir::InlineAsmOperand::SymStatic { path: _, def_id } => {
                             let instance = Instance::mono(tcx, *def_id);
-                            if should_codegen_locally(tcx, instance) {
+                            if tcx.should_codegen_locally(instance) {
                                 trace!("collecting static {:?}", def_id);
                                 used_items.push(dummy_spanned(MonoItem::Static(*def_id)));
                             }
@@ -712,7 +713,7 @@ impl<'a, 'tcx> MirVisitor<'tcx> for MirUsedCollector<'a, 'tcx> {
                 if let ty::Closure(def_id, args) = *source_ty.kind() {
                     let instance =
                         Instance::resolve_closure(self.tcx, def_id, args, ty::ClosureKind::FnOnce);
-                    if should_codegen_locally(self.tcx, instance) {
+                    if self.tcx.should_codegen_locally(instance) {
                         self.used_items.push(create_fn_mono_item(self.tcx, instance, span));
                     }
                 } else {
@@ -722,7 +723,7 @@ impl<'a, 'tcx> MirVisitor<'tcx> for MirUsedCollector<'a, 'tcx> {
             mir::Rvalue::ThreadLocalRef(def_id) => {
                 assert!(self.tcx.is_thread_local_static(def_id));
                 let instance = Instance::mono(self.tcx, def_id);
-                if should_codegen_locally(self.tcx, instance) {
+                if self.tcx.should_codegen_locally(instance) {
                     trace!("collecting thread-local static {:?}", def_id);
                     self.used_items.push(respan(span, MonoItem::Static(def_id)));
                 }
@@ -749,7 +750,7 @@ impl<'a, 'tcx> MirVisitor<'tcx> for MirUsedCollector<'a, 'tcx> {
         let tcx = self.tcx;
         let push_mono_lang_item = |this: &mut Self, lang_item: LangItem| {
             let instance = Instance::mono(tcx, tcx.require_lang_item(lang_item, Some(source)));
-            if should_codegen_locally(tcx, instance) {
+            if tcx.should_codegen_locally(instance) {
                 this.used_items.push(create_fn_mono_item(tcx, instance, source));
             }
         };
@@ -783,7 +784,7 @@ impl<'a, 'tcx> MirVisitor<'tcx> for MirUsedCollector<'a, 'tcx> {
                         }
                         mir::InlineAsmOperand::SymStatic { def_id } => {
                             let instance = Instance::mono(self.tcx, def_id);
-                            if should_codegen_locally(self.tcx, instance) {
+                            if self.tcx.should_codegen_locally(instance) {
                                 trace!("collecting asm sym static {:?}", def_id);
                                 self.used_items.push(respan(source, MonoItem::Static(def_id)));
                             }
@@ -873,7 +874,7 @@ fn visit_instance_use<'tcx>(
     output: &mut MonoItems<'tcx>,
 ) {
     debug!("visit_item_use({:?}, is_direct_call={:?})", instance, is_direct_call);
-    if !should_codegen_locally(tcx, instance) {
+    if !tcx.should_codegen_locally(instance) {
         return;
     }
     if let ty::InstanceKind::Intrinsic(def_id) = instance.def {
@@ -885,13 +886,13 @@ fn visit_instance_use<'tcx>(
             // codegen a call to that function without generating code for the function itself.
             let def_id = tcx.require_lang_item(LangItem::PanicNounwind, None);
             let panic_instance = Instance::mono(tcx, def_id);
-            if should_codegen_locally(tcx, panic_instance) {
+            if tcx.should_codegen_locally(panic_instance) {
                 output.push(create_fn_mono_item(tcx, panic_instance, source));
             }
         } else if tcx.has_attr(def_id, sym::rustc_intrinsic) {
             // Codegen the fallback body of intrinsics with fallback bodies
             let instance = ty::Instance::new(def_id, instance.args);
-            if should_codegen_locally(tcx, instance) {
+            if tcx.should_codegen_locally(instance) {
                 output.push(create_fn_mono_item(tcx, instance, source));
             }
         }
@@ -930,7 +931,7 @@ fn visit_instance_use<'tcx>(
 
 /// Returns `true` if we should codegen an instance in the local crate, or returns `false` if we
 /// can just link to the upstream crate and therefore don't need a mono item.
-pub(crate) fn should_codegen_locally<'tcx>(tcx: TyCtxt<'tcx>, instance: Instance<'tcx>) -> bool {
+fn should_codegen_locally<'tcx>(tcx: TyCtxtAt<'tcx>, instance: Instance<'tcx>) -> bool {
     let Some(def_id) = instance.def.def_id_if_not_guaranteed_local_codegen() else {
         return true;
     };
@@ -946,7 +947,7 @@ pub(crate) fn should_codegen_locally<'tcx>(tcx: TyCtxt<'tcx>, instance: Instance
     }
 
     if tcx.is_reachable_non_generic(def_id)
-        || instance.polymorphize(tcx).upstream_monomorphization(tcx).is_some()
+        || instance.polymorphize(*tcx).upstream_monomorphization(*tcx).is_some()
     {
         // We can link to the item in question, no instance needed in this crate.
         return false;
@@ -1127,7 +1128,7 @@ fn create_mono_items_for_vtable_methods<'tcx>(
                     None
                 }
                 VtblEntry::Method(instance) => {
-                    Some(*instance).filter(|instance| should_codegen_locally(tcx, *instance))
+                    Some(*instance).filter(|instance| tcx.should_codegen_locally(*instance))
                 }
             })
             .map(|item| create_fn_mono_item(tcx, item, source));
@@ -1144,7 +1145,7 @@ fn collect_alloc<'tcx>(tcx: TyCtxt<'tcx>, alloc_id: AllocId, output: &mut MonoIt
         GlobalAlloc::Static(def_id) => {
             assert!(!tcx.is_thread_local_static(def_id));
             let instance = Instance::mono(tcx, def_id);
-            if should_codegen_locally(tcx, instance) {
+            if tcx.should_codegen_locally(instance) {
                 trace!("collecting static {:?}", def_id);
                 output.push(dummy_spanned(MonoItem::Static(def_id)));
             }
@@ -1162,7 +1163,7 @@ fn collect_alloc<'tcx>(tcx: TyCtxt<'tcx>, alloc_id: AllocId, output: &mut MonoIt
             }
         }
         GlobalAlloc::Function { instance, .. } => {
-            if should_codegen_locally(tcx, instance) {
+            if tcx.should_codegen_locally(instance) {
                 trace!("collecting {:?} with {:#?}", alloc_id, instance);
                 output.push(create_fn_mono_item(tcx, instance, DUMMY_SP));
             }
@@ -1284,7 +1285,7 @@ fn visit_mentioned_item<'tcx>(
             if let ty::Closure(def_id, args) = *source_ty.kind() {
                 let instance =
                     Instance::resolve_closure(tcx, def_id, args, ty::ClosureKind::FnOnce);
-                if should_codegen_locally(tcx, instance) {
+                if tcx.should_codegen_locally(instance) {
                     output.push(create_fn_mono_item(tcx, instance, span));
                 }
             } else {
@@ -1557,7 +1558,7 @@ fn create_mono_items_for_default_impls<'tcx>(
         let instance = ty::Instance::expect_resolve(tcx, param_env, method.def_id, args, DUMMY_SP);
 
         let mono_item = create_fn_mono_item(tcx, instance, DUMMY_SP);
-        if mono_item.node.is_instantiable(tcx) && should_codegen_locally(tcx, instance) {
+        if mono_item.node.is_instantiable(tcx) && tcx.should_codegen_locally(instance) {
             output.push(mono_item);
         }
     }
@@ -1613,3 +1614,7 @@ pub(crate) fn collect_crate_mono_items<'tcx>(
 
     (mono_items, state.usage_map.into_inner())
 }
+
+pub fn provide(providers: &mut Providers) {
+    providers.hooks.should_codegen_locally = should_codegen_locally;
+}

compiler/rustc_monomorphize/src/lib.rs

@@ -5,14 +5,11 @@
 
 use rustc_hir::lang_items::LangItem;
 use rustc_middle::bug;
-use rustc_middle::query::{Providers, TyCtxtAt};
+use rustc_middle::query::TyCtxtAt;
 use rustc_middle::traits;
 use rustc_middle::ty::adjustment::CustomCoerceUnsized;
-use rustc_middle::ty::Instance;
-use rustc_middle::ty::TyCtxt;
 use rustc_middle::ty::{self, Ty};
-use rustc_span::def_id::DefId;
-use rustc_span::def_id::LOCAL_CRATE;
+use rustc_middle::util::Providers;
 use rustc_span::ErrorGuaranteed;
 
 mod collector;
@@ -21,8 +18,6 @@ mod partitioning;
 mod polymorphize;
 mod util;
 
-use collector::should_codegen_locally;
-
 rustc_fluent_macro::fluent_messages! { "../messages.ftl" }
 
 fn custom_coerce_unsize_info<'tcx>(
@@ -47,34 +42,6 @@ fn custom_coerce_unsize_info<'tcx>(
     }
 }
 
-/// Returns whether a call from the current crate to the [`Instance`] would produce a call
-/// from `compiler_builtins` to a symbol the linker must resolve.
-///
-/// Such calls from `compiler_bultins` are effectively impossible for the linker to handle. Some
-/// linkers will optimize such that dead calls to unresolved symbols are not an error, but this is
-/// not guaranteed. So we used this function in codegen backends to ensure we do not generate any
-/// unlinkable calls.
-///
-/// Note that calls to LLVM intrinsics are uniquely okay because they won't make it to the linker.
-pub fn is_call_from_compiler_builtins_to_upstream_monomorphization<'tcx>(
-    tcx: TyCtxt<'tcx>,
-    instance: Instance<'tcx>,
-) -> bool {
-    fn is_llvm_intrinsic(tcx: TyCtxt<'_>, def_id: DefId) -> bool {
-        if let Some(name) = tcx.codegen_fn_attrs(def_id).link_name {
-            name.as_str().starts_with("llvm.")
-        } else {
-            false
-        }
-    }
-
-    let def_id = instance.def_id();
-    !def_id.is_local()
-        && tcx.is_compiler_builtins(LOCAL_CRATE)
-        && !is_llvm_intrinsic(tcx, def_id)
-        && !should_codegen_locally(tcx, instance)
-}
-
 pub fn provide(providers: &mut Providers) {
     partitioning::provide(providers);
     polymorphize::provide(providers);

compiler/rustc_monomorphize/src/partitioning.rs

@@ -112,9 +112,9 @@ use rustc_middle::mir::mono::{
     CodegenUnit, CodegenUnitNameBuilder, InstantiationMode, Linkage, MonoItem, MonoItemData,
     Visibility,
 };
-use rustc_middle::query::Providers;
 use rustc_middle::ty::print::{characteristic_def_id_of_type, with_no_trimmed_paths};
 use rustc_middle::ty::{self, visit::TypeVisitableExt, InstanceKind, TyCtxt};
+use rustc_middle::util::Providers;
 use rustc_session::config::{DumpMonoStatsFormat, SwitchWithOptPath};
 use rustc_session::CodegenUnits;
 use rustc_span::symbol::Symbol;
@@ -1314,4 +1314,6 @@ pub fn provide(providers: &mut Providers) {
             .find(|cgu| cgu.name() == name)
             .unwrap_or_else(|| panic!("failed to find cgu with name {name:?}"))
     };
+
+    collector::provide(providers);
 }