Auto merge of #122580 - saethlin:compiler-builtins-can-panic, r=pnkfelix

"Handle" calls to upstream monomorphizations in compiler_builtins

This is pretty cooked, but I think it works.

compiler-builtins has a long-standing problem that at link time, its rlib cannot contain any calls to `core`. And yet, in codegen we _love_ inserting calls to symbols in `core`, generally from various panic entrypoints.

I intend this PR to attack that problem as completely as possible. When we generate a function call, we now check if we are generating a function call from `compiler_builtins` and whether the callee is a function which was not lowered in the current crate, meaning we will have to link to it.

If those conditions are met, actually generating the call is asking for a linker error. So we don't. If the callee diverges, we lower to an abort with the same behavior as `core::intrinsics::abort`. If the callee does not diverge, we produce an error. This means that compiler-builtins can contain panics, but they'll SIGILL instead of panicking. I made non-diverging calls a compile error because I'm guessing that they'd mostly get into compiler-builtins by someone making a mistake while working on the crate, and compile errors are better than linker errors. We could turn such calls into aborts as well if that's preferred.

12 files changed, 108 insertions, 12 deletions

diff --git a/compiler/rustc_codegen_cranelift/src/abi/mod.rs b/compiler/rustc_codegen_cranelift/src/abi/mod.rs
index 6e846d721f2..b33587f8948 100644
--- a/compiler/rustc_codegen_cranelift/src/abi/mod.rs
+++ b/compiler/rustc_codegen_cranelift/src/abi/mod.rs
@@ -8,8 +8,11 @@ use std::borrow::Cow;
 
 use cranelift_codegen::ir::SigRef;
 use cranelift_module::ModuleError;
+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_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};
@@ -372,6 +375,17 @@ pub(crate) fn codegen_terminator_call<'tcx>(
             ty::Instance::expect_resolve(fx.tcx, ty::ParamEnv::reveal_all(), def_id, fn_args)
                 .polymorphize(fx.tcx);
 
+        if is_call_from_compiler_builtins_to_upstream_monomorphization(fx.tcx, instance) {
+            if target.is_some() {
+                let caller = with_no_trimmed_paths!(fx.tcx.def_path_str(fx.instance.def_id()));
+                let callee = with_no_trimmed_paths!(fx.tcx.def_path_str(def_id));
+                fx.tcx.dcx().emit_err(CompilerBuiltinsCannotCall { caller, callee });
+            } else {
+                fx.bcx.ins().trap(TrapCode::User(0));
+                return;
+            }
+        }
+
         if fx.tcx.symbol_name(instance).name.starts_with("llvm.") {
             crate::intrinsics::codegen_llvm_intrinsic_call(
                 fx,
diff --git a/compiler/rustc_codegen_cranelift/src/base.rs b/compiler/rustc_codegen_cranelift/src/base.rs
index 2415c2c90b2..047dc56a32e 100644
--- a/compiler/rustc_codegen_cranelift/src/base.rs
+++ b/compiler/rustc_codegen_cranelift/src/base.rs
@@ -8,6 +8,7 @@ use rustc_index::IndexVec;
 use rustc_middle::ty::adjustment::PointerCoercion;
 use rustc_middle::ty::layout::FnAbiOf;
 use rustc_middle::ty::print::with_no_trimmed_paths;
+use rustc_monomorphize::is_call_from_compiler_builtins_to_upstream_monomorphization;
 
 use crate::constant::ConstantCx;
 use crate::debuginfo::FunctionDebugContext;
@@ -999,6 +1000,12 @@ fn codegen_panic_inner<'tcx>(
     let def_id = fx.tcx.require_lang_item(lang_item, span);
 
     let instance = Instance::mono(fx.tcx, def_id).polymorphize(fx.tcx);
+
+    if is_call_from_compiler_builtins_to_upstream_monomorphization(fx.tcx, instance) {
+        fx.bcx.ins().trap(TrapCode::User(0));
+        return;
+    }
+
     let symbol_name = fx.tcx.symbol_name(instance).name;
 
     fx.lib_call(
diff --git a/compiler/rustc_codegen_cranelift/src/lib.rs b/compiler/rustc_codegen_cranelift/src/lib.rs
index 7e2e1f7c6ac..a59a39074f8 100644
--- a/compiler/rustc_codegen_cranelift/src/lib.rs
+++ b/compiler/rustc_codegen_cranelift/src/lib.rs
@@ -21,6 +21,7 @@ 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;
diff --git a/compiler/rustc_codegen_ssa/Cargo.toml b/compiler/rustc_codegen_ssa/Cargo.toml
index 7851b9e8e03..baf10622a6d 100644
--- a/compiler/rustc_codegen_ssa/Cargo.toml
+++ b/compiler/rustc_codegen_ssa/Cargo.toml
@@ -25,6 +25,7 @@ rustc_index = { path = "../rustc_index" }
 rustc_macros = { path = "../rustc_macros" }
 rustc_metadata = { path = "../rustc_metadata" }
 rustc_middle = { path = "../rustc_middle" }
+rustc_monomorphize = { path = "../rustc_monomorphize" }
 rustc_query_system = { path = "../rustc_query_system" }
 rustc_serialize = { path = "../rustc_serialize" }
 rustc_session = { path = "../rustc_session" }
diff --git a/compiler/rustc_codegen_ssa/messages.ftl b/compiler/rustc_codegen_ssa/messages.ftl
index 5ba66d1be43..d159fe58d3e 100644
--- a/compiler/rustc_codegen_ssa/messages.ftl
+++ b/compiler/rustc_codegen_ssa/messages.ftl
@@ -16,6 +16,9 @@ codegen_ssa_cgu_not_recorded =
 
 codegen_ssa_check_installed_visual_studio = please ensure that Visual Studio 2017 or later, or Build Tools for Visual Studio were installed with the Visual C++ option.
 
+codegen_ssa_compiler_builtins_cannot_call =
+    `compiler_builtins` cannot call functions through upstream monomorphizations; encountered invalid call from `{$caller}` to `{$callee}`
+
 codegen_ssa_copy_path = could not copy {$from} to {$to}: {$error}
 
 codegen_ssa_copy_path_buf = unable to copy {$source_file} to {$output_path}: {$error}
diff --git a/compiler/rustc_codegen_ssa/src/common.rs b/compiler/rustc_codegen_ssa/src/common.rs
index 44a2434238d..71fca403def 100644
--- a/compiler/rustc_codegen_ssa/src/common.rs
+++ b/compiler/rustc_codegen_ssa/src/common.rs
@@ -2,6 +2,7 @@
 
 use rustc_hir::LangItem;
 use rustc_middle::mir;
+use rustc_middle::ty::Instance;
 use rustc_middle::ty::{self, layout::TyAndLayout, Ty, TyCtxt};
 use rustc_span::Span;
 
@@ -120,11 +121,11 @@ pub fn build_langcall<'a, 'tcx, Bx: BuilderMethods<'a, 'tcx>>(
     bx: &Bx,
     span: Option<Span>,
     li: LangItem,
-) -> (Bx::FnAbiOfResult, Bx::Value) {
+) -> (Bx::FnAbiOfResult, Bx::Value, Instance<'tcx>) {
     let tcx = bx.tcx();
     let def_id = tcx.require_lang_item(li, span);
     let instance = ty::Instance::mono(tcx, def_id);
-    (bx.fn_abi_of_instance(instance, ty::List::empty()), bx.get_fn_addr(instance))
+    (bx.fn_abi_of_instance(instance, ty::List::empty()), bx.get_fn_addr(instance), instance)
 }
 
 // To avoid UB from LLVM, these two functions mask RHS with an
diff --git a/compiler/rustc_codegen_ssa/src/errors.rs b/compiler/rustc_codegen_ssa/src/errors.rs
index 3572ee301c8..b843d1bdf23 100644
--- a/compiler/rustc_codegen_ssa/src/errors.rs
+++ b/compiler/rustc_codegen_ssa/src/errors.rs
@@ -1030,3 +1030,10 @@ pub struct FailedToGetLayout<'tcx> {
 pub struct ErrorCreatingRemarkDir {
     pub error: std::io::Error,
 }
+
+#[derive(Diagnostic)]
+#[diag(codegen_ssa_compiler_builtins_cannot_call)]
+pub struct CompilerBuiltinsCannotCall {
+    pub caller: String,
+    pub callee: String,
+}
diff --git a/compiler/rustc_codegen_ssa/src/mir/block.rs b/compiler/rustc_codegen_ssa/src/mir/block.rs
index 02e7bb05b77..dcc27a4f0e5 100644
--- a/compiler/rustc_codegen_ssa/src/mir/block.rs
+++ b/compiler/rustc_codegen_ssa/src/mir/block.rs
@@ -5,6 +5,7 @@ use super::{CachedLlbb, FunctionCx, LocalRef};
 
 use crate::base;
 use crate::common::{self, IntPredicate};
+use crate::errors::CompilerBuiltinsCannotCall;
 use crate::meth;
 use crate::traits::*;
 use crate::MemFlags;
@@ -16,6 +17,7 @@ use rustc_middle::mir::{self, AssertKind, BasicBlock, SwitchTargets, UnwindTermi
 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_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};
@@ -157,8 +159,28 @@ impl<'a, 'tcx> TerminatorCodegenHelper<'tcx> {
         destination: Option<(ReturnDest<'tcx, Bx::Value>, mir::BasicBlock)>,
         mut unwind: mir::UnwindAction,
         copied_constant_arguments: &[PlaceRef<'tcx, <Bx as BackendTypes>::Value>],
+        instance: Option<Instance<'tcx>>,
         mergeable_succ: bool,
     ) -> MergingSucc {
+        let tcx = bx.tcx();
+        if let Some(instance) = instance {
+            if is_call_from_compiler_builtins_to_upstream_monomorphization(tcx, instance) {
+                if destination.is_some() {
+                    let caller = with_no_trimmed_paths!(tcx.def_path_str(fx.instance.def_id()));
+                    let callee = with_no_trimmed_paths!(tcx.def_path_str(instance.def_id()));
+                    tcx.dcx().emit_err(CompilerBuiltinsCannotCall { caller, callee });
+                } else {
+                    info!(
+                        "compiler_builtins call to diverging function {:?} replaced with abort",
+                        instance.def_id()
+                    );
+                    bx.abort();
+                    bx.unreachable();
+                    return MergingSucc::False;
+                }
+            }
+        }
+
         // If there is a cleanup block and the function we're calling can unwind, then
         // do an invoke, otherwise do a call.
         let fn_ty = bx.fn_decl_backend_type(fn_abi);
@@ -480,6 +502,7 @@ impl<'a, 'tcx, Bx: BuilderMethods<'a, 'tcx>> FunctionCx<'a, 'tcx, Bx> {
         let ty = location.ty(self.mir, bx.tcx()).ty;
         let ty = self.monomorphize(ty);
         let drop_fn = Instance::resolve_drop_in_place(bx.tcx(), ty);
+        let instance = drop_fn.clone();
 
         if let ty::InstanceDef::DropGlue(_, None) = drop_fn.def {
             // we don't actually need to drop anything.
@@ -582,6 +605,7 @@ impl<'a, 'tcx, Bx: BuilderMethods<'a, 'tcx>> FunctionCx<'a, 'tcx, Bx> {
             Some((ReturnDest::Nothing, target)),
             unwind,
             &[],
+            Some(instance),
             mergeable_succ,
         )
     }
@@ -658,10 +682,11 @@ impl<'a, 'tcx, Bx: BuilderMethods<'a, 'tcx>> FunctionCx<'a, 'tcx, Bx> {
             }
         };
 
-        let (fn_abi, llfn) = common::build_langcall(bx, Some(span), lang_item);
+        let (fn_abi, llfn, instance) = common::build_langcall(bx, Some(span), lang_item);
 
         // Codegen the actual panic invoke/call.
-        let merging_succ = helper.do_call(self, bx, fn_abi, llfn, &args, None, unwind, &[], false);
+        let merging_succ =
+            helper.do_call(self, bx, fn_abi, llfn, &args, None, unwind, &[], Some(instance), false);
         assert_eq!(merging_succ, MergingSucc::False);
         MergingSucc::False
     }
@@ -677,7 +702,7 @@ impl<'a, 'tcx, Bx: BuilderMethods<'a, 'tcx>> FunctionCx<'a, 'tcx, Bx> {
         self.set_debug_loc(bx, terminator.source_info);
 
         // Obtain the panic entry point.
-        let (fn_abi, llfn) = common::build_langcall(bx, Some(span), reason.lang_item());
+        let (fn_abi, llfn, instance) = common::build_langcall(bx, Some(span), reason.lang_item());
 
         // Codegen the actual panic invoke/call.
         let merging_succ = helper.do_call(
@@ -689,6 +714,7 @@ impl<'a, 'tcx, Bx: BuilderMethods<'a, 'tcx>> FunctionCx<'a, 'tcx, Bx> {
             None,
             mir::UnwindAction::Unreachable,
             &[],
+            Some(instance),
             false,
         );
         assert_eq!(merging_succ, MergingSucc::False);
@@ -738,7 +764,7 @@ impl<'a, 'tcx, Bx: BuilderMethods<'a, 'tcx>> FunctionCx<'a, 'tcx, Bx> {
                 let msg = bx.const_str(&msg_str);
 
                 // Obtain the panic entry point.
-                let (fn_abi, llfn) =
+                let (fn_abi, llfn, instance) =
                     common::build_langcall(bx, Some(source_info.span), LangItem::PanicNounwind);
 
                 // Codegen the actual panic invoke/call.
@@ -751,6 +777,7 @@ impl<'a, 'tcx, Bx: BuilderMethods<'a, 'tcx>> FunctionCx<'a, 'tcx, Bx> {
                     target.as_ref().map(|bb| (ReturnDest::Nothing, *bb)),
                     unwind,
                     &[],
+                    Some(instance),
                     mergeable_succ,
                 )
             } else {
@@ -798,6 +825,7 @@ impl<'a, 'tcx, Bx: BuilderMethods<'a, 'tcx>> FunctionCx<'a, 'tcx, Bx> {
             ty::FnPtr(_) => (None, Some(callee.immediate())),
             _ => bug!("{} is not callable", callee.layout.ty),
         };
+
         let def = instance.map(|i| i.def);
 
         if let Some(ty::InstanceDef::DropGlue(_, None)) = def {
@@ -1106,6 +1134,7 @@ impl<'a, 'tcx, Bx: BuilderMethods<'a, 'tcx>> FunctionCx<'a, 'tcx, Bx> {
             destination,
             unwind,
             &copied_constant_arguments,
+            instance,
             mergeable_succ,
         )
     }
@@ -1664,11 +1693,15 @@ impl<'a, 'tcx, Bx: BuilderMethods<'a, 'tcx>> FunctionCx<'a, 'tcx, Bx> {
 
         self.set_debug_loc(&mut bx, mir::SourceInfo::outermost(self.mir.span));
 
-        let (fn_abi, fn_ptr) = common::build_langcall(&bx, None, reason.lang_item());
-        let fn_ty = bx.fn_decl_backend_type(fn_abi);
+        let (fn_abi, fn_ptr, instance) = common::build_langcall(&bx, None, reason.lang_item());
+        if is_call_from_compiler_builtins_to_upstream_monomorphization(bx.tcx(), instance) {
+            bx.abort();
+        } else {
+            let fn_ty = bx.fn_decl_backend_type(fn_abi);
 
-        let llret = bx.call(fn_ty, None, Some(fn_abi), fn_ptr, &[], funclet.as_ref());
-        bx.apply_attrs_to_cleanup_callsite(llret);
+            let llret = bx.call(fn_ty, None, Some(fn_abi), fn_ptr, &[], funclet.as_ref());
+            bx.apply_attrs_to_cleanup_callsite(llret);
+        }
 
         bx.unreachable();
 
diff --git a/compiler/rustc_codegen_ssa/src/size_of_val.rs b/compiler/rustc_codegen_ssa/src/size_of_val.rs
index 087836ca37d..e2e95cede60 100644
--- a/compiler/rustc_codegen_ssa/src/size_of_val.rs
+++ b/compiler/rustc_codegen_ssa/src/size_of_val.rs
@@ -62,7 +62,8 @@ pub fn size_and_align_of_dst<'a, 'tcx, Bx: BuilderMethods<'a, 'tcx>>(
             let msg = bx.const_str(&msg_str);
 
             // Obtain the panic entry point.
-            let (fn_abi, llfn) = common::build_langcall(bx, None, LangItem::PanicNounwind);
+            let (fn_abi, llfn, _instance) =
+                common::build_langcall(bx, None, LangItem::PanicNounwind);
 
             // Generate the call.
             // Cannot use `do_call` since we don't have a MIR terminator so we can't create a `TerminationCodegenHelper`.
diff --git a/compiler/rustc_middle/src/ty/instance.rs b/compiler/rustc_middle/src/ty/instance.rs
index 4748e961019..65574f5702b 100644
--- a/compiler/rustc_middle/src/ty/instance.rs
+++ b/compiler/rustc_middle/src/ty/instance.rs
@@ -10,6 +10,7 @@ use rustc_hir::lang_items::LangItem;
 use rustc_index::bit_set::FiniteBitSet;
 use rustc_macros::HashStable;
 use rustc_middle::ty::normalize_erasing_regions::NormalizationError;
+use rustc_span::def_id::LOCAL_CRATE;
 use rustc_span::Symbol;
 
 use std::assert_matches::assert_matches;
@@ -172,6 +173,11 @@ impl<'tcx> Instance<'tcx> {
         // If this a non-generic instance, it cannot be a shared monomorphization.
         self.args.non_erasable_generics(tcx, self.def_id()).next()?;
 
+        // compiler_builtins cannot use upstream monomorphizations.
+        if tcx.is_compiler_builtins(LOCAL_CRATE) {
+            return None;
+        }
+
         match self.def {
             InstanceDef::Item(def) => tcx
                 .upstream_monomorphizations_for(def)
diff --git a/compiler/rustc_monomorphize/src/collector.rs b/compiler/rustc_monomorphize/src/collector.rs
index 1a18a84b358..673cd968e28 100644
--- a/compiler/rustc_monomorphize/src/collector.rs
+++ b/compiler/rustc_monomorphize/src/collector.rs
@@ -1107,7 +1107,7 @@ 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.
-fn should_codegen_locally<'tcx>(tcx: TyCtxt<'tcx>, instance: &Instance<'tcx>) -> bool {
+pub(crate) fn should_codegen_locally<'tcx>(tcx: TyCtxt<'tcx>, instance: &Instance<'tcx>) -> bool {
     let Some(def_id) = instance.def.def_id_if_not_guaranteed_local_codegen() else {
         return true;
     };
diff --git a/compiler/rustc_monomorphize/src/lib.rs b/compiler/rustc_monomorphize/src/lib.rs
index 7f36ae91f1a..4ec842e8f85 100644
--- a/compiler/rustc_monomorphize/src/lib.rs
+++ b/compiler/rustc_monomorphize/src/lib.rs
@@ -11,7 +11,10 @@ use rustc_hir::lang_items::LangItem;
 use rustc_middle::query::{Providers, 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::LOCAL_CRATE;
 use rustc_span::ErrorGuaranteed;
 
 mod collector;
@@ -20,6 +23,8 @@ mod partitioning;
 mod polymorphize;
 mod util;
 
+use collector::should_codegen_locally;
+
 rustc_fluent_macro::fluent_messages! { "../messages.ftl" }
 
 fn custom_coerce_unsize_info<'tcx>(
@@ -45,6 +50,23 @@ 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.
+pub fn is_call_from_compiler_builtins_to_upstream_monomorphization<'tcx>(
+    tcx: TyCtxt<'tcx>,
+    instance: Instance<'tcx>,
+) -> bool {
+    !instance.def_id().is_local()
+        && tcx.is_compiler_builtins(LOCAL_CRATE)
+        && tcx.codegen_fn_attrs(instance.def_id()).link_name.is_none()
+        && !should_codegen_locally(tcx, &instance)
+}
+
 pub fn provide(providers: &mut Providers) {
     partitioning::provide(providers);
     polymorphize::provide(providers);