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.

4 files changed, 53 insertions, 11 deletions

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`.