Auto merge of #123244 - Mark-Simulacrum:share-inline-never-generics, r=saethlin

Enable -Zshare-generics for inline(never) functions

This avoids inlining cross-crate generic items when possible that are
already marked inline(never), implying that the author is not intending
for the function to be inlined by callers. As such, having a local copy
may make it easier for LLVM to optimize but mostly just adds to binary
bloat and codegen time. In practice our benchmarks indicate this is
indeed a win for larger compilations, where the extra cost in dynamic
linking to these symbols is diminished compared to the advantages in
fewer copies that need optimizing in each binary.

It might also make sense it expand this with other heuristics (e.g.,
`#[cold]`) in the future, but this seems like a good starting point.

FWIW, I expect that doing cleanup in where we make the decision
what should/shouldn't be shared is also a good idea. Way too
much code needed to be tweaked to check this. But I'm hoping
to leave that for a follow-up PR rather than blocking this on it.

3 files changed, 18 insertions, 9 deletions

diff --git a/compiler/rustc_middle/src/mir/mono.rs b/compiler/rustc_middle/src/mir/mono.rs
index 244d22d082f..161716610fe 100644
--- a/compiler/rustc_middle/src/mir/mono.rs
+++ b/compiler/rustc_middle/src/mir/mono.rs
@@ -111,6 +111,13 @@ impl<'tcx> MonoItem<'tcx> {
                     return InstantiationMode::GloballyShared { may_conflict: false };
                 }
 
+                if let InlineAttr::Never = tcx.codegen_fn_attrs(instance.def_id()).inline
+                    && self.is_generic_fn()
+                {
+                    // Upgrade inline(never) to a globally shared instance.
+                    return InstantiationMode::GloballyShared { may_conflict: true };
+                }
+
                 // At this point we don't have explicit linkage and we're an
                 // inlined function. If we're inlining into all CGUs then we'll
                 // be creating a local copy per CGU.
diff --git a/compiler/rustc_middle/src/ty/context.rs b/compiler/rustc_middle/src/ty/context.rs
index 2c867e6b8ca..3cbb2a3acf5 100644
--- a/compiler/rustc_middle/src/ty/context.rs
+++ b/compiler/rustc_middle/src/ty/context.rs
@@ -1955,8 +1955,6 @@ impl<'tcx> TyCtxt<'tcx> {
 
     #[inline]
     pub fn local_crate_exports_generics(self) -> bool {
-        debug_assert!(self.sess.opts.share_generics());
-
         self.crate_types().iter().any(|crate_type| {
             match crate_type {
                 CrateType::Executable
diff --git a/compiler/rustc_middle/src/ty/instance.rs b/compiler/rustc_middle/src/ty/instance.rs
index 73fd8aa5b6c..3d4ce112a64 100644
--- a/compiler/rustc_middle/src/ty/instance.rs
+++ b/compiler/rustc_middle/src/ty/instance.rs
@@ -190,19 +190,23 @@ impl<'tcx> Instance<'tcx> {
     /// This method already takes into account the global `-Zshare-generics`
     /// setting, always returning `None` if `share-generics` is off.
     pub fn upstream_monomorphization(&self, tcx: TyCtxt<'tcx>) -> Option<CrateNum> {
-        // If we are not in share generics mode, we don't link to upstream
-        // monomorphizations but always instantiate our own internal versions
-        // instead.
-        if !tcx.sess.opts.share_generics() {
-            return None;
-        }
-
         // If this is an item that is defined in the local crate, no upstream
         // crate can know about it/provide a monomorphization.
         if self.def_id().is_local() {
             return None;
         }
 
+        // If we are not in share generics mode, we don't link to upstream
+        // monomorphizations but always instantiate our own internal versions
+        // instead.
+        if !tcx.sess.opts.share_generics()
+            // However, if the def_id is marked inline(never), then it's fine to just reuse the
+            // upstream monomorphization.
+            && tcx.codegen_fn_attrs(self.def_id()).inline != rustc_attr::InlineAttr::Never
+        {
+            return None;
+        }
+
         // If this a non-generic instance, it cannot be a shared monomorphization.
         self.args.non_erasable_generics().next()?;