Rollup merge of #141558 - Diggsey:db-limit-cgu-name-length, r=matthewjasper

Limit the size of cgu names when using the `-Zhuman-readable-cgu-name…

…s` option

Prior to this change, cgu names could be generated which would result in filenames longer than the limit imposed by the OS.

compiler/rustc_middle/src/lib.rs

@@ -51,6 +51,7 @@
 #![feature(negative_impls)]
 #![feature(never_type)]
 #![feature(ptr_alignment_type)]
+#![feature(round_char_boundary)]
 #![feature(rustc_attrs)]
 #![feature(rustdoc_internals)]
 #![feature(trusted_len)]

compiler/rustc_middle/src/mir/mono.rs

@@ -1,3 +1,4 @@
+use std::borrow::Cow;
 use std::fmt;
 use std::hash::Hash;
 
@@ -468,6 +469,29 @@ impl<'tcx> CodegenUnit<'tcx> {
         hash.as_u128().to_base_fixed_len(CASE_INSENSITIVE)
     }
 
+    pub fn shorten_name(human_readable_name: &str) -> Cow<'_, str> {
+        // Set a limit a somewhat below the common platform limits for file names.
+        const MAX_CGU_NAME_LENGTH: usize = 200;
+        const TRUNCATED_NAME_PREFIX: &str = "-trunc-";
+        if human_readable_name.len() > MAX_CGU_NAME_LENGTH {
+            let mangled_name = Self::mangle_name(human_readable_name);
+            // Determine a safe byte offset to truncate the name to
+            let truncate_to = human_readable_name.floor_char_boundary(
+                MAX_CGU_NAME_LENGTH - TRUNCATED_NAME_PREFIX.len() - mangled_name.len(),
+            );
+            format!(
+                "{}{}{}",
+                &human_readable_name[..truncate_to],
+                TRUNCATED_NAME_PREFIX,
+                mangled_name
+            )
+            .into()
+        } else {
+            // If the name is short enough, we can just return it as is.
+            human_readable_name.into()
+        }
+    }
+
     pub fn compute_size_estimate(&mut self) {
         // The size of a codegen unit as the sum of the sizes of the items
         // within it.
@@ -604,7 +628,7 @@ impl<'tcx> CodegenUnitNameBuilder<'tcx> {
         let cgu_name = self.build_cgu_name_no_mangle(cnum, components, special_suffix);
 
         if self.tcx.sess.opts.unstable_opts.human_readable_cgu_names {
-            cgu_name
+            Symbol::intern(&CodegenUnit::shorten_name(cgu_name.as_str()))
         } else {
             Symbol::intern(&CodegenUnit::mangle_name(cgu_name.as_str()))
         }

compiler/rustc_monomorphize/src/partitioning.rs

@@ -461,15 +461,15 @@ fn merge_codegen_units<'tcx>(
 
         for cgu in codegen_units.iter_mut() {
             if let Some(new_cgu_name) = new_cgu_names.get(&cgu.name()) {
-                if cx.tcx.sess.opts.unstable_opts.human_readable_cgu_names {
-                    cgu.set_name(Symbol::intern(new_cgu_name));
+                let new_cgu_name = if cx.tcx.sess.opts.unstable_opts.human_readable_cgu_names {
+                    Symbol::intern(&CodegenUnit::shorten_name(new_cgu_name))
                 } else {
                     // If we don't require CGU names to be human-readable,
                     // we use a fixed length hash of the composite CGU name
                     // instead.
-                    let new_cgu_name = CodegenUnit::mangle_name(new_cgu_name);
-                    cgu.set_name(Symbol::intern(&new_cgu_name));
-                }
+                    Symbol::intern(&CodegenUnit::mangle_name(new_cgu_name))
+                };
+                cgu.set_name(new_cgu_name);
             }
         }