Auto merge of #115214 - Urgau:rfc-3127-trim-paths, r=compiler-errors

Implement rustc part of RFC 3127 trim-paths

This PR implements (or at least tries to) [RFC 3127 trim-paths](#111540), the rustc part. That is `-Zremap-path-scope` with all of it's components/scopes.

`@rustbot` label: +F-trim-paths

Author: bors

Cargo.lock

@@ -4457,6 +4457,7 @@ dependencies = [
 name = "rustc_session"
 version = "0.0.0"
 dependencies = [
+ "bitflags 1.3.2",
  "getopts",
  "libc",
  "rustc_ast",

compiler/rustc_builtin_macros/src/source_util.rs

@@ -61,9 +61,14 @@ pub fn expand_file(
 
     let topmost = cx.expansion_cause().unwrap_or(sp);
     let loc = cx.source_map().lookup_char_pos(topmost.lo());
-    base::MacEager::expr(
-        cx.expr_str(topmost, Symbol::intern(&loc.file.name.prefer_remapped().to_string_lossy())),
-    )
+
+    use rustc_session::{config::RemapPathScopeComponents, RemapFileNameExt};
+    base::MacEager::expr(cx.expr_str(
+        topmost,
+        Symbol::intern(
+            &loc.file.name.for_scope(cx.sess, RemapPathScopeComponents::MACRO).to_string_lossy(),
+        ),
+    ))
 }
 
 pub fn expand_stringify(

compiler/rustc_codegen_cranelift/src/common.rs

@@ -414,11 +414,12 @@ impl<'tcx> FunctionCx<'_, '_, 'tcx> {
     // Note: must be kept in sync with get_caller_location from cg_ssa
     pub(crate) fn get_caller_location(&mut self, mut source_info: mir::SourceInfo) -> CValue<'tcx> {
         let span_to_caller_location = |fx: &mut FunctionCx<'_, '_, 'tcx>, span: Span| {
+            use rustc_session::RemapFileNameExt;
             let topmost = span.ctxt().outer_expn().expansion_cause().unwrap_or(span);
             let caller = fx.tcx.sess.source_map().lookup_char_pos(topmost.lo());
             let const_loc = fx.tcx.const_caller_location((
                 rustc_span::symbol::Symbol::intern(
-                    &caller.file.name.prefer_remapped().to_string_lossy(),
+                    &caller.file.name.for_codegen(&fx.tcx.sess).to_string_lossy(),
                 ),
                 caller.line as u32,
                 caller.col_display as u32 + 1,

compiler/rustc_codegen_cranelift/src/debuginfo/line_info.rs

@@ -95,7 +95,11 @@ impl DebugContext {
         match &source_file.name {
             FileName::Real(path) => {
                 let (dir_path, file_name) =
-                    split_path_dir_and_file(path.remapped_path_if_available());
+                    split_path_dir_and_file(if self.should_remap_filepaths {
+                        path.remapped_path_if_available()
+                    } else {
+                        path.local_path_if_available()
+                    });
                 let dir_name = osstr_as_utf8_bytes(dir_path.as_os_str());
                 let file_name = osstr_as_utf8_bytes(file_name);
 
@@ -116,7 +120,14 @@ impl DebugContext {
             filename => {
                 let dir_id = line_program.default_directory();
                 let dummy_file_name = LineString::new(
-                    filename.prefer_remapped().to_string().into_bytes(),
+                    filename
+                        .display(if self.should_remap_filepaths {
+                            FileNameDisplayPreference::Remapped
+                        } else {
+                            FileNameDisplayPreference::Local
+                        })
+                        .to_string()
+                        .into_bytes(),
                     line_program.encoding(),
                     line_strings,
                 );

compiler/rustc_codegen_cranelift/src/debuginfo/mod.rs

@@ -31,6 +31,8 @@ pub(crate) struct DebugContext {
 
     dwarf: DwarfUnit,
     unit_range_list: RangeList,
+
+    should_remap_filepaths: bool,
 }
 
 pub(crate) struct FunctionDebugContext {
@@ -63,12 +65,18 @@ impl DebugContext {
 
         let mut dwarf = DwarfUnit::new(encoding);
 
+        let should_remap_filepaths = tcx.sess.should_prefer_remapped_for_codegen();
+
         let producer = producer();
         let comp_dir = tcx
             .sess
             .opts
             .working_dir
-            .to_string_lossy(FileNameDisplayPreference::Remapped)
+            .to_string_lossy(if should_remap_filepaths {
+                FileNameDisplayPreference::Remapped
+            } else {
+                FileNameDisplayPreference::Local
+            })
             .into_owned();
         let (name, file_info) = match tcx.sess.local_crate_source_file() {
             Some(path) => {
@@ -102,7 +110,12 @@ impl DebugContext {
             root.set(gimli::DW_AT_low_pc, AttributeValue::Address(Address::Constant(0)));
         }
 
-        DebugContext { endian, dwarf, unit_range_list: RangeList(Vec::new()) }
+        DebugContext {
+            endian,
+            dwarf,
+            unit_range_list: RangeList(Vec::new()),
+            should_remap_filepaths,
+        }
     }
 
     pub(crate) fn define_function(

compiler/rustc_codegen_llvm/src/back/write.rs

@@ -259,9 +259,17 @@ pub fn target_machine_factory(
     };
     let debuginfo_compression = SmallCStr::new(&debuginfo_compression);
 
+    let should_prefer_remapped_for_split_debuginfo_paths =
+        sess.should_prefer_remapped_for_split_debuginfo_paths();
+
     Arc::new(move |config: TargetMachineFactoryConfig| {
         let path_to_cstring_helper = |path: Option<PathBuf>| -> CString {
-            let path = path_mapping.map_prefix(path.unwrap_or_default()).0;
+            let path = path.unwrap_or_default();
+            let path = if should_prefer_remapped_for_split_debuginfo_paths {
+                path_mapping.map_prefix(path).0
+            } else {
+                path.into()
+            };
             CString::new(path.to_str().unwrap()).unwrap()
         };
 

compiler/rustc_codegen_llvm/src/coverageinfo/mapgen.rs

@@ -123,9 +123,9 @@ impl GlobalFileTable {
         // Since rustc generates coverage maps with relative paths, the
         // compilation directory can be combined with the relative paths
         // to get absolute paths, if needed.
-        let working_dir = Symbol::intern(
-            &tcx.sess.opts.working_dir.remapped_path_if_available().to_string_lossy(),
-        );
+        use rustc_session::RemapFileNameExt;
+        let working_dir =
+            Symbol::intern(&tcx.sess.opts.working_dir.for_codegen(&tcx.sess).to_string_lossy());
         global_file_table.insert(working_dir);
         Self { global_file_table }
     }

compiler/rustc_codegen_llvm/src/debuginfo/metadata.rs

@@ -547,48 +547,77 @@ pub fn file_metadata<'ll>(cx: &CodegenCx<'ll, '_>, source_file: &SourceFile) ->
     ) -> &'ll DIFile {
         debug!(?source_file.name);
 
+        use rustc_session::RemapFileNameExt;
         let (directory, file_name) = match &source_file.name {
             FileName::Real(filename) => {
                 let working_directory = &cx.sess().opts.working_dir;
                 debug!(?working_directory);
 
-                let filename = cx
-                    .sess()
-                    .source_map()
-                    .path_mapping()
-                    .to_embeddable_absolute_path(filename.clone(), working_directory);
-
-                // Construct the absolute path of the file
-                let abs_path = filename.remapped_path_if_available();
-                debug!(?abs_path);
-
-                if let Ok(rel_path) =
-                    abs_path.strip_prefix(working_directory.remapped_path_if_available())
-                {
-                    // If the compiler's working directory (which also is the DW_AT_comp_dir of
-                    // the compilation unit) is a prefix of the path we are about to emit, then
-                    // only emit the part relative to the working directory.
-                    // Because of path remapping we sometimes see strange things here: `abs_path`
-                    // might actually look like a relative path
-                    // (e.g. `<crate-name-and-version>/src/lib.rs`), so if we emit it without
-                    // taking the working directory into account, downstream tooling will
-                    // interpret it as `<working-directory>/<crate-name-and-version>/src/lib.rs`,
-                    // which makes no sense. Usually in such cases the working directory will also
-                    // be remapped to `<crate-name-and-version>` or some other prefix of the path
-                    // we are remapping, so we end up with
-                    // `<crate-name-and-version>/<crate-name-and-version>/src/lib.rs`.
-                    // By moving the working directory portion into the `directory` part of the
-                    // DIFile, we allow LLVM to emit just the relative path for DWARF, while
-                    // still emitting the correct absolute path for CodeView.
-                    (
-                        working_directory.to_string_lossy(FileNameDisplayPreference::Remapped),
-                        rel_path.to_string_lossy().into_owned(),
-                    )
+                if cx.sess().should_prefer_remapped_for_codegen() {
+                    let filename = cx
+                        .sess()
+                        .source_map()
+                        .path_mapping()
+                        .to_embeddable_absolute_path(filename.clone(), working_directory);
+
+                    // Construct the absolute path of the file
+                    let abs_path = filename.remapped_path_if_available();
+                    debug!(?abs_path);
+
+                    if let Ok(rel_path) =
+                        abs_path.strip_prefix(working_directory.remapped_path_if_available())
+                    {
+                        // If the compiler's working directory (which also is the DW_AT_comp_dir of
+                        // the compilation unit) is a prefix of the path we are about to emit, then
+                        // only emit the part relative to the working directory.
+                        // Because of path remapping we sometimes see strange things here: `abs_path`
+                        // might actually look like a relative path
+                        // (e.g. `<crate-name-and-version>/src/lib.rs`), so if we emit it without
+                        // taking the working directory into account, downstream tooling will
+                        // interpret it as `<working-directory>/<crate-name-and-version>/src/lib.rs`,
+                        // which makes no sense. Usually in such cases the working directory will also
+                        // be remapped to `<crate-name-and-version>` or some other prefix of the path
+                        // we are remapping, so we end up with
+                        // `<crate-name-and-version>/<crate-name-and-version>/src/lib.rs`.
+                        // By moving the working directory portion into the `directory` part of the
+                        // DIFile, we allow LLVM to emit just the relative path for DWARF, while
+                        // still emitting the correct absolute path for CodeView.
+                        (
+                            working_directory.to_string_lossy(FileNameDisplayPreference::Remapped),
+                            rel_path.to_string_lossy().into_owned(),
+                        )
+                    } else {
+                        ("".into(), abs_path.to_string_lossy().into_owned())
+                    }
                 } else {
-                    ("".into(), abs_path.to_string_lossy().into_owned())
+                    let working_directory = working_directory.local_path_if_available();
+                    let filename = filename.local_path_if_available();
+
+                    debug!(?working_directory, ?filename);
+
+                    let abs_path: Cow<'_, Path> = if filename.is_absolute() {
+                        filename.into()
+                    } else {
+                        let mut p = PathBuf::new();
+                        p.push(working_directory);
+                        p.push(filename);
+                        p.into()
+                    };
+
+                    if let Ok(rel_path) = abs_path.strip_prefix(working_directory) {
+                        (
+                            working_directory.to_string_lossy().into(),
+                            rel_path.to_string_lossy().into_owned(),
+                        )
+                    } else {
+                        ("".into(), abs_path.to_string_lossy().into_owned())
+                    }
                 }
             }
-            other => ("".into(), other.prefer_remapped().to_string_lossy().into_owned()),
+            other => {
+                debug!(?other);
+                ("".into(), other.for_codegen(cx.sess()).to_string_lossy().into_owned())
+            }
         };
 
         let hash_kind = match source_file.src_hash.kind {
@@ -822,8 +851,9 @@ pub fn build_compile_unit_di_node<'ll, 'tcx>(
     // FIXME(#41252) Remove "clang LLVM" if we can get GDB and LLVM to play nice.
     let producer = format!("clang LLVM ({rustc_producer})");
 
+    use rustc_session::RemapFileNameExt;
     let name_in_debuginfo = name_in_debuginfo.to_string_lossy();
-    let work_dir = tcx.sess.opts.working_dir.to_string_lossy(FileNameDisplayPreference::Remapped);
+    let work_dir = tcx.sess.opts.working_dir.for_codegen(&tcx.sess).to_string_lossy();
     let flags = "\0";
     let output_filenames = tcx.output_filenames(());
     let split_name = if tcx.sess.target_can_use_split_dwarf() {
@@ -834,7 +864,13 @@ pub fn build_compile_unit_di_node<'ll, 'tcx>(
                 Some(codegen_unit_name),
             )
             // We get a path relative to the working directory from split_dwarf_path
-            .map(|f| tcx.sess.source_map().path_mapping().map_prefix(f).0)
+            .map(|f| {
+                if tcx.sess.should_prefer_remapped_for_split_debuginfo_paths() {
+                    tcx.sess.source_map().path_mapping().map_prefix(f).0
+                } else {
+                    f.into()
+                }
+            })
     } else {
         None
     }

compiler/rustc_codegen_ssa/src/mir/block.rs

@@ -1454,10 +1454,11 @@ impl<'a, 'tcx, Bx: BuilderMethods<'a, 'tcx>> FunctionCx<'a, 'tcx, Bx> {
         let tcx = bx.tcx();
 
         let mut span_to_caller_location = |span: Span| {
+            use rustc_session::RemapFileNameExt;
             let topmost = span.ctxt().outer_expn().expansion_cause().unwrap_or(span);
             let caller = tcx.sess.source_map().lookup_char_pos(topmost.lo());
             let const_loc = tcx.const_caller_location((
-                Symbol::intern(&caller.file.name.prefer_remapped().to_string_lossy()),
+                Symbol::intern(&caller.file.name.for_codegen(self.cx.sess()).to_string_lossy()),
                 caller.line as u32,
                 caller.col_display as u32 + 1,
             ));

compiler/rustc_const_eval/src/interpret/intrinsics/caller_location.rs

@@ -114,8 +114,16 @@ impl<'mir, 'tcx: 'mir, M: Machine<'mir, 'tcx>> InterpCx<'mir, 'tcx, M> {
     pub(crate) fn location_triple_for_span(&self, span: Span) -> (Symbol, u32, u32) {
         let topmost = span.ctxt().outer_expn().expansion_cause().unwrap_or(span);
         let caller = self.tcx.sess.source_map().lookup_char_pos(topmost.lo());
+
+        use rustc_session::{config::RemapPathScopeComponents, RemapFileNameExt};
         (
-            Symbol::intern(&caller.file.name.prefer_remapped().to_string_lossy()),
+            Symbol::intern(
+                &caller
+                    .file
+                    .name
+                    .for_scope(&self.tcx.sess, RemapPathScopeComponents::DIAGNOSTICS)
+                    .to_string_lossy(),
+            ),
             u32::try_from(caller.line).unwrap(),
             u32::try_from(caller.col_display).unwrap().checked_add(1).unwrap(),
         )

compiler/rustc_metadata/src/rmeta/encoder.rs

@@ -525,9 +525,17 @@ impl<'a, 'tcx> EncodeContext<'a, 'tcx> {
             // the remapped version -- as is necessary for reproducible builds.
             let mut source_file = match source_file.name {
                 FileName::Real(ref original_file_name) => {
-                    let adapted_file_name = source_map
-                        .path_mapping()
-                        .to_embeddable_absolute_path(original_file_name.clone(), working_directory);
+                    let adapted_file_name = if self.tcx.sess.should_prefer_remapped_for_codegen() {
+                        source_map.path_mapping().to_embeddable_absolute_path(
+                            original_file_name.clone(),
+                            working_directory,
+                        )
+                    } else {
+                        source_map.path_mapping().to_local_embeddable_absolute_path(
+                            original_file_name.clone(),
+                            working_directory,
+                        )
+                    };
 
                     if adapted_file_name != *original_file_name {
                         let mut adapted: SourceFile = (**source_file).clone();

compiler/rustc_mir_transform/src/coverage/mod.rs

@@ -212,7 +212,10 @@ impl<'a, 'tcx> Instrumentor<'a, 'tcx> {
         let tcx = self.tcx;
         let source_map = tcx.sess.source_map();
         let body_span = self.body_span;
-        let file_name = Symbol::intern(&self.source_file.name.prefer_remapped().to_string_lossy());
+
+        use rustc_session::RemapFileNameExt;
+        let file_name =
+            Symbol::intern(&self.source_file.name.for_codegen(self.tcx.sess).to_string_lossy());
 
         for (bcb, spans) in coverage_spans.bcbs_with_coverage_spans() {
             let counter_kind = self.coverage_counters.take_bcb_counter(bcb).unwrap_or_else(|| {

compiler/rustc_session/Cargo.toml

@@ -4,6 +4,7 @@ version = "0.0.0"
 edition = "2021"
 
 [dependencies]
+bitflags = "1.2.1"
 getopts = "0.2"
 rustc_macros = { path = "../rustc_macros" }
 tracing = "0.1"