Auto merge of #83813 - cbeuw:remap-std, r=michaelwoerister

Fix `--remap-path-prefix` not correctly remapping `rust-src` component paths and unify handling of path mapping with virtualized paths

This PR fixes #73167 ("Binaries end up containing path to the rust-src component despite `--remap-path-prefix`") by preventing real local filesystem paths from reaching compilation output if the path is supposed to be remapped.

`RealFileName::Named` introduced in #72767 is now renamed as `LocalPath`, because this variant wraps a (most likely) valid local filesystem path.

`RealFileName::Devirtualized` is renamed as `Remapped` to be used for remapped path from a real path via `--remap-path-prefix` argument, as well as real path inferred from a virtualized (during compiler bootstrapping) `/rustc/...` path. The `local_path` field is now an `Option<PathBuf>`, as it will be set to `None` before serialisation, so it never reaches any build output. Attempting to serialise a non-`None` `local_path` will cause an assertion faliure.

When a path is remapped, a `RealFileName::Remapped` variant is created. The original path is preserved in `local_path` field and the remapped path is saved in `virtual_name` field. Previously, the `local_path` is directly modified which goes against its purpose of "suitable for reading from the file system on the local host".

`rustc_span::SourceFile`'s fields `unmapped_path` (introduced by #44940) and `name_was_remapped` (introduced by #41508 when `--remap-path-prefix` feature originally added) are removed, as these two pieces of information can be inferred from the `name` field: if it's anything other than a `FileName::Real(_)`, or if it is a `FileName::Real(RealFileName::LocalPath(_))`, then clearly `name_was_remapped` would've been false and `unmapped_path` would've been `None`. If it is a `FileName::Real(RealFileName::Remapped{local_path, virtual_name})`, then `name_was_remapped` would've been true and `unmapped_path` would've been `Some(local_path)`.

cc `@eddyb` who implemented `/rustc/...` path devirtualisation

1 files changed, 43 insertions, 69 deletions

diff --git a/compiler/rustc_span/src/source_map.rs b/compiler/rustc_span/src/source_map.rs
index e365844980b..0dadd419200 100644
--- a/compiler/rustc_span/src/source_map.rs
+++ b/compiler/rustc_span/src/source_map.rs
@@ -15,11 +15,11 @@ pub use crate::*;
 use rustc_data_structures::fx::FxHashMap;
 use rustc_data_structures::stable_hasher::StableHasher;
 use rustc_data_structures::sync::{AtomicU32, Lrc, MappedReadGuard, ReadGuard, RwLock};
-use std::cmp;
-use std::convert::TryFrom;
 use std::hash::Hash;
 use std::path::{Path, PathBuf};
 use std::sync::atomic::Ordering;
+use std::{clone::Clone, cmp};
+use std::{convert::TryFrom, unreachable};
 
 use std::fs;
 use std::io;
@@ -127,30 +127,13 @@ pub struct StableSourceFileId(u128);
 // StableSourceFileId, perhaps built atop source_file.name_hash.
 impl StableSourceFileId {
     pub fn new(source_file: &SourceFile) -> StableSourceFileId {
-        StableSourceFileId::new_from_pieces(
-            &source_file.name,
-            source_file.name_was_remapped,
-            source_file.unmapped_path.as_ref(),
-        )
+        StableSourceFileId::new_from_name(&source_file.name)
     }
 
-    fn new_from_pieces(
-        name: &FileName,
-        name_was_remapped: bool,
-        unmapped_path: Option<&FileName>,
-    ) -> StableSourceFileId {
+    fn new_from_name(name: &FileName) -> StableSourceFileId {
         let mut hasher = StableHasher::new();
 
-        if let FileName::Real(real_name) = name {
-            // rust-lang/rust#70924: Use the stable (virtualized) name when
-            // available. (We do not want artifacts from transient file system
-            // paths for libstd to leak into our build artifacts.)
-            real_name.stable_name().hash(&mut hasher)
-        } else {
-            name.hash(&mut hasher);
-        }
-        name_was_remapped.hash(&mut hasher);
-        unmapped_path.hash(&mut hasher);
+        name.hash(&mut hasher);
 
         StableSourceFileId(hasher.finish())
     }
@@ -283,35 +266,15 @@ impl SourceMap {
 
     fn try_new_source_file(
         &self,
-        mut filename: FileName,
+        filename: FileName,
         src: String,
     ) -> Result<Lrc<SourceFile>, OffsetOverflowError> {
-        // The path is used to determine the directory for loading submodules and
-        // include files, so it must be before remapping.
         // Note that filename may not be a valid path, eg it may be `<anon>` etc,
         // but this is okay because the directory determined by `path.pop()` will
         // be empty, so the working directory will be used.
-        let unmapped_path = filename.clone();
-
-        let was_remapped;
-        if let FileName::Real(real_filename) = &mut filename {
-            match real_filename {
-                RealFileName::Named(path_to_be_remapped)
-                | RealFileName::Devirtualized {
-                    local_path: path_to_be_remapped,
-                    virtual_name: _,
-                } => {
-                    let mapped = self.path_mapping.map_prefix(path_to_be_remapped.clone());
-                    was_remapped = mapped.1;
-                    *path_to_be_remapped = mapped.0;
-                }
-            }
-        } else {
-            was_remapped = false;
-        }
+        let (filename, _) = self.path_mapping.map_filename_prefix(&filename);
 
-        let file_id =
-            StableSourceFileId::new_from_pieces(&filename, was_remapped, Some(&unmapped_path));
+        let file_id = StableSourceFileId::new_from_name(&filename);
 
         let lrc_sf = match self.source_file_by_stable_id(file_id) {
             Some(lrc_sf) => lrc_sf,
@@ -320,8 +283,6 @@ impl SourceMap {
 
                 let source_file = Lrc::new(SourceFile::new(
                     filename,
-                    was_remapped,
-                    unmapped_path,
                     src,
                     Pos::from_usize(start_pos),
                     self.hash_kind,
@@ -345,7 +306,6 @@ impl SourceMap {
     pub fn new_imported_source_file(
         &self,
         filename: FileName,
-        name_was_remapped: bool,
         src_hash: SourceFileHash,
         name_hash: u128,
         source_len: usize,
@@ -382,8 +342,6 @@ impl SourceMap {
 
         let source_file = Lrc::new(SourceFile {
             name: filename,
-            name_was_remapped,
-            unmapped_path: None,
             src: None,
             src_hash,
             external_src: Lock::new(ExternalSource::Foreign {
@@ -411,11 +369,6 @@ impl SourceMap {
         source_file
     }
 
-    pub fn mk_substr_filename(&self, sp: Span) -> String {
-        let pos = self.lookup_char_pos(sp.lo());
-        format!("<{}:{}:{}>", pos.file.name, pos.line, pos.col.to_usize() + 1)
-    }
-
     // If there is a doctest offset, applies it to the line.
     pub fn doctest_offset_line(&self, file: &FileName, orig: usize) -> usize {
         match file {
@@ -453,7 +406,7 @@ impl SourceMap {
         }
     }
 
-    pub fn span_to_string(&self, sp: Span) -> String {
+    fn span_to_string(&self, sp: Span, prefer_local: bool) -> String {
         if self.files.borrow().source_files.is_empty() && sp.is_dummy() {
             return "no-location".to_string();
         }
@@ -462,7 +415,7 @@ impl SourceMap {
         let hi = self.lookup_char_pos(sp.hi());
         format!(
             "{}:{}:{}: {}:{}",
-            lo.file.name,
+            if prefer_local { lo.file.name.prefer_local() } else { lo.file.name.prefer_remapped() },
             lo.line,
             lo.col.to_usize() + 1,
             hi.line,
@@ -470,16 +423,20 @@ impl SourceMap {
         )
     }
 
-    pub fn span_to_filename(&self, sp: Span) -> FileName {
-        self.lookup_char_pos(sp.lo()).file.name.clone()
+    /// Format the span location suitable for embedding in build artifacts
+    pub fn span_to_embeddable_string(&self, sp: Span) -> String {
+        self.span_to_string(sp, false)
+    }
+
+    /// Format the span location to be printed in diagnostics. Must not be emitted
+    /// to build artifacts as this may leak local file paths. Use span_to_embeddable_string
+    /// for string suitable for embedding.
+    pub fn span_to_diagnostic_string(&self, sp: Span) -> String {
+        self.span_to_string(sp, true)
     }
 
-    pub fn span_to_unmapped_path(&self, sp: Span) -> FileName {
-        self.lookup_char_pos(sp.lo())
-            .file
-            .unmapped_path
-            .clone()
-            .expect("`SourceMap::span_to_unmapped_path` called for imported `SourceFile`?")
+    pub fn span_to_filename(&self, sp: Span) -> FileName {
+        self.lookup_char_pos(sp.lo()).file.name.clone()
     }
 
     pub fn is_multiline(&self, sp: Span) -> bool {
@@ -1001,7 +958,13 @@ impl SourceMap {
     }
     pub fn ensure_source_file_source_present(&self, source_file: Lrc<SourceFile>) -> bool {
         source_file.add_external_src(|| match source_file.name {
-            FileName::Real(ref name) => self.file_loader.read_file(name.local_path()).ok(),
+            FileName::Real(ref name) => {
+                if let Some(local_path) = name.local_path() {
+                    self.file_loader.read_file(local_path).ok()
+                } else {
+                    None
+                }
+            }
             _ => None,
         })
     }
@@ -1046,9 +1009,20 @@ impl FilePathMapping {
     fn map_filename_prefix(&self, file: &FileName) -> (FileName, bool) {
         match file {
             FileName::Real(realfile) => {
-                let path = realfile.local_path();
-                let (path, mapped) = self.map_prefix(path.to_path_buf());
-                (FileName::Real(RealFileName::Named(path)), mapped)
+                if let RealFileName::LocalPath(local_path) = realfile {
+                    let (mapped_path, mapped) = self.map_prefix(local_path.to_path_buf());
+                    let realfile = if mapped {
+                        RealFileName::Remapped {
+                            local_path: Some(local_path.clone()),
+                            virtual_name: mapped_path,
+                        }
+                    } else {
+                        realfile.clone()
+                    };
+                    (FileName::Real(realfile), mapped)
+                } else {
+                    unreachable!("attempted to remap an already remapped filename");
+                }
             }
             other => (other.clone(), false),
         }