Auto merge of #96867 - michaelwoerister:path-prefix-fixes-2, r=davidtwco

--remap-path-prefix: Fix duplicated path components in debuginfo

This PR fixes an issue with `--remap-path-prefix` where path components could appear twice in the remapped version of the path (e.g. #78479). The underlying problem was that `--remap-path-prefix` is often used to map an absolute path to something that looks like a relative path, e.g.:

```
--remap-path-prefix=/home/calvin/.cargo/registry/src/github.com-1ecc6299db9ec823=crates.io",
```

and relative paths in debuginfo are interpreted as being relative to the compilation directory. So if Cargo invokes the compiler with `/home/calvin/.cargo/registry/src/github.com-1ecc6299db9ec823/some_crate-0.1.0/src/lib.rs` as input and `/home/calvin/.cargo/registry/src/github.com-1ecc6299db9ec823/some_crate-0.1.0` as the compiler's working directory, then debuginfo will state that the working directory was `crates.io/some_crate-0.1.0` and the file is question was `crates.io/some_crate-0.1.0/src/lib.rs`, which combined gives the path:

```
crates.io/some_crate-0.1.0/crates.io/some_crate-0.1.0/src/lib.rs
```

With this PR the compiler will detect this situation and set up debuginfo in LLVM in a way that makes it strip the duplicated path components when emitting DWARF.

The PR also extracts the logic for making remapped paths absolute into a common helper function that is now used by debuginfo too (instead of just during crate metadata generation).

Author: bors

compiler/rustc_codegen_llvm/src/debuginfo/metadata.rs

@@ -36,20 +36,21 @@ use rustc_middle::ty::subst::GenericArgKind;
 use rustc_middle::ty::{self, AdtKind, Instance, ParamEnv, Ty, TyCtxt, COMMON_VTABLE_ENTRIES};
 use rustc_session::config::{self, DebugInfo};
 use rustc_span::symbol::Symbol;
+use rustc_span::FileName;
 use rustc_span::FileNameDisplayPreference;
-use rustc_span::{self, SourceFile, SourceFileHash};
+use rustc_span::{self, SourceFile};
 use rustc_target::abi::{Align, Size};
 use smallvec::smallvec;
 use tracing::debug;
 
 use libc::{c_longlong, c_uint};
 use std::borrow::Cow;
-use std::collections::hash_map::Entry;
 use std::fmt::{self, Write};
 use std::hash::{Hash, Hasher};
 use std::iter;
 use std::path::{Path, PathBuf};
 use std::ptr;
+use tracing::instrument;
 
 impl PartialEq for llvm::Metadata {
     fn eq(&self, other: &Self) -> bool {
@@ -527,78 +528,105 @@ fn hex_encode(data: &[u8]) -> String {
 }
 
 pub fn file_metadata<'ll>(cx: &CodegenCx<'ll, '_>, source_file: &SourceFile) -> &'ll DIFile {
-    debug!("file_metadata: file_name: {:?}", source_file.name);
-
-    let hash = Some(&source_file.src_hash);
-    let file_name = Some(source_file.name.prefer_remapped().to_string());
-    let directory = if source_file.is_real_file() && !source_file.is_imported() {
-        Some(
-            cx.sess()
-                .opts
-                .working_dir
-                .to_string_lossy(FileNameDisplayPreference::Remapped)
-                .to_string(),
-        )
-    } else {
-        // If the path comes from an upstream crate we assume it has been made
-        // independent of the compiler's working directory one way or another.
-        None
-    };
-    file_metadata_raw(cx, file_name, directory, hash)
-}
-
-pub fn unknown_file_metadata<'ll>(cx: &CodegenCx<'ll, '_>) -> &'ll DIFile {
-    file_metadata_raw(cx, None, None, None)
-}
-
-fn file_metadata_raw<'ll>(
-    cx: &CodegenCx<'ll, '_>,
-    file_name: Option<String>,
-    directory: Option<String>,
-    hash: Option<&SourceFileHash>,
-) -> &'ll DIFile {
-    let key = (file_name, directory);
-
-    match debug_context(cx).created_files.borrow_mut().entry(key) {
-        Entry::Occupied(o) => o.get(),
-        Entry::Vacant(v) => {
-            let (file_name, directory) = v.key();
-            debug!("file_metadata: file_name: {:?}, directory: {:?}", file_name, directory);
-
-            let file_name = file_name.as_deref().unwrap_or("<unknown>");
-            let directory = directory.as_deref().unwrap_or("");
-
-            let (hash_kind, hash_value) = match hash {
-                Some(hash) => {
-                    let kind = match hash.kind {
-                        rustc_span::SourceFileHashAlgorithm::Md5 => llvm::ChecksumKind::MD5,
-                        rustc_span::SourceFileHashAlgorithm::Sha1 => llvm::ChecksumKind::SHA1,
-                        rustc_span::SourceFileHashAlgorithm::Sha256 => llvm::ChecksumKind::SHA256,
-                    };
-                    (kind, hex_encode(hash.hash_bytes()))
+    let cache_key = Some((source_file.name_hash, source_file.src_hash));
+    return debug_context(cx)
+        .created_files
+        .borrow_mut()
+        .entry(cache_key)
+        .or_insert_with(|| alloc_new_file_metadata(cx, source_file));
+
+    #[instrument(skip(cx, source_file), level = "debug")]
+    fn alloc_new_file_metadata<'ll>(
+        cx: &CodegenCx<'ll, '_>,
+        source_file: &SourceFile,
+    ) -> &'ll DIFile {
+        debug!(?source_file.name);
+
+        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(),
+                    )
+                } else {
+                    ("".into(), abs_path.to_string_lossy().into_owned())
                 }
-                None => (llvm::ChecksumKind::None, String::new()),
-            };
+            }
+            other => ("".into(), other.prefer_remapped().to_string_lossy().into_owned()),
+        };
 
-            let file_metadata = unsafe {
-                llvm::LLVMRustDIBuilderCreateFile(
-                    DIB(cx),
-                    file_name.as_ptr().cast(),
-                    file_name.len(),
-                    directory.as_ptr().cast(),
-                    directory.len(),
-                    hash_kind,
-                    hash_value.as_ptr().cast(),
-                    hash_value.len(),
-                )
-            };
+        let hash_kind = match source_file.src_hash.kind {
+            rustc_span::SourceFileHashAlgorithm::Md5 => llvm::ChecksumKind::MD5,
+            rustc_span::SourceFileHashAlgorithm::Sha1 => llvm::ChecksumKind::SHA1,
+            rustc_span::SourceFileHashAlgorithm::Sha256 => llvm::ChecksumKind::SHA256,
+        };
+        let hash_value = hex_encode(source_file.src_hash.hash_bytes());
 
-            v.insert(file_metadata);
-            file_metadata
+        unsafe {
+            llvm::LLVMRustDIBuilderCreateFile(
+                DIB(cx),
+                file_name.as_ptr().cast(),
+                file_name.len(),
+                directory.as_ptr().cast(),
+                directory.len(),
+                hash_kind,
+                hash_value.as_ptr().cast(),
+                hash_value.len(),
+            )
         }
     }
 }
 
+pub fn unknown_file_metadata<'ll>(cx: &CodegenCx<'ll, '_>) -> &'ll DIFile {
+    debug_context(cx).created_files.borrow_mut().entry(None).or_insert_with(|| unsafe {
+        let file_name = "<unknown>";
+        let directory = "";
+        let hash_value = "";
+
+        llvm::LLVMRustDIBuilderCreateFile(
+            DIB(cx),
+            file_name.as_ptr().cast(),
+            file_name.len(),
+            directory.as_ptr().cast(),
+            directory.len(),
+            llvm::ChecksumKind::None,
+            hash_value.as_ptr().cast(),
+            hash_value.len(),
+        )
+    })
+}
+
 trait MsvcBasicName {
     fn msvc_basic_name(self) -> &'static str;
 }

compiler/rustc_codegen_llvm/src/debuginfo/mod.rs

@@ -31,7 +31,7 @@ use rustc_middle::ty::{self, Instance, ParamEnv, Ty, TypeFoldable};
 use rustc_session::config::{self, DebugInfo};
 use rustc_session::Session;
 use rustc_span::symbol::Symbol;
-use rustc_span::{self, BytePos, Pos, SourceFile, SourceFileAndLine, Span};
+use rustc_span::{self, BytePos, Pos, SourceFile, SourceFileAndLine, SourceFileHash, Span};
 use rustc_target::abi::Size;
 
 use libc::c_uint;
@@ -61,7 +61,7 @@ pub struct CodegenUnitDebugContext<'ll, 'tcx> {
     llcontext: &'ll llvm::Context,
     llmod: &'ll llvm::Module,
     builder: &'ll mut DIBuilder<'ll>,
-    created_files: RefCell<FxHashMap<(Option<String>, Option<String>), &'ll DIFile>>,
+    created_files: RefCell<FxHashMap<Option<(u128, SourceFileHash)>, &'ll DIFile>>,
 
     type_map: metadata::TypeMap<'ll, 'tcx>,
     namespace_map: RefCell<DefIdMap<&'ll DIScope>>,

compiler/rustc_metadata/src/rmeta/encoder.rs

@@ -33,18 +33,14 @@ use rustc_middle::ty::{self, SymbolName, Ty, TyCtxt};
 use rustc_serialize::{opaque, Encodable, Encoder};
 use rustc_session::config::CrateType;
 use rustc_session::cstore::{ForeignModule, LinkagePreference, NativeLib};
+use rustc_span::hygiene::{ExpnIndex, HygieneEncodeContext, MacroKind};
 use rustc_span::symbol::{sym, Ident, Symbol};
 use rustc_span::{
     self, DebuggerVisualizerFile, ExternalSource, FileName, SourceFile, Span, SyntaxContext,
 };
-use rustc_span::{
-    hygiene::{ExpnIndex, HygieneEncodeContext, MacroKind},
-    RealFileName,
-};
 use rustc_target::abi::VariantIdx;
 use std::hash::Hash;
 use std::num::NonZeroUsize;
-use std::path::Path;
 use tracing::{debug, trace};
 
 pub(super) struct EncodeContext<'a, 'tcx> {
@@ -490,6 +486,8 @@ impl<'a, 'tcx> EncodeContext<'a, 'tcx> {
         // is done.
         let required_source_files = self.required_source_files.take().unwrap();
 
+        let working_directory = &self.tcx.sess.opts.working_dir;
+
         let adapted = all_source_files
             .iter()
             .enumerate()
@@ -502,76 +500,50 @@ impl<'a, 'tcx> EncodeContext<'a, 'tcx> {
                 (!source_file.is_imported() || self.is_proc_macro)
             })
             .map(|(_, source_file)| {
-                let mut adapted = match source_file.name {
-                    FileName::Real(ref realname) => {
-                        let mut adapted = (**source_file).clone();
-                        adapted.name = FileName::Real(match realname {
-                            RealFileName::LocalPath(path_to_file) => {
-                                // Prepend path of working directory onto potentially
-                                // relative paths, because they could become relative
-                                // to a wrong directory.
-                                // We include `working_dir` as part of the crate hash,
-                                // so it's okay for us to use it as part of the encoded
-                                // metadata.
-                                let working_dir = &self.tcx.sess.opts.working_dir;
-                                match working_dir {
-                                    RealFileName::LocalPath(absolute) => {
-                                        // Although neither working_dir or the file name were subject
-                                        // to path remapping, the concatenation between the two may
-                                        // be. Hence we need to do a remapping here.
-                                        let joined = Path::new(absolute).join(path_to_file);
-                                        let (joined, remapped) =
-                                            source_map.path_mapping().map_prefix(joined);
-                                        if remapped {
-                                            RealFileName::Remapped {
-                                                local_path: None,
-                                                virtual_name: joined,
-                                            }
-                                        } else {
-                                            RealFileName::LocalPath(joined)
-                                        }
-                                    }
-                                    RealFileName::Remapped { local_path: _, virtual_name } => {
-                                        // If working_dir has been remapped, then we emit
-                                        // Remapped variant as the expanded path won't be valid
-                                        RealFileName::Remapped {
-                                            local_path: None,
-                                            virtual_name: Path::new(virtual_name)
-                                                .join(path_to_file),
-                                        }
-                                    }
-                                }
-                            }
-                            RealFileName::Remapped { local_path: _, virtual_name } => {
-                                RealFileName::Remapped {
-                                    // We do not want any local path to be exported into metadata
-                                    local_path: None,
-                                    virtual_name: virtual_name.clone(),
-                                }
-                            }
-                        });
-                        adapted.name_hash = {
-                            let mut hasher: StableHasher = StableHasher::new();
-                            adapted.name.hash(&mut hasher);
-                            hasher.finish::<u128>()
-                        };
-                        Lrc::new(adapted)
+                // At export time we expand all source file paths to absolute paths because
+                // downstream compilation sessions can have a different compiler working
+                // directory, so relative paths from this or any other upstream crate
+                // won't be valid anymore.
+                //
+                // At this point we also erase the actual on-disk path and only keep
+                // the remapped version -- as is necessary for reproducible builds.
+                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,
+                            );
+
+                        if adapted_file_name != *original_file_name {
+                            let mut adapted: SourceFile = (**source_file).clone();
+                            adapted.name = FileName::Real(adapted_file_name);
+                            adapted.name_hash = {
+                                let mut hasher: StableHasher = StableHasher::new();
+                                adapted.name.hash(&mut hasher);
+                                hasher.finish::<u128>()
+                            };
+                            Lrc::new(adapted)
+                        } else {
+                            // Nothing to adapt
+                            source_file.clone()
+                        }
                     }
-
                     // expanded code, not from a file
                     _ => source_file.clone(),
-                };
-
+                }
+            })
+            .map(|mut source_file| {
                 // We're serializing this `SourceFile` into our crate metadata,
                 // so mark it as coming from this crate.
                 // This also ensures that we don't try to deserialize the
                 // `CrateNum` for a proc-macro dependency - since proc macro
                 // dependencies aren't loaded when we deserialize a proc-macro,
                 // trying to remap the `CrateNum` would fail.
                 if self.is_proc_macro {
-                    Lrc::make_mut(&mut adapted).cnum = LOCAL_CRATE;
+                    Lrc::make_mut(&mut source_file).cnum = LOCAL_CRATE;
                 }
-                adapted
+                source_file
             })
             .collect::<Vec<_>>();
 

compiler/rustc_span/src/lib.rs

@@ -335,8 +335,8 @@ impl fmt::Display for FileNameDisplay<'_> {
     }
 }
 
-impl FileNameDisplay<'_> {
-    pub fn to_string_lossy(&self) -> Cow<'_, str> {
+impl<'a> FileNameDisplay<'a> {
+    pub fn to_string_lossy(&self) -> Cow<'a, str> {
         match self.inner {
             FileName::Real(ref inner) => inner.to_string_lossy(self.display_pref),
             _ => Cow::from(format!("{}", self)),
@@ -1153,7 +1153,7 @@ impl FromStr for SourceFileHashAlgorithm {
 }
 
 /// The hash of the on-disk source file used for debug info.
-#[derive(Copy, Clone, PartialEq, Eq, Debug)]
+#[derive(Copy, Clone, PartialEq, Eq, Debug, Hash)]
 #[derive(HashStable_Generic, Encodable, Decodable)]
 pub struct SourceFileHash {
     pub kind: SourceFileHashAlgorithm,