Auto merge of #96544 - m-ysk:feature/issue-96358, r=cjgillot

Stop keeping metadata in memory before writing it to disk

Fixes #96358

I created this PR according with the instruction given in the issue except for the following points:

- While the issue says "Write metadata into the temporary file in `encode_and_write_metadata` even if `!need_metadata_file`", I could not do that. That is because though I tried to do that and run `x.py test`, I got a lot of test failures as follows.

<details>
<summary>List of failed tests</summary>
<pre>
<code>
failures:
    [ui] src/test/ui/json-multiple.rs
    [ui] src/test/ui/json-options.rs
    [ui] src/test/ui/rmeta/rmeta-rpass.rs
    [ui] src/test/ui/save-analysis/emit-notifications.rs
    [ui] src/test/ui/svh/changing-crates.rs
    [ui] src/test/ui/svh/svh-change-lit.rs
    [ui] src/test/ui/svh/svh-change-significant-cfg.rs
    [ui] src/test/ui/svh/svh-change-trait-bound.rs
    [ui] src/test/ui/svh/svh-change-type-arg.rs
    [ui] src/test/ui/svh/svh-change-type-ret.rs
    [ui] src/test/ui/svh/svh-change-type-static.rs
    [ui] src/test/ui/svh/svh-use-trait.rs

test result: FAILED. 12915 passed; 12 failed; 100 ignored; 0 measured; 0 filtered out; finished in 71.41s

Some tests failed in compiletest suite=ui mode=ui host=x86_64-unknown-linux-gnu target=x86_64-unknown-linux-gnu
Build completed unsuccessfully in 0:01:58
</code>
</pre>
</details>

- I could not resolve the extra tasks about `create_rmeta_file` and `create_compressed_metadata_file` for my lack of ability.

Cargo.lock

@@ -3969,7 +3969,6 @@ dependencies = [
  "rustc_ty_utils",
  "rustc_typeck",
  "smallvec",
- "tempfile",
  "tracing",
  "winapi",
 ]
@@ -4080,6 +4079,7 @@ dependencies = [
  "rustc_type_ir",
  "smallvec",
  "snap",
+ "tempfile",
  "tracing",
 ]
 

compiler/rustc_codegen_ssa/src/back/link.rs

@@ -6,6 +6,7 @@ use rustc_data_structures::temp_dir::MaybeTempDir;
 use rustc_errors::{ErrorGuaranteed, Handler};
 use rustc_fs_util::fix_windows_verbatim_for_gcc;
 use rustc_hir::def_id::CrateNum;
+use rustc_metadata::fs::{emit_metadata, METADATA_FILENAME};
 use rustc_middle::middle::dependency_format::Linkage;
 use rustc_middle::middle::exported_symbols::SymbolExportKind;
 use rustc_session::config::{self, CFGuard, CrateType, DebugInfo, LdImpl, Strip};
@@ -28,10 +29,7 @@ use super::command::Command;
 use super::linker::{self, Linker};
 use super::metadata::{create_rmeta_file, MetadataPosition};
 use super::rpath::{self, RPathConfig};
-use crate::{
-    looks_like_rust_object_file, CodegenResults, CompiledModule, CrateInfo, NativeLib,
-    METADATA_FILENAME,
-};
+use crate::{looks_like_rust_object_file, CodegenResults, CompiledModule, CrateInfo, NativeLib};
 
 use cc::windows_registry;
 use regex::Regex;
@@ -241,22 +239,6 @@ pub fn each_linked_rlib(
     Ok(())
 }
 
-/// We use a temp directory here to avoid races between concurrent rustc processes,
-/// such as builds in the same directory using the same filename for metadata while
-/// building an `.rlib` (stomping over one another), or writing an `.rmeta` into a
-/// directory being searched for `extern crate` (observing an incomplete file).
-/// The returned path is the temporary file containing the complete metadata.
-pub fn emit_metadata(sess: &Session, metadata: &[u8], tmpdir: &MaybeTempDir) -> PathBuf {
-    let out_filename = tmpdir.as_ref().join(METADATA_FILENAME);
-    let result = fs::write(&out_filename, metadata);
-
-    if let Err(e) = result {
-        sess.fatal(&format!("failed to write {}: {}", out_filename.display(), e));
-    }
-
-    out_filename
-}
-
 /// Create an 'rlib'.
 ///
 /// An rlib in its current incarnation is essentially a renamed .a file. The rlib primarily contains

compiler/rustc_codegen_ssa/src/back/metadata.rs

@@ -16,14 +16,13 @@ use rustc_data_structures::memmap::Mmap;
 use rustc_data_structures::owning_ref::OwningRef;
 use rustc_data_structures::rustc_erase_owner;
 use rustc_data_structures::sync::MetadataRef;
+use rustc_metadata::fs::METADATA_FILENAME;
 use rustc_metadata::EncodedMetadata;
 use rustc_session::cstore::MetadataLoader;
 use rustc_session::Session;
 use rustc_target::abi::Endian;
 use rustc_target::spec::{RelocModel, Target};
 
-use crate::METADATA_FILENAME;
-
 /// The default metadata loader. This is used by cg_llvm and cg_clif.
 ///
 /// # Metadata location

compiler/rustc_codegen_ssa/src/lib.rs

@@ -64,9 +64,6 @@ pub struct ModuleCodegen<M> {
     pub kind: ModuleKind,
 }
 
-// FIXME(eddyb) maybe include the crate name in this?
-pub const METADATA_FILENAME: &str = "lib.rmeta";
-
 impl<M> ModuleCodegen<M> {
     pub fn into_compiled_module(
         self,

compiler/rustc_data_structures/src/memmap.rs

@@ -1,6 +1,6 @@
 use std::fs::File;
 use std::io;
-use std::ops::Deref;
+use std::ops::{Deref, DerefMut};
 
 use crate::owning_ref::StableAddress;
 
@@ -45,3 +45,64 @@ impl Deref for Mmap {
 // export any function that can cause the `Vec` to be re-allocated. As such the address of the
 // bytes inside this `Vec` is stable.
 unsafe impl StableAddress for Mmap {}
+
+#[cfg(not(target_arch = "wasm32"))]
+pub struct MmapMut(memmap2::MmapMut);
+
+#[cfg(target_arch = "wasm32")]
+pub struct MmapMut(Vec<u8>);
+
+#[cfg(not(target_arch = "wasm32"))]
+impl MmapMut {
+    #[inline]
+    pub fn map_anon(len: usize) -> io::Result<Self> {
+        let mmap = memmap2::MmapMut::map_anon(len)?;
+        Ok(MmapMut(mmap))
+    }
+
+    #[inline]
+    pub fn flush(&mut self) -> io::Result<()> {
+        self.0.flush()
+    }
+
+    #[inline]
+    pub fn make_read_only(self) -> std::io::Result<Mmap> {
+        let mmap = self.0.make_read_only()?;
+        Ok(Mmap(mmap))
+    }
+}
+
+#[cfg(target_arch = "wasm32")]
+impl MmapMut {
+    #[inline]
+    pub fn map_anon(len: usize) -> io::Result<Self> {
+        let data = Vec::with_capacity(len);
+        Ok(MmapMut(data))
+    }
+
+    #[inline]
+    pub fn flush(&mut self) -> io::Result<()> {
+        Ok(())
+    }
+
+    #[inline]
+    pub fn make_read_only(self) -> std::io::Result<Mmap> {
+        Ok(Mmap(self.0))
+    }
+}
+
+impl Deref for MmapMut {
+    type Target = [u8];
+
+    #[inline]
+    fn deref(&self) -> &[u8] {
+        &*self.0
+    }
+}
+
+impl DerefMut for MmapMut {
+    #[inline]
+    fn deref_mut(&mut self) -> &mut [u8] {
+        &mut *self.0
+    }
+}

compiler/rustc_interface/Cargo.toml

@@ -46,7 +46,6 @@ rustc_query_impl = { path = "../rustc_query_impl" }
 rustc_resolve = { path = "../rustc_resolve" }
 rustc_trait_selection = { path = "../rustc_trait_selection" }
 rustc_ty_utils = { path = "../rustc_ty_utils" }
-tempfile = "3.2"
 
 [target.'cfg(unix)'.dependencies]
 libc = "0.2"

compiler/rustc_interface/src/passes.rs

@@ -5,18 +5,15 @@ use crate::util;
 use ast::CRATE_NODE_ID;
 use rustc_ast::{self as ast, visit};
 use rustc_borrowck as mir_borrowck;
-use rustc_codegen_ssa::back::link::emit_metadata;
 use rustc_codegen_ssa::traits::CodegenBackend;
 use rustc_data_structures::parallel;
 use rustc_data_structures::sync::{Lrc, OnceCell, WorkerLocal};
-use rustc_data_structures::temp_dir::MaybeTempDir;
 use rustc_errors::{Applicability, ErrorGuaranteed, MultiSpan, PResult};
 use rustc_expand::base::{ExtCtxt, LintStoreExpand, ResolverExpand};
-use rustc_hir::def_id::{StableCrateId, LOCAL_CRATE};
+use rustc_hir::def_id::StableCrateId;
 use rustc_hir::definitions::Definitions;
 use rustc_lint::{BufferedEarlyLint, EarlyCheckNode, LintStore};
 use rustc_metadata::creader::CStore;
-use rustc_metadata::{encode_metadata, EncodedMetadata};
 use rustc_middle::arena::Arena;
 use rustc_middle::dep_graph::DepGraph;
 use rustc_middle::ty::query::{ExternProviders, Providers};
@@ -29,14 +26,13 @@ use rustc_query_impl::{OnDiskCache, Queries as TcxQueries};
 use rustc_resolve::{Resolver, ResolverArenas};
 use rustc_session::config::{CrateType, Input, OutputFilenames, OutputType};
 use rustc_session::cstore::{CrateStoreDyn, MetadataLoader, MetadataLoaderDyn};
-use rustc_session::output::{filename_for_input, filename_for_metadata};
+use rustc_session::output::filename_for_input;
 use rustc_session::search_paths::PathKind;
 use rustc_session::{Limit, Session};
 use rustc_span::symbol::{sym, Symbol};
 use rustc_span::FileName;
 use rustc_trait_selection::traits;
 use rustc_typeck as typeck;
-use tempfile::Builder as TempFileBuilder;
 use tracing::{info, warn};
 
 use std::any::Any;
@@ -993,69 +989,6 @@ fn analysis(tcx: TyCtxt<'_>, (): ()) -> Result<()> {
     Ok(())
 }
 
-fn encode_and_write_metadata(
-    tcx: TyCtxt<'_>,
-    outputs: &OutputFilenames,
-) -> (EncodedMetadata, bool) {
-    #[derive(PartialEq, Eq, PartialOrd, Ord)]
-    enum MetadataKind {
-        None,
-        Uncompressed,
-        Compressed,
-    }
-
-    let metadata_kind = tcx
-        .sess
-        .crate_types()
-        .iter()
-        .map(|ty| match *ty {
-            CrateType::Executable | CrateType::Staticlib | CrateType::Cdylib => MetadataKind::None,
-
-            CrateType::Rlib => MetadataKind::Uncompressed,
-
-            CrateType::Dylib | CrateType::ProcMacro => MetadataKind::Compressed,
-        })
-        .max()
-        .unwrap_or(MetadataKind::None);
-
-    let metadata = match metadata_kind {
-        MetadataKind::None => EncodedMetadata::new(),
-        MetadataKind::Uncompressed | MetadataKind::Compressed => encode_metadata(tcx),
-    };
-
-    let _prof_timer = tcx.sess.prof.generic_activity("write_crate_metadata");
-
-    let need_metadata_file = tcx.sess.opts.output_types.contains_key(&OutputType::Metadata);
-    if need_metadata_file {
-        let crate_name = tcx.crate_name(LOCAL_CRATE);
-        let out_filename = filename_for_metadata(tcx.sess, crate_name.as_str(), outputs);
-        // To avoid races with another rustc process scanning the output directory,
-        // we need to write the file somewhere else and atomically move it to its
-        // final destination, with an `fs::rename` call. In order for the rename to
-        // always succeed, the temporary file needs to be on the same filesystem,
-        // which is why we create it inside the output directory specifically.
-        let metadata_tmpdir = TempFileBuilder::new()
-            .prefix("rmeta")
-            .tempdir_in(out_filename.parent().unwrap())
-            .unwrap_or_else(|err| tcx.sess.fatal(&format!("couldn't create a temp dir: {}", err)));
-        let metadata_tmpdir = MaybeTempDir::new(metadata_tmpdir, tcx.sess.opts.cg.save_temps);
-        let metadata_filename = emit_metadata(tcx.sess, metadata.raw_data(), &metadata_tmpdir);
-        if let Err(e) = util::non_durable_rename(&metadata_filename, &out_filename) {
-            tcx.sess.fatal(&format!("failed to write {}: {}", out_filename.display(), e));
-        }
-        if tcx.sess.opts.json_artifact_notifications {
-            tcx.sess
-                .parse_sess
-                .span_diagnostic
-                .emit_artifact_notification(&out_filename, "metadata");
-        }
-    }
-
-    let need_metadata_module = metadata_kind == MetadataKind::Compressed;
-
-    (metadata, need_metadata_module)
-}
-
 /// Runs the codegen backend, after which the AST and analysis can
 /// be discarded.
 pub fn start_codegen<'tcx>(
@@ -1065,7 +998,8 @@ pub fn start_codegen<'tcx>(
 ) -> Box<dyn Any> {
     info!("Pre-codegen\n{:?}", tcx.debug_stats());
 
-    let (metadata, need_metadata_module) = encode_and_write_metadata(tcx, outputs);
+    let (metadata, need_metadata_module) =
+        rustc_metadata::fs::encode_and_write_metadata(tcx, outputs);
 
     let codegen = tcx.sess.time("codegen_crate", move || {
         codegen_backend.codegen_crate(tcx, metadata, need_metadata_module)

compiler/rustc_interface/src/util.rs

@@ -650,24 +650,6 @@ pub fn build_output_filenames(
     }
 }
 
-#[cfg(not(target_os = "linux"))]
-pub fn non_durable_rename(src: &Path, dst: &Path) -> std::io::Result<()> {
-    std::fs::rename(src, dst)
-}
-
-/// This function attempts to bypass the auto_da_alloc heuristic implemented by some filesystems
-/// such as btrfs and ext4. When renaming over a file that already exists then they will "helpfully"
-/// write back the source file before committing the rename in case a developer forgot some of
-/// the fsyncs in the open/write/fsync(file)/rename/fsync(dir) dance for atomic file updates.
-///
-/// To avoid triggering this heuristic we delete the destination first, if it exists.
-/// The cost of an extra syscall is much lower than getting descheduled for the sync IO.
-#[cfg(target_os = "linux")]
-pub fn non_durable_rename(src: &Path, dst: &Path) -> std::io::Result<()> {
-    let _ = std::fs::remove_file(dst);
-    std::fs::rename(src, dst)
-}
-
 /// Returns a version string such as "1.46.0 (04488afe3 2020-08-24)"
 pub fn version_str() -> Option<&'static str> {
     option_env!("CFG_VERSION")

compiler/rustc_metadata/Cargo.toml

@@ -12,6 +12,7 @@ odht = { version = "0.3.1", features = ["nightly"] }
 snap = "1"
 tracing = "0.1"
 smallvec = { version = "1.8.1", features = ["union", "may_dangle"] }
+tempfile = "3.2"
 rustc_middle = { path = "../rustc_middle" }
 rustc_attr = { path = "../rustc_attr" }
 rustc_data_structures = { path = "../rustc_data_structures" }