the behavior of the type system not only depends on the current
assumptions, but also the currentnphase of the compiler. This is
mostly necessary as we need to decide whether and how to reveal
opaque types. We track this via the `TypingMode`.
Over in Zed we've noticed that loading crates for a large-ish workspace can take almost 200ms. We've pinned it down to how rustc searches for paths, as it performs a linear search over the list of candidate paths. In our case the candidate list had about 20k entries which we had to iterate over for each dependency being loaded.
This commit introduces a simple FilesIndex that's just a sorted Vec under the hood. Since crates are looked up by both prefix and suffix, we perform a range search on said Vec (which constraints the search space based on prefix) and follow up with a linear scan of entries with matching suffixes.
FilesIndex is also pre-filtered before any queries are performed using available target information; query prefixes/sufixes are based on the target we are compiling for, so we can remove entries that can never match up front.
Overall, this commit brings down build time for us in dev scenarios by about 6%.
100ms might not seem like much, but this is a constant cost that each of our workspace crates has to pay, even when said crate is miniscule.
Add a default implementation for CodegenBackend::link
As a side effect this should add raw-dylib support to cg_gcc as the default ArchiveBuilderBuilder that is used implements create_dll_import_lib. I haven't tested if the raw-dylib support actually works however.
After link_binary the temporary files referenced by CodegenResults are
deleted, so calling link_binary again with the same CodegenResults
should not be allowed.
As a side effect this should add raw-dylib support to cg_gcc as the
default ArchiveBuilderBuilder that is used implements
create_dll_import_lib. I haven't tested if the raw-dylib support
actually works however.
Use lld with non-LLVM backends
On arm64, Cranelift used to produce object files that don't work with lld. This has since been fixed. The GCC backend should always produce object files that work with lld unless lld for whatever reason drops GCC support. Most of the other more niche backends don't use cg_ssa's linker code at all. If they do and don't work with lld, they can always disable lld usage using a cli argument.
Without this commit using cg_clif is by default in a non-trivial amount of cases a perf regression on Linux due to ld.bfd being a fair bit slower than lld. It is possible to explicitly enable it without this commit, but most users are unlikely to do this.
On arm64, Cranelift used to produce object files that don't work with
lld. This has since been fixed. The GCC backend should always produce
object files that work with lld unless lld for whatever reason drops GCC
support. Most of the other more niche backends don't use cg_ssa's linker
code at all. If they do and don't work with lld, they can always disable
lld usage using a cli argument.
Without this commit using cg_clif is by default in a non-trivial amount
of cases a perf regression on Linux due to ld.bfd being a fair bit
slower than lld. It is possible to explicitly enable it without this
commit, but most users are unlikely to do this.
Set "symbol name" in raw-dylib import libraries to the decorated name
`windows-rs` received a bug report that mixing raw-dylib generated and the Windows SDK import libraries was causing linker failures: <https://github.com/microsoft/windows-rs/issues/3285>
The root cause turned out to be #124958, that is we are not including the decorated name in the import library and so the import name type is also not being correctly set.
This change modifies the generation of import libraries to set the "symbol name" to the fully decorated name and correctly marks the import as being data vs function.
Note that this also required some changes to how the symbol is named within Rust: for MSVC we now need to use the decorated name but for MinGW we still need to use partially decorated (or undecorated) name.
Fixes#124958
Passing i686 MSVC and MinGW build: <https://github.com/rust-lang/rust/actions/runs/11000433888?pr=130586>
r? `@ChrisDenton`
Reduce dependence on the target name
The target name can be anything with custom target specs. Matching on fields inside the target spec is much more robust than matching on the target name.
Also remove the unused is_builtin target spec field.
Generate correct symbols.o for sparc-unknown-none-elf
This fixes#130172 by selecting the correct ELF Machine type for sparc-unknown-none-elf (which has a baseline of SPARC V7).
The target name can be anything with custom target specs. Matching on
fields inside the target spec is much more robust than matching on the
target name.
Move versioned Apple LLVM targets from `rustc_target` to `rustc_codegen_ssa`
Fully specified LLVM targets contain the OS version on macOS/iOS/tvOS/watchOS/visionOS, and this version depends on the deployment target environment variables like `MACOSX_DEPLOYMENT_TARGET`, `IPHONEOS_DEPLOYMENT_TARGET` etc.
We would like to move this to later in the compilation pipeline, both because it feels impure to access environment variables when fetching target information, but mostly because we need access to more information from https://github.com/rust-lang/rust/pull/130883 to do https://github.com/rust-lang/rust/issues/118204. See also https://github.com/rust-lang/rust/pull/129342#issuecomment-2335156119 for some discussion.
The first and second commit does the actual refactor, it should be a non-functional change, the third commit adds diagnostics for invalid deployment targets, which are now possible to do because we have access to the session.
Tested with the same commands as in https://github.com/rust-lang/rust/pull/130435.
r? ``````@petrochenkov``````
Remove support for `-Zprofile` (gcov-style coverage instrumentation)
Tracking issue: #42524
MCP: https://github.com/rust-lang/compiler-team/issues/798
---
This PR removes the unstable `-Zprofile` flag, which enables ”gcov-style” coverage instrumentation, along with its associated `-Zprofile-emit` configuration flag.
(The profile flag predates and is almost entirely separate from the stable `-Cinstrument-coverage` flag.)
Notably, the `-Zprofile` flag:
- Is largely untested in-tree, having only one run-make test that does not check whether its output is correct or useful.
- Has no known maintainer.
- Has seen no push towards stabilization.
- Has at least one severe regression reported in 2022 that apparently remains unaddressed.
- #100125
- Is confusingly named, since it appears to be more about coverage than performance profiling, and has nothing to do with PGO.
- Is fundamentally limited by relying on counters auto-inserted by LLVM, with no knowledge of Rust beyond debuginfo.
The OS version depends on the deployment target environment variables,
the access of which we want to move to later in the compilation pipeline
that has access to more information, for example `env_depinfo`.
- removed extra bits from predicates queries that are no longer needed in the new system
- removed the need for `non_erasable_generics` to take in tcx and DefId, removed unused arguments in callers
Create `_imp__` symbols also when doing ThinLTO
When generating a rlib crate on Windows we create `dllimport` / `_imp__` symbols for each global. This effectively makes the rlib contain an import library for itself and allows them to both be dynamically and statically linked. However when doing ThinLTO we do not generate these and thus we end up with missing symbols. Microsoft's `link` can fix these up (and emits warnings), but `lld` seems to currently be unable to.
This PR also does this generation for ThinLTO avoiding those issues with `lld` and also avoids the warnings on `link`.
This is an workaround for https://github.com/rust-lang/rust/issues/81408.
cc `@lqd`
Apple: Do not specify an SDK version in `rlib` object files
This was added in https://github.com/rust-lang/rust/pull/114114, but is unnecessary, since it ends up being overwritten when linking anyhow, and it feels wrong to embed some arbitrary SDK version in here. The object files produced by LLVM also do not set this, and the tooling shows `n/a` when it's `0`, so it seems to genuinely be optional in object files.
I've also added a test for the different places the SDK version shows up, and documented a bit more in the code how SDK versions work.
See https://github.com/rust-lang/rust/issues/129432 for the bigger picture.
Tested with (excludes the same few targets as in https://github.com/rust-lang/rust/pull/130435):
```console
./x test tests/run-make/apple-sdk-version --target aarch64-apple-darwin,aarch64-apple-ios,aarch64-apple-ios-macabi,aarch64-apple-ios-sim,aarch64-apple-tvos,aarch64-apple-tvos-sim,aarch64-apple-visionos,aarch64-apple-visionos-sim,aarch64-apple-watchos,aarch64-apple-watchos-sim,arm64_32-apple-watchos,armv7k-apple-watchos,armv7s-apple-ios,x86_64-apple-darwin,x86_64-apple-ios,x86_64-apple-ios-macabi,x86_64-apple-tvos,x86_64-apple-watchos-sim,x86_64h-apple-darwin
IPHONEOS_DEPLOYMENT_TARGET=10.0 ./x test tests/run-make/apple-sdk-version --target=i386-apple-ios
```
CC `@BlackHoleFox,` you [originally commented on these values](https://github.com/rust-lang/rust/pull/114114#discussion_r1300599445).
`@rustbot` label O-apple
Fix up setting strip = true in Cargo.toml makes build scripts fail in…
Fix issue: https://github.com/rust-lang/rust/issues/110536
Strip binary is PATH dependent which breaks builds in MacOS.
For example, on my Mac, the output of 'which strip' is '/opt/homebrew/opt/binutils/bin/strip', which leads to incorrect 'strip' results. Therefore, just like on other systems, it is also necessary to specify 'stripcmd' on macOS. However, it seems that there is a bug in binutils [bugzilla-Bug 31571](https://sourceware.org/bugzilla/show_bug.cgi?id=31571), which leads to the problem mentioned above.
Implement a Method to Seal `DiagInner`'s Suggestions
This PR adds a method on `DiagInner` called `.seal_suggestions()` to prevent new suggestions from being added while preserving existing suggestions.
This is useful because currently there is no way to prevent new suggestions from being added to a diagnostic. `.disable_suggestions()` is the closest but it gets rid of all suggestions before and after the call.
Therefore, `.seal_suggestions()` can be used when, for example, misspelled keyword is detected and reported. In such cases, we may want to prevent other suggestions from being added to the diagnostic, as they would likely be meaningless once the misspelled keyword is identified. For context: https://github.com/rust-lang/rust/pull/129899#discussion_r1741307132
To store an additional state, the type of the `suggestions` field in `DiagInner` was changed into a three variant enum. While this change affects files across different crates, care was taken to preserve the existing code's semantics. This is validated by the fact that all UI tests pass without any modifications.
r? chenyukang
linker: Allow MSVC to use import libraries following the Meson/MinGW convention
Hi all,
This PR implements support for `MsvcLinker` to use import libraries following Meson and the MinGW toolchain's naming convention. Meson [follows the `libfoo.dll.a` naming convention](https://mesonbuild.com/FAQ.html#why-does-building-my-project-with-msvc-output-static-libraries-called-libfooa) to disambiguate between static and import libraries.
This support already existed for static libraries (see #100101), but not for dynamic libraries. The latter case was added by duplicating the logic in `native_libs::find_native_static_library`, but a separate case was added in `link_dylib_by_name` for the Windows CRT libraries which must be handled by the linker itself.
See for prerequisites #129366, #126094, and #128370.
All feedback is appreciated!
Fixes#122455
cc `@sdroege` `@nirbheek`
