Auto merge of #107782 - Zoxc:worker-local, r=cjgillot

Move the WorkerLocal type from the rustc-rayon fork into rustc_data_structures

This PR moves the definition of the `WorkerLocal` type from `rustc-rayon` into `rustc_data_structures`. This is enabled by the introduction of the `Registry` type which allows you to group up threads to be used by `WorkerLocal` which is basically just an array with an per thread index. The `Registry` type mirrors the one in Rayon and each Rayon worker thread is also registered with the new `Registry`. Safety for `WorkerLocal` is ensured by having it keep a reference to the registry and checking on each access that we're still on the group of threads associated with the registry used to construct it.

Accessing a `WorkerLocal` is micro-optimized due to it being hot since it's used for most arena allocations.

Performance is slightly improved for the parallel compiler:
<table><tr><td rowspan="2">Benchmark</td><td colspan="1"><b>Before</b></th><td colspan="2"><b>After</b></th></tr><tr><td align="right">Time</td><td align="right">Time</td><td align="right">%</th></tr><tr><td>🟣 <b>clap</b>:check</td><td align="right">1.9992s</td><td align="right">1.9949s</td><td align="right"> -0.21%</td></tr><tr><td>🟣 <b>hyper</b>:check</td><td align="right">0.2977s</td><td align="right">0.2970s</td><td align="right"> -0.22%</td></tr><tr><td>🟣 <b>regex</b>:check</td><td align="right">1.1335s</td><td align="right">1.1315s</td><td align="right"> -0.18%</td></tr><tr><td>🟣 <b>syn</b>:check</td><td align="right">1.8235s</td><td align="right">1.8171s</td><td align="right"> -0.35%</td></tr><tr><td>🟣 <b>syntex_syntax</b>:check</td><td align="right">6.9047s</td><td align="right">6.8930s</td><td align="right"> -0.17%</td></tr><tr><td>Total</td><td align="right">12.1586s</td><td align="right">12.1336s</td><td align="right"> -0.21%</td></tr><tr><td>Summary</td><td align="right">1.0000s</td><td align="right">0.9977s</td><td align="right"> -0.23%</td></tr></table>

cc `@SparrowLii`

1 files changed, 7 insertions, 29 deletions

diff --git a/compiler/rustc_data_structures/src/sync.rs b/compiler/rustc_data_structures/src/sync.rs
index ef1da85198f..e73ca56efa0 100644
--- a/compiler/rustc_data_structures/src/sync.rs
+++ b/compiler/rustc_data_structures/src/sync.rs
@@ -45,6 +45,9 @@ use std::hash::{BuildHasher, Hash};
 use std::ops::{Deref, DerefMut};
 use std::panic::{catch_unwind, resume_unwind, AssertUnwindSafe};
 
+mod worker_local;
+pub use worker_local::{Registry, WorkerLocal};
+
 pub use std::sync::atomic::Ordering;
 pub use std::sync::atomic::Ordering::SeqCst;
 
@@ -205,33 +208,6 @@ cfg_if! {
 
         use std::cell::Cell;
 
-        #[derive(Debug)]
-        pub struct WorkerLocal<T>(OneThread<T>);
-
-        impl<T> WorkerLocal<T> {
-            /// Creates a new worker local where the `initial` closure computes the
-            /// value this worker local should take for each thread in the thread pool.
-            #[inline]
-            pub fn new<F: FnMut(usize) -> T>(mut f: F) -> WorkerLocal<T> {
-                WorkerLocal(OneThread::new(f(0)))
-            }
-
-            /// Returns the worker-local value for each thread
-            #[inline]
-            pub fn into_inner(self) -> Vec<T> {
-                vec![OneThread::into_inner(self.0)]
-            }
-        }
-
-        impl<T> Deref for WorkerLocal<T> {
-            type Target = T;
-
-            #[inline(always)]
-            fn deref(&self) -> &T {
-                &self.0
-            }
-        }
-
         pub type MTLockRef<'a, T> = &'a mut MTLock<T>;
 
         #[derive(Debug, Default)]
@@ -351,8 +327,6 @@ cfg_if! {
             };
         }
 
-        pub use rayon_core::WorkerLocal;
-
         pub use rayon::iter::ParallelIterator;
         use rayon::iter::IntoParallelIterator;
 
@@ -383,6 +357,10 @@ pub fn assert_send<T: ?Sized + Send>() {}
 pub fn assert_send_val<T: ?Sized + Send>(_t: &T) {}
 pub fn assert_send_sync_val<T: ?Sized + Sync + Send>(_t: &T) {}
 
+#[derive(Default)]
+#[cfg_attr(parallel_compiler, repr(align(64)))]
+pub struct CacheAligned<T>(pub T);
+
 pub trait HashMapExt<K, V> {
     /// Same as HashMap::insert, but it may panic if there's already an
     /// entry for `key` with a value not equal to `value`