Auto merge of rust-lang#81172 - SimonSapin:ptr-metadata, r=oli-obk

Implement RFC 2580: Pointer metadata & VTable

RFC: rust-lang/rfcs#2580

~~Before merging this PR:~~

* [x] Wait for the end of the RFC’s [FCP to merge](rust-lang/rfcs#2580 (comment)).
* [x] Open a tracking issue: rust-lang#81513
* [x] Update `#[unstable]` attributes in the PR with the tracking issue number

----

This PR extends the language with a new lang item for the `Pointee` trait which is special-cased in trait resolution to implement it for all types. Even in generic contexts, parameters can be assumed to implement it without a corresponding bound.

For this I mostly imitated what the compiler was already doing for the `DiscriminantKind` trait. I’m very unfamiliar with compiler internals, so careful review is appreciated.

This PR also extends the standard library with new unstable APIs in `core::ptr` and `std::ptr`:

```rust
pub trait Pointee {
    /// One of `()`, `usize`, or `DynMetadata<dyn SomeTrait>`
    type Metadata: Copy + Send + Sync + Ord + Hash + Unpin;
}

pub trait Thin = Pointee<Metadata = ()>;

pub const fn metadata<T: ?Sized>(ptr: *const T) -> <T as Pointee>::Metadata {}

pub const fn from_raw_parts<T: ?Sized>(*const (), <T as Pointee>::Metadata) -> *const T {}
pub const fn from_raw_parts_mut<T: ?Sized>(*mut (),<T as Pointee>::Metadata) -> *mut T {}

impl<T: ?Sized> NonNull<T> {
    pub const fn from_raw_parts(NonNull<()>, <T as Pointee>::Metadata) -> NonNull<T> {}

    /// Convenience for `(ptr.cast(), metadata(ptr))`
    pub const fn to_raw_parts(self) -> (NonNull<()>, <T as Pointee>::Metadata) {}
}

impl<T: ?Sized> *const T {
    pub const fn to_raw_parts(self) -> (*const (), <T as Pointee>::Metadata) {}
}

impl<T: ?Sized> *mut T {
    pub const fn to_raw_parts(self) -> (*mut (), <T as Pointee>::Metadata) {}
}

/// `<dyn SomeTrait as Pointee>::Metadata == DynMetadata<dyn SomeTrait>`
pub struct DynMetadata<Dyn: ?Sized> {
    // Private pointer to vtable
}

impl<Dyn: ?Sized> DynMetadata<Dyn> {
    pub fn size_of(self) -> usize {}
    pub fn align_of(self) -> usize {}
    pub fn layout(self) -> crate::alloc::Layout {}
}

unsafe impl<Dyn: ?Sized> Send for DynMetadata<Dyn> {}
unsafe impl<Dyn: ?Sized> Sync for DynMetadata<Dyn> {}
impl<Dyn: ?Sized> Debug for DynMetadata<Dyn> {}
impl<Dyn: ?Sized> Unpin for DynMetadata<Dyn> {}
impl<Dyn: ?Sized> Copy for DynMetadata<Dyn> {}
impl<Dyn: ?Sized> Clone for DynMetadata<Dyn> {}
impl<Dyn: ?Sized> Eq for DynMetadata<Dyn> {}
impl<Dyn: ?Sized> PartialEq for DynMetadata<Dyn> {}
impl<Dyn: ?Sized> Ord for DynMetadata<Dyn> {}
impl<Dyn: ?Sized> PartialOrd for DynMetadata<Dyn> {}
impl<Dyn: ?Sized> Hash for DynMetadata<Dyn> {}
```

API differences from the RFC, in areas noted as unresolved questions in the RFC:

* Module-level functions instead of associated `from_raw_parts` functions on `*const T` and `*mut T`, following the precedent of `null`, `slice_from_raw_parts`, etc.
* Added `to_raw_parts`

Author: bors

core/src/hash/mod.rs

@@ -673,39 +673,57 @@ mod impls {
     #[stable(feature = "rust1", since = "1.0.0")]
     impl<T: ?Sized> Hash for *const T {
         fn hash<H: Hasher>(&self, state: &mut H) {
-            if mem::size_of::<Self>() == mem::size_of::<usize>() {
-                // Thin pointer
-                state.write_usize(*self as *const () as usize);
-            } else {
-                // Fat pointer
-                // SAFETY: we are accessing the memory occupied by `self`
-                // which is guaranteed to be valid.
-                // This assumes a fat pointer can be represented by a `(usize, usize)`,
-                // which is safe to do in `std` because it is shipped and kept in sync
-                // with the implementation of fat pointers in `rustc`.
-                let (a, b) = unsafe { *(self as *const Self as *const (usize, usize)) };
-                state.write_usize(a);
-                state.write_usize(b);
+            #[cfg(not(bootstrap))]
+            {
+                let (address, metadata) = self.to_raw_parts();
+                state.write_usize(address as usize);
+                metadata.hash(state);
+            }
+            #[cfg(bootstrap)]
+            {
+                if mem::size_of::<Self>() == mem::size_of::<usize>() {
+                    // Thin pointer
+                    state.write_usize(*self as *const () as usize);
+                } else {
+                    // Fat pointer
+                    // SAFETY: we are accessing the memory occupied by `self`
+                    // which is guaranteed to be valid.
+                    // This assumes a fat pointer can be represented by a `(usize, usize)`,
+                    // which is safe to do in `std` because it is shipped and kept in sync
+                    // with the implementation of fat pointers in `rustc`.
+                    let (a, b) = unsafe { *(self as *const Self as *const (usize, usize)) };
+                    state.write_usize(a);
+                    state.write_usize(b);
+                }
             }
         }
     }
 
     #[stable(feature = "rust1", since = "1.0.0")]
     impl<T: ?Sized> Hash for *mut T {
         fn hash<H: Hasher>(&self, state: &mut H) {
-            if mem::size_of::<Self>() == mem::size_of::<usize>() {
-                // Thin pointer
-                state.write_usize(*self as *const () as usize);
-            } else {
-                // Fat pointer
-                // SAFETY: we are accessing the memory occupied by `self`
-                // which is guaranteed to be valid.
-                // This assumes a fat pointer can be represented by a `(usize, usize)`,
-                // which is safe to do in `std` because it is shipped and kept in sync
-                // with the implementation of fat pointers in `rustc`.
-                let (a, b) = unsafe { *(self as *const Self as *const (usize, usize)) };
-                state.write_usize(a);
-                state.write_usize(b);
+            #[cfg(not(bootstrap))]
+            {
+                let (address, metadata) = self.to_raw_parts();
+                state.write_usize(address as usize);
+                metadata.hash(state);
+            }
+            #[cfg(bootstrap)]
+            {
+                if mem::size_of::<Self>() == mem::size_of::<usize>() {
+                    // Thin pointer
+                    state.write_usize(*self as *const () as usize);
+                } else {
+                    // Fat pointer
+                    // SAFETY: we are accessing the memory occupied by `self`
+                    // which is guaranteed to be valid.
+                    // This assumes a fat pointer can be represented by a `(usize, usize)`,
+                    // which is safe to do in `std` because it is shipped and kept in sync
+                    // with the implementation of fat pointers in `rustc`.
+                    let (a, b) = unsafe { *(self as *const Self as *const (usize, usize)) };
+                    state.write_usize(a);
+                    state.write_usize(b);
+                }
             }
         }
     }

core/src/lib.rs

@@ -111,6 +111,7 @@
 #![feature(extended_key_value_attributes)]
 #![feature(extern_types)]
 #![feature(fundamental)]
+#![cfg_attr(not(bootstrap), feature(intra_doc_pointers))]
 #![feature(intrinsics)]
 #![feature(lang_items)]
 #![feature(link_llvm_intrinsics)]
@@ -123,6 +124,7 @@
 #![feature(auto_traits)]
 #![feature(or_patterns)]
 #![feature(prelude_import)]
+#![cfg_attr(not(bootstrap), feature(ptr_metadata))]
 #![feature(repr_simd, platform_intrinsics)]
 #![feature(rustc_attrs)]
 #![feature(simd_ffi)]
@@ -133,6 +135,7 @@
 #![feature(stmt_expr_attributes)]
 #![feature(str_split_as_str)]
 #![feature(str_split_inclusive_as_str)]
+#![feature(trait_alias)]
 #![feature(transparent_unions)]
 #![feature(try_blocks)]
 #![feature(unboxed_closures)]

core/src/ptr/const_ptr.rs

@@ -48,6 +48,17 @@ impl<T: ?Sized> *const T {
         self as _
     }
 
+    /// Decompose a (possibly wide) pointer into is address and metadata components.
+    ///
+    /// The pointer can be later reconstructed with [`from_raw_parts`].
+    #[cfg(not(bootstrap))]
+    #[unstable(feature = "ptr_metadata", issue = "81513")]
+    #[rustc_const_unstable(feature = "ptr_metadata", issue = "81513")]
+    #[inline]
+    pub const fn to_raw_parts(self) -> (*const (), <T as super::Pointee>::Metadata) {
+        (self.cast(), metadata(self))
+    }
+
     /// Returns `None` if the pointer is null, or else returns a shared reference to
     /// the value wrapped in `Some`. If the value may be uninitialized, [`as_uninit_ref`]
     /// must be used instead.
@@ -905,9 +916,14 @@ impl<T> *const [T] {
     #[unstable(feature = "slice_ptr_len", issue = "71146")]
     #[rustc_const_unstable(feature = "const_slice_ptr_len", issue = "71146")]
     pub const fn len(self) -> usize {
-        // SAFETY: this is safe because `*const [T]` and `FatPtr<T>` have the same layout.
-        // Only `std` can make this guarantee.
-        unsafe { Repr { rust: self }.raw }.len
+        #[cfg(bootstrap)]
+        {
+            // SAFETY: this is safe because `*const [T]` and `FatPtr<T>` have the same layout.
+            // Only `std` can make this guarantee.
+            unsafe { Repr { rust: self }.raw }.len
+        }
+        #[cfg(not(bootstrap))]
+        metadata(self)
     }
 
     /// Returns a raw pointer to the slice's buffer.