Rollup merge of #108022 - CraftSpider:align-bytes, r=oli-obk

Support allocations with non-Box<[u8]> bytes

This is prep work for allowing miri to support passing pointers to C code, which will require `Allocation`s to be correctly aligned. Currently, it just makes `Allocation` generic and plumbs the necessary changes through the right places.

The follow-up to this will be adding a type in the miri interpreter which correctly aligns the bytes, using that for the Miri engine, then allowing Miri to pass pointers into these allocations to C calls.

Based off of #100467, credit to ```@emarteca``` for the code

compiler/rustc_middle/src/mir/interpret/allocation.rs

@@ -8,7 +8,8 @@ mod tests;
 use std::borrow::Cow;
 use std::fmt;
 use std::hash;
-use std::ops::Range;
+use std::hash::Hash;
+use std::ops::{Deref, DerefMut, Range};
 use std::ptr;
 
 use either::{Left, Right};
@@ -29,6 +30,39 @@ use provenance_map::*;
 
 pub use init_mask::{InitChunk, InitChunkIter};
 
+/// Functionality required for the bytes of an `Allocation`.
+pub trait AllocBytes:
+    Clone + fmt::Debug + Eq + PartialEq + Hash + Deref<Target = [u8]> + DerefMut<Target = [u8]>
+{
+    /// Adjust the bytes to the specified alignment -- by default, this is a no-op.
+    fn adjust_to_align(self, _align: Align) -> Self;
+
+    /// Create an `AllocBytes` from a slice of `u8`.
+    fn from_bytes<'a>(slice: impl Into<Cow<'a, [u8]>>, _align: Align) -> Self;
+
+    /// Create a zeroed `AllocBytes` of the specified size and alignment;
+    /// call the callback error handler if there is an error in allocating the memory.
+    fn zeroed(size: Size, _align: Align) -> Option<Self>;
+}
+
+// Default `bytes` for `Allocation` is a `Box<[u8]>`.
+impl AllocBytes for Box<[u8]> {
+    fn adjust_to_align(self, _align: Align) -> Self {
+        self
+    }
+
+    fn from_bytes<'a>(slice: impl Into<Cow<'a, [u8]>>, _align: Align) -> Self {
+        Box::<[u8]>::from(slice.into())
+    }
+
+    fn zeroed(size: Size, _align: Align) -> Option<Self> {
+        let bytes = Box::<[u8]>::try_new_zeroed_slice(size.bytes_usize()).ok()?;
+        // SAFETY: the box was zero-allocated, which is a valid initial value for Box<[u8]>
+        let bytes = unsafe { bytes.assume_init() };
+        Some(bytes)
+    }
+}
+
 /// This type represents an Allocation in the Miri/CTFE core engine.
 ///
 /// Its public API is rather low-level, working directly with allocation offsets and a custom error
@@ -38,10 +72,10 @@ pub use init_mask::{InitChunk, InitChunkIter};
 // hashed. (see the `Hash` impl below for more details), so the impl is not derived.
 #[derive(Clone, Eq, PartialEq, TyEncodable, TyDecodable)]
 #[derive(HashStable)]
-pub struct Allocation<Prov: Provenance = AllocId, Extra = ()> {
+pub struct Allocation<Prov: Provenance = AllocId, Extra = (), Bytes = Box<[u8]>> {
     /// The actual bytes of the allocation.
     /// Note that the bytes of a pointer represent the offset of the pointer.
-    bytes: Box<[u8]>,
+    bytes: Bytes,
     /// Maps from byte addresses to extra provenance data for each pointer.
     /// Only the first byte of a pointer is inserted into the map; i.e.,
     /// every entry in this map applies to `pointer_size` consecutive bytes starting
@@ -220,14 +254,27 @@ impl AllocRange {
 }
 
 // The constructors are all without extra; the extra gets added by a machine hook later.
-impl<Prov: Provenance> Allocation<Prov> {
+impl<Prov: Provenance, Bytes: AllocBytes> Allocation<Prov, (), Bytes> {
+    /// Creates an allocation from an existing `Bytes` value - this is needed for miri FFI support
+    pub fn from_raw_bytes(bytes: Bytes, align: Align, mutability: Mutability) -> Self {
+        let size = Size::from_bytes(bytes.len());
+        Self {
+            bytes,
+            provenance: ProvenanceMap::new(),
+            init_mask: InitMask::new(size, true),
+            align,
+            mutability,
+            extra: (),
+        }
+    }
+
     /// Creates an allocation initialized by the given bytes
     pub fn from_bytes<'a>(
         slice: impl Into<Cow<'a, [u8]>>,
         align: Align,
         mutability: Mutability,
     ) -> Self {
-        let bytes = Box::<[u8]>::from(slice.into());
+        let bytes = Bytes::from_bytes(slice, align);
         let size = Size::from_bytes(bytes.len());
         Self {
             bytes,
@@ -248,7 +295,7 @@ impl<Prov: Provenance> Allocation<Prov> {
     ///
     /// If `panic_on_fail` is true, this will never return `Err`.
     pub fn uninit<'tcx>(size: Size, align: Align, panic_on_fail: bool) -> InterpResult<'tcx, Self> {
-        let bytes = Box::<[u8]>::try_new_zeroed_slice(size.bytes_usize()).map_err(|_| {
+        let bytes = Bytes::zeroed(size, align).ok_or_else(|| {
             // This results in an error that can happen non-deterministically, since the memory
             // available to the compiler can change between runs. Normally queries are always
             // deterministic. However, we can be non-deterministic here because all uses of const
@@ -262,8 +309,7 @@ impl<Prov: Provenance> Allocation<Prov> {
             });
             InterpError::ResourceExhaustion(ResourceExhaustionInfo::MemoryExhausted)
         })?;
-        // SAFETY: the box was zero-allocated, which is a valid initial value for Box<[u8]>
-        let bytes = unsafe { bytes.assume_init() };
+
         Ok(Allocation {
             bytes,
             provenance: ProvenanceMap::new(),
@@ -275,7 +321,7 @@ impl<Prov: Provenance> Allocation<Prov> {
     }
 }
 
-impl Allocation {
+impl<Bytes: AllocBytes> Allocation<AllocId, (), Bytes> {
     /// Adjust allocation from the ones in tcx to a custom Machine instance
     /// with a different Provenance and Extra type.
     pub fn adjust_from_tcx<Prov: Provenance, Extra, Err>(
@@ -283,9 +329,11 @@ impl Allocation {
         cx: &impl HasDataLayout,
         extra: Extra,
         mut adjust_ptr: impl FnMut(Pointer<AllocId>) -> Result<Pointer<Prov>, Err>,
-    ) -> Result<Allocation<Prov, Extra>, Err> {
-        // Compute new pointer provenance, which also adjusts the bytes.
-        let mut bytes = self.bytes;
+    ) -> Result<Allocation<Prov, Extra, Bytes>, Err> {
+        // Compute new pointer provenance, which also adjusts the bytes, and realign the pointer if
+        // necessary.
+        let mut bytes = self.bytes.adjust_to_align(self.align);
+
         let mut new_provenance = Vec::with_capacity(self.provenance.ptrs().len());
         let ptr_size = cx.data_layout().pointer_size.bytes_usize();
         let endian = cx.data_layout().endian;
@@ -311,7 +359,7 @@ impl Allocation {
 }
 
 /// Raw accessors. Provide access to otherwise private bytes.
-impl<Prov: Provenance, Extra> Allocation<Prov, Extra> {
+impl<Prov: Provenance, Extra, Bytes: AllocBytes> Allocation<Prov, Extra, Bytes> {
     pub fn len(&self) -> usize {
         self.bytes.len()
     }
@@ -340,7 +388,11 @@ impl<Prov: Provenance, Extra> Allocation<Prov, Extra> {
 }
 
 /// Byte accessors.
-impl<Prov: Provenance, Extra> Allocation<Prov, Extra> {
+impl<Prov: Provenance, Extra, Bytes: AllocBytes> Allocation<Prov, Extra, Bytes> {
+    pub fn base_addr(&self) -> *const u8 {
+        self.bytes.as_ptr()
+    }
+
     /// This is the entirely abstraction-violating way to just grab the raw bytes without
     /// caring about provenance or initialization.
     ///
@@ -412,7 +464,7 @@ impl<Prov: Provenance, Extra> Allocation<Prov, Extra> {
 }
 
 /// Reading and writing.
-impl<Prov: Provenance, Extra> Allocation<Prov, Extra> {
+impl<Prov: Provenance, Extra, Bytes: AllocBytes> Allocation<Prov, Extra, Bytes> {
     /// Sets the init bit for the given range.
     fn mark_init(&mut self, range: AllocRange, is_init: bool) {
         if range.size.bytes() == 0 {

compiler/rustc_middle/src/mir/interpret/mod.rs

@@ -127,8 +127,8 @@ pub use self::error::{
 pub use self::value::{get_slice_bytes, ConstAlloc, ConstValue, Scalar};
 
 pub use self::allocation::{
-    alloc_range, AllocError, AllocRange, AllocResult, Allocation, ConstAllocation, InitChunk,
-    InitChunkIter,
+    alloc_range, AllocBytes, AllocError, AllocRange, AllocResult, Allocation, ConstAllocation,
+    InitChunk, InitChunkIter,
 };
 
 pub use self::pointer::{Pointer, PointerArithmetic, Provenance};

compiler/rustc_middle/src/mir/pretty.rs

@@ -12,8 +12,8 @@ use rustc_data_structures::fx::FxHashMap;
 use rustc_hir::def_id::DefId;
 use rustc_index::vec::Idx;
 use rustc_middle::mir::interpret::{
-    alloc_range, read_target_uint, AllocId, Allocation, ConstAllocation, ConstValue, GlobalAlloc,
-    Pointer, Provenance,
+    alloc_range, read_target_uint, AllocBytes, AllocId, Allocation, ConstAllocation, ConstValue,
+    GlobalAlloc, Pointer, Provenance,
 };
 use rustc_middle::mir::visit::Visitor;
 use rustc_middle::mir::*;
@@ -787,21 +787,21 @@ pub fn write_allocations<'tcx>(
 /// After the hex dump, an ascii dump follows, replacing all unprintable characters (control
 /// characters or characters whose value is larger than 127) with a `.`
 /// This also prints provenance adequately.
-pub fn display_allocation<'a, 'tcx, Prov: Provenance, Extra>(
+pub fn display_allocation<'a, 'tcx, Prov: Provenance, Extra, Bytes: AllocBytes>(
     tcx: TyCtxt<'tcx>,
-    alloc: &'a Allocation<Prov, Extra>,
-) -> RenderAllocation<'a, 'tcx, Prov, Extra> {
+    alloc: &'a Allocation<Prov, Extra, Bytes>,
+) -> RenderAllocation<'a, 'tcx, Prov, Extra, Bytes> {
     RenderAllocation { tcx, alloc }
 }
 
 #[doc(hidden)]
-pub struct RenderAllocation<'a, 'tcx, Prov: Provenance, Extra> {
+pub struct RenderAllocation<'a, 'tcx, Prov: Provenance, Extra, Bytes: AllocBytes> {
     tcx: TyCtxt<'tcx>,
-    alloc: &'a Allocation<Prov, Extra>,
+    alloc: &'a Allocation<Prov, Extra, Bytes>,
 }
 
-impl<'a, 'tcx, Prov: Provenance, Extra> std::fmt::Display
-    for RenderAllocation<'a, 'tcx, Prov, Extra>
+impl<'a, 'tcx, Prov: Provenance, Extra, Bytes: AllocBytes> std::fmt::Display
+    for RenderAllocation<'a, 'tcx, Prov, Extra, Bytes>
 {
     fn fmt(&self, w: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
         let RenderAllocation { tcx, alloc } = *self;
@@ -845,9 +845,9 @@ fn write_allocation_newline(
 /// The `prefix` argument allows callers to add an arbitrary prefix before each line (even if there
 /// is only one line). Note that your prefix should contain a trailing space as the lines are
 /// printed directly after it.
-fn write_allocation_bytes<'tcx, Prov: Provenance, Extra>(
+fn write_allocation_bytes<'tcx, Prov: Provenance, Extra, Bytes: AllocBytes>(
     tcx: TyCtxt<'tcx>,
-    alloc: &Allocation<Prov, Extra>,
+    alloc: &Allocation<Prov, Extra, Bytes>,
     w: &mut dyn std::fmt::Write,
     prefix: &str,
 ) -> std::fmt::Result {