Rollup merge of rust-lang#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 rust-lang#100467, credit to ```@emarteca``` for the code

compiler/rustc_const_eval/src/interpret/machine.rs

@@ -16,8 +16,8 @@ use rustc_target::spec::abi::Abi as CallAbi;
 use crate::const_eval::CheckAlignment;
 
 use super::{
-    AllocId, AllocRange, Allocation, ConstAllocation, Frame, ImmTy, InterpCx, InterpResult,
-    MemoryKind, OpTy, Operand, PlaceTy, Pointer, Provenance, Scalar, StackPopUnwind,
+    AllocBytes, AllocId, AllocRange, Allocation, ConstAllocation, Frame, ImmTy, InterpCx,
+    InterpResult, MemoryKind, OpTy, Operand, PlaceTy, Pointer, Provenance, Scalar, StackPopUnwind,
 };
 
 /// Data returned by Machine::stack_pop,
@@ -105,10 +105,16 @@ pub trait Machine<'mir, 'tcx>: Sized {
     /// Extra data stored in every allocation.
     type AllocExtra: Debug + Clone + 'static;
 
+    /// Type for the bytes of the allocation.
+    type Bytes: AllocBytes + 'static;
+
     /// Memory's allocation map
     type MemoryMap: AllocMap<
             AllocId,
-            (MemoryKind<Self::MemoryKind>, Allocation<Self::Provenance, Self::AllocExtra>),
+            (
+                MemoryKind<Self::MemoryKind>,
+                Allocation<Self::Provenance, Self::AllocExtra, Self::Bytes>,
+            ),
         > + Default
         + Clone;
 
@@ -338,7 +344,7 @@ pub trait Machine<'mir, 'tcx>: Sized {
         id: AllocId,
         alloc: Cow<'b, Allocation>,
         kind: Option<MemoryKind<Self::MemoryKind>>,
-    ) -> InterpResult<'tcx, Cow<'b, Allocation<Self::Provenance, Self::AllocExtra>>>;
+    ) -> InterpResult<'tcx, Cow<'b, Allocation<Self::Provenance, Self::AllocExtra, Self::Bytes>>>;
 
     fn eval_inline_asm(
         _ecx: &mut InterpCx<'mir, 'tcx, Self>,
@@ -459,6 +465,7 @@ pub macro compile_time_machine(<$mir: lifetime, $tcx: lifetime>) {
 
     type AllocExtra = ();
     type FrameExtra = ();
+    type Bytes = Box<[u8]>;
 
     #[inline(always)]
     fn use_addr_for_alignment_check(_ecx: &InterpCx<$mir, $tcx, Self>) -> bool {

compiler/rustc_const_eval/src/interpret/memory.rs

@@ -21,8 +21,9 @@ use rustc_target::abi::{Align, HasDataLayout, Size};
 use crate::const_eval::CheckAlignment;
 
 use super::{
-    alloc_range, AllocId, AllocMap, AllocRange, Allocation, CheckInAllocMsg, GlobalAlloc, InterpCx,
-    InterpResult, Machine, MayLeak, Pointer, PointerArithmetic, Provenance, Scalar,
+    alloc_range, AllocBytes, AllocId, AllocMap, AllocRange, Allocation, CheckInAllocMsg,
+    GlobalAlloc, InterpCx, InterpResult, Machine, MayLeak, Pointer, PointerArithmetic, Provenance,
+    Scalar,
 };
 
 #[derive(Debug, PartialEq, Copy, Clone)]
@@ -114,16 +115,16 @@ pub struct Memory<'mir, 'tcx, M: Machine<'mir, 'tcx>> {
 /// A reference to some allocation that was already bounds-checked for the given region
 /// and had the on-access machine hooks run.
 #[derive(Copy, Clone)]
-pub struct AllocRef<'a, 'tcx, Prov: Provenance, Extra> {
-    alloc: &'a Allocation<Prov, Extra>,
+pub struct AllocRef<'a, 'tcx, Prov: Provenance, Extra, Bytes: AllocBytes = Box<[u8]>> {
+    alloc: &'a Allocation<Prov, Extra, Bytes>,
     range: AllocRange,
     tcx: TyCtxt<'tcx>,
     alloc_id: AllocId,
 }
 /// A reference to some allocation that was already bounds-checked for the given region
 /// and had the on-access machine hooks run.
-pub struct AllocRefMut<'a, 'tcx, Prov: Provenance, Extra> {
-    alloc: &'a mut Allocation<Prov, Extra>,
+pub struct AllocRefMut<'a, 'tcx, Prov: Provenance, Extra, Bytes: AllocBytes = Box<[u8]>> {
+    alloc: &'a mut Allocation<Prov, Extra, Bytes>,
     range: AllocRange,
     tcx: TyCtxt<'tcx>,
     alloc_id: AllocId,
@@ -483,7 +484,7 @@ impl<'mir, 'tcx: 'mir, M: Machine<'mir, 'tcx>> InterpCx<'mir, 'tcx, M> {
         &self,
         id: AllocId,
         is_write: bool,
-    ) -> InterpResult<'tcx, Cow<'tcx, Allocation<M::Provenance, M::AllocExtra>>> {
+    ) -> InterpResult<'tcx, Cow<'tcx, Allocation<M::Provenance, M::AllocExtra, M::Bytes>>> {
         let (alloc, def_id) = match self.tcx.try_get_global_alloc(id) {
             Some(GlobalAlloc::Memory(mem)) => {
                 // Memory of a constant or promoted or anonymous memory referenced by a static.
@@ -526,14 +527,25 @@ impl<'mir, 'tcx: 'mir, M: Machine<'mir, 'tcx>> InterpCx<'mir, 'tcx, M> {
         )
     }
 
+    /// Get the base address for the bytes in an `Allocation` specified by the
+    /// `AllocID` passed in; error if no such allocation exists.
+    ///
+    /// It is up to the caller to take sufficient care when using this address:
+    /// there could be provenance or uninit memory in there, and other memory
+    /// accesses could invalidate the exposed pointer.
+    pub fn alloc_base_addr(&self, id: AllocId) -> InterpResult<'tcx, *const u8> {
+        let alloc = self.get_alloc_raw(id)?;
+        Ok(alloc.base_addr())
+    }
+
     /// Gives raw access to the `Allocation`, without bounds or alignment checks.
     /// The caller is responsible for calling the access hooks!
     ///
     /// You almost certainly want to use `get_ptr_alloc`/`get_ptr_alloc_mut` instead.
     fn get_alloc_raw(
         &self,
         id: AllocId,
-    ) -> InterpResult<'tcx, &Allocation<M::Provenance, M::AllocExtra>> {
+    ) -> InterpResult<'tcx, &Allocation<M::Provenance, M::AllocExtra, M::Bytes>> {
         // The error type of the inner closure here is somewhat funny. We have two
         // ways of "erroring": An actual error, or because we got a reference from
         // `get_global_alloc` that we can actually use directly without inserting anything anywhere.
@@ -569,7 +581,8 @@ impl<'mir, 'tcx: 'mir, M: Machine<'mir, 'tcx>> InterpCx<'mir, 'tcx, M> {
         ptr: Pointer<Option<M::Provenance>>,
         size: Size,
         align: Align,
-    ) -> InterpResult<'tcx, Option<AllocRef<'a, 'tcx, M::Provenance, M::AllocExtra>>> {
+    ) -> InterpResult<'tcx, Option<AllocRef<'a, 'tcx, M::Provenance, M::AllocExtra, M::Bytes>>>
+    {
         let ptr_and_alloc = self.check_and_deref_ptr(
             ptr,
             size,
@@ -612,7 +625,7 @@ impl<'mir, 'tcx: 'mir, M: Machine<'mir, 'tcx>> InterpCx<'mir, 'tcx, M> {
     fn get_alloc_raw_mut(
         &mut self,
         id: AllocId,
-    ) -> InterpResult<'tcx, (&mut Allocation<M::Provenance, M::AllocExtra>, &mut M)> {
+    ) -> InterpResult<'tcx, (&mut Allocation<M::Provenance, M::AllocExtra, M::Bytes>, &mut M)> {
         // We have "NLL problem case #3" here, which cannot be worked around without loss of
         // efficiency even for the common case where the key is in the map.
         // <https://rust-lang.github.io/rfcs/2094-nll.html#problem-case-3-conditional-control-flow-across-functions>
@@ -641,7 +654,8 @@ impl<'mir, 'tcx: 'mir, M: Machine<'mir, 'tcx>> InterpCx<'mir, 'tcx, M> {
         ptr: Pointer<Option<M::Provenance>>,
         size: Size,
         align: Align,
-    ) -> InterpResult<'tcx, Option<AllocRefMut<'a, 'tcx, M::Provenance, M::AllocExtra>>> {
+    ) -> InterpResult<'tcx, Option<AllocRefMut<'a, 'tcx, M::Provenance, M::AllocExtra, M::Bytes>>>
+    {
         let parts = self.get_ptr_access(ptr, size, align)?;
         if let Some((alloc_id, offset, prov)) = parts {
             let tcx = *self.tcx;
@@ -840,11 +854,11 @@ pub struct DumpAllocs<'a, 'mir, 'tcx, M: Machine<'mir, 'tcx>> {
 impl<'a, 'mir, 'tcx, M: Machine<'mir, 'tcx>> std::fmt::Debug for DumpAllocs<'a, 'mir, 'tcx, M> {
     fn fmt(&self, fmt: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
         // Cannot be a closure because it is generic in `Prov`, `Extra`.
-        fn write_allocation_track_relocs<'tcx, Prov: Provenance, Extra>(
+        fn write_allocation_track_relocs<'tcx, Prov: Provenance, Extra, Bytes: AllocBytes>(
             fmt: &mut std::fmt::Formatter<'_>,
             tcx: TyCtxt<'tcx>,
             allocs_to_print: &mut VecDeque<AllocId>,
-            alloc: &Allocation<Prov, Extra>,
+            alloc: &Allocation<Prov, Extra, Bytes>,
         ) -> std::fmt::Result {
             for alloc_id in alloc.provenance().provenances().filter_map(|prov| prov.get_alloc_id())
             {
@@ -912,7 +926,9 @@ impl<'a, 'mir, 'tcx, M: Machine<'mir, 'tcx>> std::fmt::Debug for DumpAllocs<'a,
 }
 
 /// Reading and writing.
-impl<'tcx, 'a, Prov: Provenance, Extra> AllocRefMut<'a, 'tcx, Prov, Extra> {
+impl<'tcx, 'a, Prov: Provenance, Extra, Bytes: AllocBytes>
+    AllocRefMut<'a, 'tcx, Prov, Extra, Bytes>
+{
     /// `range` is relative to this allocation reference, not the base of the allocation.
     pub fn write_scalar(&mut self, range: AllocRange, val: Scalar<Prov>) -> InterpResult<'tcx> {
         let range = self.range.subrange(range);
@@ -937,7 +953,7 @@ impl<'tcx, 'a, Prov: Provenance, Extra> AllocRefMut<'a, 'tcx, Prov, Extra> {
     }
 }
 
-impl<'tcx, 'a, Prov: Provenance, Extra> AllocRef<'a, 'tcx, Prov, Extra> {
+impl<'tcx, 'a, Prov: Provenance, Extra, Bytes: AllocBytes> AllocRef<'a, 'tcx, Prov, Extra, Bytes> {
     /// `range` is relative to this allocation reference, not the base of the allocation.
     pub fn read_scalar(
         &self,

compiler/rustc_const_eval/src/interpret/place.rs

@@ -353,7 +353,8 @@ where
     pub(super) fn get_place_alloc(
         &self,
         place: &MPlaceTy<'tcx, M::Provenance>,
-    ) -> InterpResult<'tcx, Option<AllocRef<'_, 'tcx, M::Provenance, M::AllocExtra>>> {
+    ) -> InterpResult<'tcx, Option<AllocRef<'_, 'tcx, M::Provenance, M::AllocExtra, M::Bytes>>>
+    {
         assert!(place.layout.is_sized());
         assert!(!place.meta.has_meta());
         let size = place.layout.size;
@@ -364,7 +365,8 @@ where
     pub(super) fn get_place_alloc_mut(
         &mut self,
         place: &MPlaceTy<'tcx, M::Provenance>,
-    ) -> InterpResult<'tcx, Option<AllocRefMut<'_, 'tcx, M::Provenance, M::AllocExtra>>> {
+    ) -> InterpResult<'tcx, Option<AllocRefMut<'_, 'tcx, M::Provenance, M::AllocExtra, M::Bytes>>>
+    {
         assert!(place.layout.is_sized());
         assert!(!place.meta.has_meta());
         let size = place.layout.size;

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(),
@@ -275,17 +321,19 @@ 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>(
         self,
         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};