make const `align_offset` useful

4 files changed, 152 insertions, 28 deletions

diff --git a/compiler/rustc_const_eval/src/const_eval/machine.rs b/compiler/rustc_const_eval/src/const_eval/machine.rs
index 66d6014946c..97d168ceb01 100644
--- a/compiler/rustc_const_eval/src/const_eval/machine.rs
+++ b/compiler/rustc_const_eval/src/const_eval/machine.rs
@@ -1,8 +1,11 @@
 use rustc_hir::def::DefKind;
 use rustc_middle::mir;
+use rustc_middle::mir::interpret::PointerArithmetic;
+use rustc_middle::ty::layout::FnAbiOf;
 use rustc_middle::ty::{self, Ty, TyCtxt};
 use std::borrow::Borrow;
 use std::hash::Hash;
+use std::ops::ControlFlow;
 
 use rustc_data_structures::fx::FxIndexMap;
 use rustc_data_structures::fx::IndexEntry;
@@ -17,8 +20,8 @@ use rustc_target::abi::{Align, Size};
 use rustc_target::spec::abi::Abi as CallAbi;
 
 use crate::interpret::{
-    self, compile_time_machine, AllocId, ConstAllocation, Frame, ImmTy, InterpCx, InterpResult,
-    OpTy, PlaceTy, Pointer, Scalar, StackPopUnwind,
+    self, compile_time_machine, AllocId, ConstAllocation, FnVal, Frame, ImmTy, InterpCx,
+    InterpResult, OpTy, PlaceTy, Pointer, Scalar, StackPopUnwind,
 };
 
 use super::error::*;
@@ -145,15 +148,19 @@ impl interpret::MayLeak for ! {
 }
 
 impl<'mir, 'tcx: 'mir> CompileTimeEvalContext<'mir, 'tcx> {
-    /// "Intercept" a function call to a panic-related function
-    /// because we have something special to do for it.
-    /// If this returns successfully (`Ok`), the function should just be evaluated normally.
+    /// "Intercept" a function call, because we have something special to do for it.
+    /// All `#[rustc_do_not_const_check]` functions should be hooked here.
+    /// If this returns `Some` function, which may be `instance` or a different function with
+    /// compatible arguments, then evaluation should continue with that function.
+    /// If this returns `None`, the function call has been handled and the function has returned.
     fn hook_special_const_fn(
         &mut self,
         instance: ty::Instance<'tcx>,
+        _abi: CallAbi,
         args: &[OpTy<'tcx>],
+        dest: &PlaceTy<'tcx>,
+        ret: Option<mir::BasicBlock>,
     ) -> InterpResult<'tcx, Option<ty::Instance<'tcx>>> {
-        // All `#[rustc_do_not_const_check]` functions should be hooked here.
         let def_id = instance.def_id();
 
         if Some(def_id) == self.tcx.lang_items().panic_display()
@@ -173,20 +180,91 @@ impl<'mir, 'tcx: 'mir> CompileTimeEvalContext<'mir, 'tcx> {
             return Err(ConstEvalErrKind::Panic { msg, file, line, col }.into());
         } else if Some(def_id) == self.tcx.lang_items().panic_fmt() {
             // For panic_fmt, call const_panic_fmt instead.
-            if let Some(const_panic_fmt) = self.tcx.lang_items().const_panic_fmt() {
-                return Ok(Some(
-                    ty::Instance::resolve(
-                        *self.tcx,
-                        ty::ParamEnv::reveal_all(),
-                        const_panic_fmt,
-                        self.tcx.intern_substs(&[]),
-                    )
-                    .unwrap()
-                    .unwrap(),
-                ));
+            let Some(const_def_id) = self.tcx.lang_items().const_panic_fmt() else {
+                bug!("`const_panic_fmt` must be defined to call `panic_fmt` in const eval")
+            };
+            let new_instance = ty::Instance::resolve(
+                *self.tcx,
+                ty::ParamEnv::reveal_all(),
+                const_def_id,
+                instance.substs,
+            )
+            .unwrap()
+            .unwrap();
+
+            return Ok(Some(new_instance));
+        } else if Some(def_id) == self.tcx.lang_items().align_offset_fn() {
+            // For align_offset, we replace the function call if the pointer has no address.
+            match self.align_offset(instance, args, dest, ret)? {
+                ControlFlow::Continue(()) => return Ok(Some(instance)),
+                ControlFlow::Break(()) => return Ok(None),
+            }
+        }
+        Ok(Some(instance))
+    }
+
+    /// `align_offset(ptr, target_align)` needs special handling in const eval, because the pointer
+    /// may not have an address.
+    ///
+    /// If `ptr` does have a known address, then we return `CONTINUE` and the function call should
+    /// proceed as normal.
+    ///
+    /// If `ptr` doesn't have an address, but its underlying allocation's alignment is at most
+    /// `target_align`, then we call the function again with an dummy address relative to the
+    /// allocation.
+    ///
+    /// If `ptr` doesn't have an address and `target_align` is stricter than the underlying
+    /// allocation's alignment, then we return `usize::MAX` immediately.
+    fn align_offset(
+        &mut self,
+        instance: ty::Instance<'tcx>,
+        args: &[OpTy<'tcx>],
+        dest: &PlaceTy<'tcx>,
+        ret: Option<mir::BasicBlock>,
+    ) -> InterpResult<'tcx, ControlFlow<()>> {
+        assert_eq!(args.len(), 2);
+
+        let ptr = self.read_pointer(&args[0])?;
+        let target_align = self.read_scalar(&args[1])?.to_machine_usize(self)?;
+
+        if !target_align.is_power_of_two() {
+            throw_ub_format!("`align_offset` called with non-power-of-two align: {}", target_align);
+        }
+
+        match self.ptr_try_get_alloc_id(ptr) {
+            Ok((alloc_id, offset, _extra)) => {
+                let (_size, alloc_align, _kind) = self.get_alloc_info(alloc_id);
+
+                if target_align <= alloc_align.bytes() {
+                    // Extract the address relative to the allocation base that is definitely
+                    // sufficiently aligned and call `align_offset` again.
+                    let addr = ImmTy::from_uint(offset.bytes(), args[0].layout).into();
+                    let align = ImmTy::from_uint(target_align, args[1].layout).into();
+
+                    let fn_abi = self.fn_abi_of_instance(instance, ty::List::empty())?;
+                    self.eval_fn_call(
+                        FnVal::Instance(instance),
+                        (CallAbi::Rust, fn_abi),
+                        &[addr, align],
+                        false,
+                        dest,
+                        ret,
+                        StackPopUnwind::NotAllowed,
+                    )?;
+                    Ok(ControlFlow::BREAK)
+                } else {
+                    // Not alignable in const, return `usize::MAX`.
+                    let usize_max = Scalar::from_machine_usize(self.machine_usize_max(), self);
+                    self.write_scalar(usize_max, dest)?;
+                    self.return_to_block(ret)?;
+                    Ok(ControlFlow::BREAK)
+                }
+            }
+            Err(_addr) => {
+                // The pointer has an address, continue with function call.
+                Ok(ControlFlow::CONTINUE)
             }
         }
-        Ok(None)
     }
 
     /// See documentation on the `ptr_guaranteed_cmp` intrinsic.
@@ -269,8 +347,8 @@ impl<'mir, 'tcx> interpret::Machine<'mir, 'tcx> for CompileTimeInterpreter<'mir,
         instance: ty::Instance<'tcx>,
         _abi: CallAbi,
         args: &[OpTy<'tcx>],
-        _dest: &PlaceTy<'tcx>,
-        _ret: Option<mir::BasicBlock>,
+        dest: &PlaceTy<'tcx>,
+        ret: Option<mir::BasicBlock>,
         _unwind: StackPopUnwind, // unwinding is not supported in consts
     ) -> InterpResult<'tcx, Option<(&'mir mir::Body<'tcx>, ty::Instance<'tcx>)>> {
         debug!("find_mir_or_eval_fn: {:?}", instance);
@@ -289,7 +367,11 @@ impl<'mir, 'tcx> interpret::Machine<'mir, 'tcx> for CompileTimeInterpreter<'mir,
                 }
             }
 
-            if let Some(new_instance) = ecx.hook_special_const_fn(instance, args)? {
+            let Some(new_instance) = ecx.hook_special_const_fn(instance, _abi, args, dest, ret)? else {
+                return Ok(None);
+            };
+
+            if new_instance != instance {
                 // We call another const fn instead.
                 // However, we return the *original* instance to make backtraces work out
                 // (and we hope this does not confuse the FnAbi checks too much).
@@ -298,13 +380,14 @@ impl<'mir, 'tcx> interpret::Machine<'mir, 'tcx> for CompileTimeInterpreter<'mir,
                     new_instance,
                     _abi,
                     args,
-                    _dest,
-                    _ret,
+                    dest,
+                    ret,
                     _unwind,
                 )?
                 .map(|(body, _instance)| (body, instance)));
             }
         }
+
         // This is a const fn. Call it.
         Ok(Some((ecx.load_mir(instance.def, None)?, instance)))
     }
diff --git a/library/core/src/ptr/const_ptr.rs b/library/core/src/ptr/const_ptr.rs
index bff270b787e..f0cdc3d8399 100644
--- a/library/core/src/ptr/const_ptr.rs
+++ b/library/core/src/ptr/const_ptr.rs
@@ -1322,6 +1322,21 @@ impl<T: ?Sized> *const T {
     /// ```
     #[stable(feature = "align_offset", since = "1.36.0")]
     #[rustc_const_unstable(feature = "const_align_offset", issue = "90962")]
+    #[cfg(not(bootstrap))]
+    pub const fn align_offset(self, align: usize) -> usize
+    where
+        T: Sized,
+    {
+        assert!(align.is_power_of_two(), "align_offset: align is not a power-of-two");
+
+        // SAFETY: `align` has been checked to be a power of 2 above
+        unsafe { align_offset(self, align) }
+    }
+
+    #[stable(feature = "align_offset", since = "1.36.0")]
+    #[rustc_const_unstable(feature = "const_align_offset", issue = "90962")]
+    #[allow(missing_docs)]
+    #[cfg(bootstrap)]
     pub const fn align_offset(self, align: usize) -> usize
     where
         T: Sized,
diff --git a/library/core/src/ptr/mod.rs b/library/core/src/ptr/mod.rs
index e0ddb3154de..1ebd9dca098 100644
--- a/library/core/src/ptr/mod.rs
+++ b/library/core/src/ptr/mod.rs
@@ -1574,10 +1574,14 @@ pub unsafe fn write_volatile<T>(dst: *mut T, src: T) {
 
 /// Align pointer `p`.
 ///
-/// Calculate offset (in terms of elements of `stride` stride) that has to be applied
+/// Calculate offset (in terms of elements of `size_of::<T>()` stride) that has to be applied
 /// to pointer `p` so that pointer `p` would get aligned to `a`.
 ///
-/// Note: This implementation has been carefully tailored to not panic. It is UB for this to panic.
+/// # Safety
+/// `a` must be a power of two.
+///
+/// # Notes
+/// This implementation has been carefully tailored to not panic. It is UB for this to panic.
 /// The only real change that can be made here is change of `INV_TABLE_MOD_16` and associated
 /// constants.
 ///
@@ -1586,8 +1590,10 @@ pub unsafe fn write_volatile<T>(dst: *mut T, src: T) {
 /// than trying to adapt this to accommodate that change.
 ///
 /// Any questions go to @nagisa.
+// #[cfg(not(bootstrap))] -- Calling this function in a const context from the bootstrap
+// compiler will always cause an error.
 #[lang = "align_offset"]
-pub(crate) unsafe fn align_offset<T: Sized>(p: *const T, a: usize) -> usize {
+pub(crate) const unsafe fn align_offset<T: Sized>(p: *const T, a: usize) -> usize {
     // FIXME(#75598): Direct use of these intrinsics improves codegen significantly at opt-level <=
     // 1, where the method versions of these operations are not inlined.
     use intrinsics::{
@@ -1604,7 +1610,7 @@ pub(crate) unsafe fn align_offset<T: Sized>(p: *const T, a: usize) -> usize {
     ///
     /// Implementation of this function shall not panic. Ever.
     #[inline]
-    unsafe fn mod_inv(x: usize, m: usize) -> usize {
+    const unsafe fn mod_inv(x: usize, m: usize) -> usize {
         /// Multiplicative modular inverse table modulo 2⁴ = 16.
         ///
         /// Note, that this table does not contain values where inverse does not exist (i.e., for
@@ -1646,8 +1652,13 @@ pub(crate) unsafe fn align_offset<T: Sized>(p: *const T, a: usize) -> usize {
         inverse & m_minus_one
     }
 
-    let addr = p.addr();
     let stride = mem::size_of::<T>();
+
+    // SAFETY: At runtime transmuting a pointer to `usize` is always safe, because they have the
+    // same layout. During const eval we hook this function to ensure that the pointer always has
+    // an address (only the standard library can do this).
+    let addr = unsafe { mem::transmute(p) };
+
     // SAFETY: `a` is a power-of-two, therefore non-zero.
     let a_minus_one = unsafe { unchecked_sub(a, 1) };
 
diff --git a/library/core/src/ptr/mut_ptr.rs b/library/core/src/ptr/mut_ptr.rs
index 8f4809ec4ba..eb1a6a07c6b 100644
--- a/library/core/src/ptr/mut_ptr.rs
+++ b/library/core/src/ptr/mut_ptr.rs
@@ -1590,6 +1590,21 @@ impl<T: ?Sized> *mut T {
     /// ```
     #[stable(feature = "align_offset", since = "1.36.0")]
     #[rustc_const_unstable(feature = "const_align_offset", issue = "90962")]
+    #[cfg(not(bootstrap))]
+    pub const fn align_offset(self, align: usize) -> usize
+    where
+        T: Sized,
+    {
+        assert!(align.is_power_of_two(), "align_offset: align is not a power-of-two");
+
+        // SAFETY: `align` has been checked to be a power of 2 above
+        unsafe { align_offset(self, align) }
+    }
+
+    #[stable(feature = "align_offset", since = "1.36.0")]
+    #[rustc_const_unstable(feature = "const_align_offset", issue = "90962")]
+    #[allow(missing_docs)]
+    #[cfg(bootstrap)]
     pub const fn align_offset(self, align: usize) -> usize
     where
         T: Sized,