Re: [PATCH v7 16/31] rust: ptr: add const_align_up()

["David Rheinsberg" <david@readahead.eu>]

Hi

On Fri, Mar 20, 2026, at 9:44 AM, Alice Ryhl wrote:
> On Fri, Mar 20, 2026 at 9:38 AM David Rheinsberg <david@readahead.eu> wrote:
>>
>> Hi
>>
>> On Tue, Mar 17, 2026, at 11:53 PM, John Hubbard wrote:
>> > Add const_align_up() to kernel::ptr as the const-compatible equivalent
>> > of Alignable::align_up().
>> >
>> > Suggested-by: Danilo Krummrich <dakr@kernel.org>
>> > Suggested-by: Gary Guo <gary@garyguo.net>
>> > Suggested-by: Miguel Ojeda <ojeda@kernel.org>
>> > Signed-off-by: John Hubbard <jhubbard@nvidia.com>
>> > ---
>> >  rust/kernel/ptr.rs | 24 ++++++++++++++++++++++++
>> >  1 file changed, 24 insertions(+)
>> >
>> > diff --git a/rust/kernel/ptr.rs b/rust/kernel/ptr.rs
>> > index bdc2d79ff669..7e99f129543b 100644
>> > --- a/rust/kernel/ptr.rs
>> > +++ b/rust/kernel/ptr.rs
>> > @@ -253,3 +253,27 @@ fn size(p: *const Self) -> usize {
>> >          p.len() * size_of::<T>()
>> >      }
>> >  }
>> > +
>> > +/// Aligns `value` up to `align`.
>> > +///
>> > +/// This is the const-compatible equivalent of [`Alignable::align_up`].
>> > +///
>> > +/// Returns [`None`] on overflow.
>> > +///
>> > +/// # Examples
>> > +///
>> > +/// ```
>> > +/// use kernel::ptr::{const_align_up, Alignment};
>> > +/// use kernel::sizes::SZ_4K;
>> > +///
>> > +/// assert_eq!(const_align_up(0x4f, Alignment::new::<16>()), Some(0x50));
>> > +/// assert_eq!(const_align_up(0x40, Alignment::new::<16>()), Some(0x40));
>> > +/// assert_eq!(const_align_up(1, Alignment::new::<SZ_4K>()), Some(SZ_4K));
>> > +/// ```
>> > +#[inline(always)]
>> > +pub const fn const_align_up(value: usize, align: Alignment) -> Option<usize> {
>> > +    match value.checked_add(align.as_usize() - 1) {
>> > +        Some(v) => Some(v & align.mask()),
>> > +        None => None,
>> > +    }
>>
>> This would return `None` if the value is already aligned, but the addition overflows `usize`, right? For instance, this would incorrectly return `None`: `const_align_up(usize::MAX - 1, 2.into())`
>
> No, in that case it computes `usize::MAX-1 + (2-1)` which is just
> usize::MAX and does not overflow. After applying the mask, it returns
> `usize::MAX-1` as the return value.

My bad! If alignment is below `usize::MAX / 2` then this always works. Once alignment gets bigger, the function fails, though. The following assertion does not hold:

assert_eq!(const_align_up(usize::MAX - 1, (usize::MAX - 1).into()), Some(usize::MAX - 1));

Doesn't matter too much, I guess, but with `checked_next_multiple_of()` this assertion holds.

>> FYI, `core` provides `usize::checked_next_multiple_of()` ((const-)stable since 1.73). So an alternative would be:
>>
>> pub const fn const_align_up(value: usize, align: Alignment) -> Option<usize> {
>>     value.checked_next_multiple_of(align.as_usize())
>> }
>
> That would return value+align when value is already aligned, which is wrong.

You sure? (emphasis mine:)

"Calculates the smallest value greater than or **EQUAL TO** self that is a multiple of rhs."

assert_eq!(16_u64.next_multiple_of(8), 16);

Thanks
David