diff mbox series

[v6,5/6] rust: str: add radix prefixed integer parsing functions

Message ID 20250211-module-params-v3-v6-5-24b297ddc43d@kernel.org (mailing list archive)
State New
Headers show
Series rust: extend `module!` macro with integer parameter support | expand

Checks

Context Check Description
mcgrof/vmtest-modules-next-PR fail PR summary
mcgrof/vmtest-modules-next-VM_Test-1 success Logs for Run CI tests
mcgrof/vmtest-modules-next-VM_Test-3 fail Logs for cleanup / Archive results and cleanup
mcgrof/vmtest-modules-next-VM_Test-0 success Logs for Run CI tests
mcgrof/vmtest-modules-next-VM_Test-4 fail Logs for setup / Setup kdevops environment
mcgrof/vmtest-modules-next-VM_Test-2 fail Logs for cleanup / Archive results and cleanup
mcgrof/vmtest-modules-next-VM_Test-5 fail Logs for setup / Setup kdevops environment

Commit Message

Andreas Hindborg Feb. 11, 2025, 3:57 p.m. UTC
Add the trait `ParseInt` for parsing string representations of integers
where the string representations are optionally prefixed by a radix
specifier. Implement the trait for the primitive integer types.

Signed-off-by: Andreas Hindborg <a.hindborg@kernel.org>
---
 rust/kernel/str.rs | 111 +++++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 111 insertions(+)

Comments

Gary Guo Feb. 11, 2025, 4:43 p.m. UTC | #1
On Tue, 11 Feb 2025 16:57:39 +0100
Andreas Hindborg <a.hindborg@kernel.org> wrote:

> Add the trait `ParseInt` for parsing string representations of integers
> where the string representations are optionally prefixed by a radix
> specifier. Implement the trait for the primitive integer types.
> 
> Signed-off-by: Andreas Hindborg <a.hindborg@kernel.org>
> ---
>  rust/kernel/str.rs | 111 +++++++++++++++++++++++++++++++++++++++++++++++++++++
>  1 file changed, 111 insertions(+)
> 
> diff --git a/rust/kernel/str.rs b/rust/kernel/str.rs
> index c102adac32757..192cd0ff5974f 100644
> --- a/rust/kernel/str.rs
> +++ b/rust/kernel/str.rs
> @@ -945,3 +945,114 @@ fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
>  macro_rules! fmt {
>      ($($f:tt)*) => ( core::format_args!($($f)*) )
>  }
> +
> +pub mod parse_int {
> +    //! Integer parsing functions for parsing signed and unsigned integers
> +    //! potentially prefixed with `0x`, `0o`, or `0b`.
> +
> +    use crate::alloc::flags;
> +    use crate::prelude::*;
> +    use crate::str::BStr;
> +    use core::ops::Deref;
> +
> +    /// Trait that allows parsing a [`&BStr`] to an integer with a radix.
> +    ///
> +    /// [`&BStr`]: kernel::str::BStr
> +    // This is required because the `from_str_radix` function on the primitive
> +    // integer types is not part of any trait.
> +    pub trait FromStrRadix: Sized {
> +        /// Parse `src` to `Self` using radix `radix`.
> +        fn from_str_radix(src: &BStr, radix: u32) -> Result<Self, crate::error::Error>;
> +    }
> +
> +    /// Extract the radix from an integer literal optionally prefixed with
> +    /// one of `0x`, `0X`, `0o`, `0O`, `0b`, `0B`, `0`.
> +    fn strip_radix(src: &BStr) -> (u32, &BStr) {
> +        match src.deref() {
> +            [b'0', b'x' | b'X', ..] => (16, &src[2..]),

This can be written as

	[b'0', b'x' | b'X', rest @ ..] => (16, rest),

to avoid manual indexing. Same for o and b below.

> +            [b'0', b'o' | b'O', ..] => (8, &src[2..]),
> +            [b'0', b'b' | b'B', ..] => (2, &src[2..]),
> +            [b'0', ..] => (8, src),

Perhaps add a comment saying that this isn't using `src[1..]` so `0`
can be parsed.

> +            _ => (10, src),
> +        }
> +    }
> +
> +    /// Trait for parsing string representations of integers.
> +    ///
> +    /// Strings beginning with `0x`, `0o`, or `0b` are parsed as hex, octal, or
> +    /// binary respectively. Strings beginning with `0` otherwise are parsed as
> +    /// octal. Anything else is parsed as decimal. A leading `+` or `-` is also
> +    /// permitted. Any string parsed by [`kstrtol()`] or [`kstrtoul()`] will be
> +    /// successfully parsed.
> +    ///
> +    /// [`kstrtol()`]: https://www.kernel.org/doc/html/latest/core-api/kernel-api.html#c.kstrtol
> +    /// [`kstrtoul()`]: https://www.kernel.org/doc/html/latest/core-api/kernel-api.html#c.kstrtoul
> +    ///
> +    /// # Example
> +    /// ```
> +    /// use kernel::str::parse_int::ParseInt;
> +    /// use kernel::b_str;
> +    ///
> +    /// assert_eq!(Ok(0), u8::from_str(b_str!("0")));
> +    ///
> +    /// assert_eq!(Ok(0xa2u8), u8::from_str(b_str!("0xa2")));
> +    /// assert_eq!(Ok(-0xa2i32), i32::from_str(b_str!("-0xa2")));
> +    ///
> +    /// assert_eq!(Ok(-0o57i8), i8::from_str(b_str!("-0o57")));
> +    /// assert_eq!(Ok(0o57i8), i8::from_str(b_str!("057")));
> +    ///
> +    /// assert_eq!(Ok(0b1001i16), i16::from_str(b_str!("0b1001")));
> +    /// assert_eq!(Ok(-0b1001i16), i16::from_str(b_str!("-0b1001")));
> +    ///
> +    /// assert_eq!(Ok(127), i8::from_str(b_str!("127")));
> +    /// assert!(i8::from_str(b_str!("128")).is_err());
> +    /// assert_eq!(Ok(-128), i8::from_str(b_str!("-128")));
> +    /// assert!(i8::from_str(b_str!("-129")).is_err());
> +    /// assert_eq!(Ok(255), u8::from_str(b_str!("255")));
> +    /// assert!(u8::from_str(b_str!("256")).is_err());
> +    /// ```
> +    pub trait ParseInt: FromStrRadix {
> +        /// Parse a string according to the description in [`Self`].
> +        fn from_str(src: &BStr) -> Result<Self> {
> +            match src.iter().next() {
> +                None => Err(EINVAL),
> +                Some(sign @ b'-') | Some(sign @ b'+') => {
> +                    let (radix, digits) = strip_radix(BStr::from_bytes(&src[1..]));
> +                    let mut n_digits: KVec<u8> =
> +                        KVec::with_capacity(digits.len() + 1, flags::GFP_KERNEL)?;
> +                    n_digits.push(*sign, flags::GFP_KERNEL)?;
> +                    n_digits.extend_from_slice(digits, flags::GFP_KERNEL)?;

I think my comment from a previous series saying that this shouldn't
need allocation is not addressed.

> +                    Self::from_str_radix(BStr::from_bytes(&n_digits), radix).map_err(|_| EINVAL)
> +                }
> +                Some(_) => {
> +                    let (radix, digits) = strip_radix(src);
> +                    Self::from_str_radix(digits, radix).map_err(|_| EINVAL)
> +                }
> +            }
> +        }
> +    }
> +
> +    macro_rules! impl_parse_int {
> +        ($ty:ty) => {
> +            impl FromStrRadix for $ty {
> +                fn from_str_radix(src: &BStr, radix: u32) -> Result<Self, crate::error::Error> {
> +                    <$ty>::from_str_radix(core::str::from_utf8(src).map_err(|_| EINVAL)?, radix)
> +                        .map_err(|_| EINVAL)
> +                }
> +            }
> +
> +            impl ParseInt for $ty {}
> +        };
> +    }
> +
> +    impl_parse_int!(i8);
> +    impl_parse_int!(u8);
> +    impl_parse_int!(i16);
> +    impl_parse_int!(u16);
> +    impl_parse_int!(i32);
> +    impl_parse_int!(u32);
> +    impl_parse_int!(i64);
> +    impl_parse_int!(u64);
> +    impl_parse_int!(isize);
> +    impl_parse_int!(usize);
> +}
>
Andreas Hindborg Feb. 11, 2025, 8:13 p.m. UTC | #2
"Gary Guo" <gary@garyguo.net> writes:

> On Tue, 11 Feb 2025 16:57:39 +0100
> Andreas Hindborg <a.hindborg@kernel.org> wrote:
>
>> Add the trait `ParseInt` for parsing string representations of integers
>> where the string representations are optionally prefixed by a radix
>> specifier. Implement the trait for the primitive integer types.
>>
>> Signed-off-by: Andreas Hindborg <a.hindborg@kernel.org>
>> ---
>>  rust/kernel/str.rs | 111 +++++++++++++++++++++++++++++++++++++++++++++++++++++
>>  1 file changed, 111 insertions(+)
>>
>> diff --git a/rust/kernel/str.rs b/rust/kernel/str.rs
>> index c102adac32757..192cd0ff5974f 100644
>> --- a/rust/kernel/str.rs
>> +++ b/rust/kernel/str.rs
>> @@ -945,3 +945,114 @@ fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
>>  macro_rules! fmt {
>>      ($($f:tt)*) => ( core::format_args!($($f)*) )
>>  }
>> +
>> +pub mod parse_int {
>> +    //! Integer parsing functions for parsing signed and unsigned integers
>> +    //! potentially prefixed with `0x`, `0o`, or `0b`.
>> +
>> +    use crate::alloc::flags;
>> +    use crate::prelude::*;
>> +    use crate::str::BStr;
>> +    use core::ops::Deref;
>> +
>> +    /// Trait that allows parsing a [`&BStr`] to an integer with a radix.
>> +    ///
>> +    /// [`&BStr`]: kernel::str::BStr
>> +    // This is required because the `from_str_radix` function on the primitive
>> +    // integer types is not part of any trait.
>> +    pub trait FromStrRadix: Sized {
>> +        /// Parse `src` to `Self` using radix `radix`.
>> +        fn from_str_radix(src: &BStr, radix: u32) -> Result<Self, crate::error::Error>;
>> +    }
>> +
>> +    /// Extract the radix from an integer literal optionally prefixed with
>> +    /// one of `0x`, `0X`, `0o`, `0O`, `0b`, `0B`, `0`.
>> +    fn strip_radix(src: &BStr) -> (u32, &BStr) {
>> +        match src.deref() {
>> +            [b'0', b'x' | b'X', ..] => (16, &src[2..]),
>
> This can be written as
>
> 	[b'0', b'x' | b'X', rest @ ..] => (16, rest),
>
> to avoid manual indexing. Same for o and b below.

error[E0308]: mismatched types
   --> /home/aeh/src/linux-rust/module-params/rust/kernel/str.rs:972:52
    |
972 |             [b'0', b'x' | b'X', rest @ ..] => (16, rest),
    |                                                    ^^^^ expected `&BStr`, found `&[u8]`
    |
    = note: expected reference `&BStr`
               found reference `&[u8]`

But I guess I could use the new AsRef impl. Or is it more idiomatic to
implement `From<&[u8]> for &BStr` and go with `rest.into()`?

>
>> +            [b'0', b'o' | b'O', ..] => (8, &src[2..]),
>> +            [b'0', b'b' | b'B', ..] => (2, &src[2..]),
>> +            [b'0', ..] => (8, src),
>
> Perhaps add a comment saying that this isn't using `src[1..]` so `0`
> can be parsed.

Good idea.

>
>> +            _ => (10, src),
>> +        }
>> +    }
>> +
>> +    /// Trait for parsing string representations of integers.
>> +    ///
>> +    /// Strings beginning with `0x`, `0o`, or `0b` are parsed as hex, octal, or
>> +    /// binary respectively. Strings beginning with `0` otherwise are parsed as
>> +    /// octal. Anything else is parsed as decimal. A leading `+` or `-` is also
>> +    /// permitted. Any string parsed by [`kstrtol()`] or [`kstrtoul()`] will be
>> +    /// successfully parsed.
>> +    ///
>> +    /// [`kstrtol()`]: https://www.kernel.org/doc/html/latest/core-api/kernel-api.html#c.kstrtol
>> +    /// [`kstrtoul()`]: https://www.kernel.org/doc/html/latest/core-api/kernel-api.html#c.kstrtoul
>> +    ///
>> +    /// # Example
>> +    /// ```
>> +    /// use kernel::str::parse_int::ParseInt;
>> +    /// use kernel::b_str;
>> +    ///
>> +    /// assert_eq!(Ok(0), u8::from_str(b_str!("0")));
>> +    ///
>> +    /// assert_eq!(Ok(0xa2u8), u8::from_str(b_str!("0xa2")));
>> +    /// assert_eq!(Ok(-0xa2i32), i32::from_str(b_str!("-0xa2")));
>> +    ///
>> +    /// assert_eq!(Ok(-0o57i8), i8::from_str(b_str!("-0o57")));
>> +    /// assert_eq!(Ok(0o57i8), i8::from_str(b_str!("057")));
>> +    ///
>> +    /// assert_eq!(Ok(0b1001i16), i16::from_str(b_str!("0b1001")));
>> +    /// assert_eq!(Ok(-0b1001i16), i16::from_str(b_str!("-0b1001")));
>> +    ///
>> +    /// assert_eq!(Ok(127), i8::from_str(b_str!("127")));
>> +    /// assert!(i8::from_str(b_str!("128")).is_err());
>> +    /// assert_eq!(Ok(-128), i8::from_str(b_str!("-128")));
>> +    /// assert!(i8::from_str(b_str!("-129")).is_err());
>> +    /// assert_eq!(Ok(255), u8::from_str(b_str!("255")));
>> +    /// assert!(u8::from_str(b_str!("256")).is_err());
>> +    /// ```
>> +    pub trait ParseInt: FromStrRadix {
>> +        /// Parse a string according to the description in [`Self`].
>> +        fn from_str(src: &BStr) -> Result<Self> {
>> +            match src.iter().next() {
>> +                None => Err(EINVAL),
>> +                Some(sign @ b'-') | Some(sign @ b'+') => {
>> +                    let (radix, digits) = strip_radix(BStr::from_bytes(&src[1..]));
>> +                    let mut n_digits: KVec<u8> =
>> +                        KVec::with_capacity(digits.len() + 1, flags::GFP_KERNEL)?;
>> +                    n_digits.push(*sign, flags::GFP_KERNEL)?;
>> +                    n_digits.extend_from_slice(digits, flags::GFP_KERNEL)?;
>
> I think my comment from a previous series saying that this shouldn't
> need allocation is not addressed.

Thanks for noticing. This is the discussion from v4:

>> I don't think we should allocate for parsing. This can trivially be a
>> non-allocating. Just check that the next byte is an ASCII digit (reject
>> if so, in case people give multiple signs), and then from_str_radix and
>> return as is or use `checked_neg`.
>
>The issue with that approach is that 2s complement signed integer types
>of width `b` can assume values from -2^(b-1) to (2^(b-1))-1. We would
>reject the value -2^(b-1) when trying to parse as 2^(b-1).
>
>We could parse into an unsigned type, but it gets kind of clunky.
>
>Another option is to stop relying on `from_str_radix` from core and roll
>our own that takes sign as a separate function argument.

What is your take on that?


Best regards,
Andreas Hindborg
Gary Guo Feb. 12, 2025, 9:04 a.m. UTC | #3
On Tue, 11 Feb 2025 21:13:10 +0100
Andreas Hindborg <a.hindborg@kernel.org> wrote:

> "Gary Guo" <gary@garyguo.net> writes:
> 
> > On Tue, 11 Feb 2025 16:57:39 +0100
> > Andreas Hindborg <a.hindborg@kernel.org> wrote:
> >  
> >> Add the trait `ParseInt` for parsing string representations of integers
> >> where the string representations are optionally prefixed by a radix
> >> specifier. Implement the trait for the primitive integer types.
> >>
> >> Signed-off-by: Andreas Hindborg <a.hindborg@kernel.org>
> >> ---
> >>  rust/kernel/str.rs | 111 +++++++++++++++++++++++++++++++++++++++++++++++++++++
> >>  1 file changed, 111 insertions(+)
> >>
> >> diff --git a/rust/kernel/str.rs b/rust/kernel/str.rs
> >> index c102adac32757..192cd0ff5974f 100644
> >> --- a/rust/kernel/str.rs
> >> +++ b/rust/kernel/str.rs
> >> @@ -945,3 +945,114 @@ fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
> >>  macro_rules! fmt {
> >>      ($($f:tt)*) => ( core::format_args!($($f)*) )
> >>  }
> >> +
> >> +pub mod parse_int {
> >> +    //! Integer parsing functions for parsing signed and unsigned integers
> >> +    //! potentially prefixed with `0x`, `0o`, or `0b`.
> >> +
> >> +    use crate::alloc::flags;
> >> +    use crate::prelude::*;
> >> +    use crate::str::BStr;
> >> +    use core::ops::Deref;
> >> +
> >> +    /// Trait that allows parsing a [`&BStr`] to an integer with a radix.
> >> +    ///
> >> +    /// [`&BStr`]: kernel::str::BStr
> >> +    // This is required because the `from_str_radix` function on the primitive
> >> +    // integer types is not part of any trait.
> >> +    pub trait FromStrRadix: Sized {
> >> +        /// Parse `src` to `Self` using radix `radix`.
> >> +        fn from_str_radix(src: &BStr, radix: u32) -> Result<Self, crate::error::Error>;
> >> +    }
> >> +
> >> +    /// Extract the radix from an integer literal optionally prefixed with
> >> +    /// one of `0x`, `0X`, `0o`, `0O`, `0b`, `0B`, `0`.
> >> +    fn strip_radix(src: &BStr) -> (u32, &BStr) {
> >> +        match src.deref() {
> >> +            [b'0', b'x' | b'X', ..] => (16, &src[2..]),  
> >
> > This can be written as
> >
> > 	[b'0', b'x' | b'X', rest @ ..] => (16, rest),
> >
> > to avoid manual indexing. Same for o and b below.  
> 
> error[E0308]: mismatched types
>    --> /home/aeh/src/linux-rust/module-params/rust/kernel/str.rs:972:52  
>     |
> 972 |             [b'0', b'x' | b'X', rest @ ..] => (16, rest),
>     |                                                    ^^^^ expected `&BStr`, found `&[u8]`
>     |
>     = note: expected reference `&BStr`
>                found reference `&[u8]`
> 
> But I guess I could use the new AsRef impl. Or is it more idiomatic to
> implement `From<&[u8]> for &BStr` and go with `rest.into()`?

Ah, alright, I missed that this function is operating on BStr instead
of slice. Keeping the current form is fine then.

> 
> >  
> >> +            [b'0', b'o' | b'O', ..] => (8, &src[2..]),
> >> +            [b'0', b'b' | b'B', ..] => (2, &src[2..]),
> >> +            [b'0', ..] => (8, src),  
> >
> > Perhaps add a comment saying that this isn't using `src[1..]` so `0`
> > can be parsed.  
> 
> Good idea.
> 
> >  
> >> +            _ => (10, src),
> >> +        }
> >> +    }

> >> +    pub trait ParseInt: FromStrRadix {
> >> +        /// Parse a string according to the description in [`Self`].
> >> +        fn from_str(src: &BStr) -> Result<Self> {
> >> +            match src.iter().next() {
> >> +                None => Err(EINVAL),
> >> +                Some(sign @ b'-') | Some(sign @ b'+') => {
> >> +                    let (radix, digits) = strip_radix(BStr::from_bytes(&src[1..]));
> >> +                    let mut n_digits: KVec<u8> =
> >> +                        KVec::with_capacity(digits.len() + 1, flags::GFP_KERNEL)?;
> >> +                    n_digits.push(*sign, flags::GFP_KERNEL)?;
> >> +                    n_digits.extend_from_slice(digits, flags::GFP_KERNEL)?;  
> >
> > I think my comment from a previous series saying that this shouldn't
> > need allocation is not addressed.  
> 
> Thanks for noticing. This is the discussion from v4:
> 
> >> I don't think we should allocate for parsing. This can trivially be a
> >> non-allocating. Just check that the next byte is an ASCII digit (reject
> >> if so, in case people give multiple signs), and then from_str_radix and
> >> return as is or use `checked_neg`.  
> >
> >The issue with that approach is that 2s complement signed integer types
> >of width `b` can assume values from -2^(b-1) to (2^(b-1))-1. We would
> >reject the value -2^(b-1) when trying to parse as 2^(b-1).
> >
> >We could parse into an unsigned type, but it gets kind of clunky.

I would say either that or just call into kstrto* family.

Best,
Gary

> >
> >Another option is to stop relying on `from_str_radix` from core and roll
> >our own that takes sign as a separate function argument.  
> 
> What is your take on that?
> 
> 
> Best regards,
> Andreas Hindborg
> 
>
Andreas Hindborg Feb. 18, 2025, 11 a.m. UTC | #4
"Gary Guo" <gary@garyguo.net> writes:

> On Tue, 11 Feb 2025 21:13:10 +0100
> Andreas Hindborg <a.hindborg@kernel.org> wrote:
>
>> "Gary Guo" <gary@garyguo.net> writes:
>>
>> > On Tue, 11 Feb 2025 16:57:39 +0100
>> > Andreas Hindborg <a.hindborg@kernel.org> wrote:
>> >
>> >> Add the trait `ParseInt` for parsing string representations of integers
>> >> where the string representations are optionally prefixed by a radix
>> >> specifier. Implement the trait for the primitive integer types.
>> >>
>> >> Signed-off-by: Andreas Hindborg <a.hindborg@kernel.org>
>> >> ---
>> >>  rust/kernel/str.rs | 111 +++++++++++++++++++++++++++++++++++++++++++++++++++++
>> >>  1 file changed, 111 insertions(+)
>> >>
>> >> diff --git a/rust/kernel/str.rs b/rust/kernel/str.rs
>> >> index c102adac32757..192cd0ff5974f 100644
>> >> --- a/rust/kernel/str.rs
>> >> +++ b/rust/kernel/str.rs
>> >> @@ -945,3 +945,114 @@ fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
>> >>  macro_rules! fmt {
>> >>      ($($f:tt)*) => ( core::format_args!($($f)*) )
>> >>  }
>> >> +
>> >> +pub mod parse_int {
>> >> +    //! Integer parsing functions for parsing signed and unsigned integers
>> >> +    //! potentially prefixed with `0x`, `0o`, or `0b`.
>> >> +
>> >> +    use crate::alloc::flags;
>> >> +    use crate::prelude::*;
>> >> +    use crate::str::BStr;
>> >> +    use core::ops::Deref;
>> >> +
>> >> +    /// Trait that allows parsing a [`&BStr`] to an integer with a radix.
>> >> +    ///
>> >> +    /// [`&BStr`]: kernel::str::BStr
>> >> +    // This is required because the `from_str_radix` function on the primitive
>> >> +    // integer types is not part of any trait.
>> >> +    pub trait FromStrRadix: Sized {
>> >> +        /// Parse `src` to `Self` using radix `radix`.
>> >> +        fn from_str_radix(src: &BStr, radix: u32) -> Result<Self, crate::error::Error>;
>> >> +    }
>> >> +
>> >> +    /// Extract the radix from an integer literal optionally prefixed with
>> >> +    /// one of `0x`, `0X`, `0o`, `0O`, `0b`, `0B`, `0`.
>> >> +    fn strip_radix(src: &BStr) -> (u32, &BStr) {
>> >> +        match src.deref() {
>> >> +            [b'0', b'x' | b'X', ..] => (16, &src[2..]),
>> >
>> > This can be written as
>> >
>> > 	[b'0', b'x' | b'X', rest @ ..] => (16, rest),
>> >
>> > to avoid manual indexing. Same for o and b below.
>>
>> error[E0308]: mismatched types
>>    --> /home/aeh/src/linux-rust/module-params/rust/kernel/str.rs:972:52
>>     |
>> 972 |             [b'0', b'x' | b'X', rest @ ..] => (16, rest),
>>     |                                                    ^^^^ expected `&BStr`, found `&[u8]`
>>     |
>>     = note: expected reference `&BStr`
>>                found reference `&[u8]`
>>
>> But I guess I could use the new AsRef impl. Or is it more idiomatic to
>> implement `From<&[u8]> for &BStr` and go with `rest.into()`?
>
> Ah, alright, I missed that this function is operating on BStr instead
> of slice. Keeping the current form is fine then.
>
>>
>> >
>> >> +            [b'0', b'o' | b'O', ..] => (8, &src[2..]),
>> >> +            [b'0', b'b' | b'B', ..] => (2, &src[2..]),
>> >> +            [b'0', ..] => (8, src),
>> >
>> > Perhaps add a comment saying that this isn't using `src[1..]` so `0`
>> > can be parsed.
>>
>> Good idea.
>>
>> >
>> >> +            _ => (10, src),
>> >> +        }
>> >> +    }
>
>> >> +    pub trait ParseInt: FromStrRadix {
>> >> +        /// Parse a string according to the description in [`Self`].
>> >> +        fn from_str(src: &BStr) -> Result<Self> {
>> >> +            match src.iter().next() {
>> >> +                None => Err(EINVAL),
>> >> +                Some(sign @ b'-') | Some(sign @ b'+') => {
>> >> +                    let (radix, digits) = strip_radix(BStr::from_bytes(&src[1..]));
>> >> +                    let mut n_digits: KVec<u8> =
>> >> +                        KVec::with_capacity(digits.len() + 1, flags::GFP_KERNEL)?;
>> >> +                    n_digits.push(*sign, flags::GFP_KERNEL)?;
>> >> +                    n_digits.extend_from_slice(digits, flags::GFP_KERNEL)?;
>> >
>> > I think my comment from a previous series saying that this shouldn't
>> > need allocation is not addressed.
>>
>> Thanks for noticing. This is the discussion from v4:
>>
>> >> I don't think we should allocate for parsing. This can trivially be a
>> >> non-allocating. Just check that the next byte is an ASCII digit (reject
>> >> if so, in case people give multiple signs), and then from_str_radix and
>> >> return as is or use `checked_neg`.
>> >
>> >The issue with that approach is that 2s complement signed integer types
>> >of width `b` can assume values from -2^(b-1) to (2^(b-1))-1. We would
>> >reject the value -2^(b-1) when trying to parse as 2^(b-1).
>> >
>> >We could parse into an unsigned type, but it gets kind of clunky.
>
> I would say either that or just call into kstrto* family.

Right. I'll rather parse into i128 than call into that.


Best regards,
Andreas Hindborg
diff mbox series

Patch

diff --git a/rust/kernel/str.rs b/rust/kernel/str.rs
index c102adac32757..192cd0ff5974f 100644
--- a/rust/kernel/str.rs
+++ b/rust/kernel/str.rs
@@ -945,3 +945,114 @@  fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
 macro_rules! fmt {
     ($($f:tt)*) => ( core::format_args!($($f)*) )
 }
+
+pub mod parse_int {
+    //! Integer parsing functions for parsing signed and unsigned integers
+    //! potentially prefixed with `0x`, `0o`, or `0b`.
+
+    use crate::alloc::flags;
+    use crate::prelude::*;
+    use crate::str::BStr;
+    use core::ops::Deref;
+
+    /// Trait that allows parsing a [`&BStr`] to an integer with a radix.
+    ///
+    /// [`&BStr`]: kernel::str::BStr
+    // This is required because the `from_str_radix` function on the primitive
+    // integer types is not part of any trait.
+    pub trait FromStrRadix: Sized {
+        /// Parse `src` to `Self` using radix `radix`.
+        fn from_str_radix(src: &BStr, radix: u32) -> Result<Self, crate::error::Error>;
+    }
+
+    /// Extract the radix from an integer literal optionally prefixed with
+    /// one of `0x`, `0X`, `0o`, `0O`, `0b`, `0B`, `0`.
+    fn strip_radix(src: &BStr) -> (u32, &BStr) {
+        match src.deref() {
+            [b'0', b'x' | b'X', ..] => (16, &src[2..]),
+            [b'0', b'o' | b'O', ..] => (8, &src[2..]),
+            [b'0', b'b' | b'B', ..] => (2, &src[2..]),
+            [b'0', ..] => (8, src),
+            _ => (10, src),
+        }
+    }
+
+    /// Trait for parsing string representations of integers.
+    ///
+    /// Strings beginning with `0x`, `0o`, or `0b` are parsed as hex, octal, or
+    /// binary respectively. Strings beginning with `0` otherwise are parsed as
+    /// octal. Anything else is parsed as decimal. A leading `+` or `-` is also
+    /// permitted. Any string parsed by [`kstrtol()`] or [`kstrtoul()`] will be
+    /// successfully parsed.
+    ///
+    /// [`kstrtol()`]: https://www.kernel.org/doc/html/latest/core-api/kernel-api.html#c.kstrtol
+    /// [`kstrtoul()`]: https://www.kernel.org/doc/html/latest/core-api/kernel-api.html#c.kstrtoul
+    ///
+    /// # Example
+    /// ```
+    /// use kernel::str::parse_int::ParseInt;
+    /// use kernel::b_str;
+    ///
+    /// assert_eq!(Ok(0), u8::from_str(b_str!("0")));
+    ///
+    /// assert_eq!(Ok(0xa2u8), u8::from_str(b_str!("0xa2")));
+    /// assert_eq!(Ok(-0xa2i32), i32::from_str(b_str!("-0xa2")));
+    ///
+    /// assert_eq!(Ok(-0o57i8), i8::from_str(b_str!("-0o57")));
+    /// assert_eq!(Ok(0o57i8), i8::from_str(b_str!("057")));
+    ///
+    /// assert_eq!(Ok(0b1001i16), i16::from_str(b_str!("0b1001")));
+    /// assert_eq!(Ok(-0b1001i16), i16::from_str(b_str!("-0b1001")));
+    ///
+    /// assert_eq!(Ok(127), i8::from_str(b_str!("127")));
+    /// assert!(i8::from_str(b_str!("128")).is_err());
+    /// assert_eq!(Ok(-128), i8::from_str(b_str!("-128")));
+    /// assert!(i8::from_str(b_str!("-129")).is_err());
+    /// assert_eq!(Ok(255), u8::from_str(b_str!("255")));
+    /// assert!(u8::from_str(b_str!("256")).is_err());
+    /// ```
+    pub trait ParseInt: FromStrRadix {
+        /// Parse a string according to the description in [`Self`].
+        fn from_str(src: &BStr) -> Result<Self> {
+            match src.iter().next() {
+                None => Err(EINVAL),
+                Some(sign @ b'-') | Some(sign @ b'+') => {
+                    let (radix, digits) = strip_radix(BStr::from_bytes(&src[1..]));
+                    let mut n_digits: KVec<u8> =
+                        KVec::with_capacity(digits.len() + 1, flags::GFP_KERNEL)?;
+                    n_digits.push(*sign, flags::GFP_KERNEL)?;
+                    n_digits.extend_from_slice(digits, flags::GFP_KERNEL)?;
+                    Self::from_str_radix(BStr::from_bytes(&n_digits), radix).map_err(|_| EINVAL)
+                }
+                Some(_) => {
+                    let (radix, digits) = strip_radix(src);
+                    Self::from_str_radix(digits, radix).map_err(|_| EINVAL)
+                }
+            }
+        }
+    }
+
+    macro_rules! impl_parse_int {
+        ($ty:ty) => {
+            impl FromStrRadix for $ty {
+                fn from_str_radix(src: &BStr, radix: u32) -> Result<Self, crate::error::Error> {
+                    <$ty>::from_str_radix(core::str::from_utf8(src).map_err(|_| EINVAL)?, radix)
+                        .map_err(|_| EINVAL)
+                }
+            }
+
+            impl ParseInt for $ty {}
+        };
+    }
+
+    impl_parse_int!(i8);
+    impl_parse_int!(u8);
+    impl_parse_int!(i16);
+    impl_parse_int!(u16);
+    impl_parse_int!(i32);
+    impl_parse_int!(u32);
+    impl_parse_int!(i64);
+    impl_parse_int!(u64);
+    impl_parse_int!(isize);
+    impl_parse_int!(usize);
+}