// Copyright 2025 Jonas Kruckenberg
//
// Licensed under the Apache License, Version 2.0, <LICENSE-APACHE or
// http://apache.org/licenses/LICENSE-2.0> or the MIT license <LICENSE-MIT or
// http://opensource.org/licenses/MIT>, at your option. This file may not be
// copied, modified, or distributed except according to those terms.

use core::ops::{Deref, DerefMut};

/// `CachePadded` wraps an inner type `T` applying architecture-specific padding to ensure the type
/// takes up exactly one cache line on the target architecture. This avoids [false sharing].
///
/// The cache padding rules are copied from crossbeam-utils/src/cache_padded.rs
///
/// Starting from Intel's Sandy Bridge, spatial prefetcher is now pulling pairs of 64-byte cache
/// lines at a time, so we have to align to 128 bytes rather than 64.
///
/// Sources:
/// - <https://www.intel.com/content/dam/www/public/us/en/documents/manuals/64-ia-32-architectures-optimization-manual.pdf>
/// - <https://github.com/facebook/folly/blob/1b5288e6eea6df074758f877c849b6e73bbb9fbb/folly/lang/Align.h#L107>
///
/// ARM's big.LITTLE architecture has asymmetric cores and "big" cores have 128-byte cache line size.
///
/// Sources:
/// - <https://www.mono-project.com/news/2016/09/12/arm64-icache/>
///
/// powerpc64 has 128-byte cache line size.
///
/// Sources:
/// - <https://github.com/golang/go/blob/3dd58676054223962cd915bb0934d1f9f489d4d2/src/internal/cpu/cpu_ppc64x.go#L9>
///
/// [false sharing]: <https://en.wikipedia.org/wiki/False_sharing>
#[cfg_attr(
    any(
        target_arch = "x86_64",
        target_arch = "aarch64",
        target_arch = "powerpc64",
    ),
    repr(align(128))
)]
///
/// arm, mips, mips64, sparc, and hexagon have 32-byte cache line size.
///
/// Sources:
/// - <https://github.com/golang/go/blob/3dd58676054223962cd915bb0934d1f9f489d4d2/src/internal/cpu/cpu_arm.go#L7>
/// - <https://github.com/golang/go/blob/3dd58676054223962cd915bb0934d1f9f489d4d2/src/internal/cpu/cpu_mips.go#L7>
/// - <https://github.com/golang/go/blob/3dd58676054223962cd915bb0934d1f9f489d4d2/src/internal/cpu/cpu_mipsle.go#L7>
/// - <https://github.com/golang/go/blob/3dd58676054223962cd915bb0934d1f9f489d4d2/src/internal/cpu/cpu_mips64x.go#L9>
/// - <https://github.com/torvalds/linux/blob/3516bd729358a2a9b090c1905bd2a3fa926e24c6/arch/sparc/include/asm/cache.h#L17>
/// - <https://github.com/torvalds/linux/blob/3516bd729358a2a9b090c1905bd2a3fa926e24c6/arch/hexagon/include/asm/cache.h#L12>
#[cfg_attr(
    any(
        target_arch = "arm",
        target_arch = "mips",
        target_arch = "mips64",
        target_arch = "sparc",
        target_arch = "hexagon",
    ),
    repr(align(32))
)]
///
/// m68k has 16-byte cache line size.
///
/// Sources:
/// - <https://github.com/torvalds/linux/blob/3516bd729358a2a9b090c1905bd2a3fa926e24c6/arch/m68k/include/asm/cache.h#L9>
#[cfg_attr(target_arch = "m68k", repr(align(16)))]
///
/// s390x has 256-byte cache line size.
///
/// Sources:
/// - <https://github.com/golang/go/blob/3dd58676054223962cd915bb0934d1f9f489d4d2/src/internal/cpu/cpu_s390x.go#L7>
/// - <https://github.com/torvalds/linux/blob/3516bd729358a2a9b090c1905bd2a3fa926e24c6/arch/s390/include/asm/cache.h#L13>
#[cfg_attr(target_arch = "s390x", repr(align(256)))]
///
/// x86, riscv, wasm, and sparc64 have 64-byte cache line size.
///
/// Sources:
/// - <https://github.com/golang/go/blob/dda2991c2ea0c5914714469c4defc2562a907230/src/internal/cpu/cpu_x86.go#L9>
/// - <https://github.com/golang/go/blob/3dd58676054223962cd915bb0934d1f9f489d4d2/src/internal/cpu/cpu_wasm.go#L7>
/// - <https://github.com/torvalds/linux/blob/3516bd729358a2a9b090c1905bd2a3fa926e24c6/arch/sparc/include/asm/cache.h#L19>
/// - <https://github.com/torvalds/linux/blob/3516bd729358a2a9b090c1905bd2a3fa926e24c6/arch/riscv/include/asm/cache.h#L10>
///
/// All others are assumed to have 64-byte cache line size.
#[cfg_attr(
    not(any(
        target_arch = "x86_64",
        target_arch = "aarch64",
        target_arch = "powerpc64",
        target_arch = "arm",
        target_arch = "mips",
        target_arch = "mips64",
        target_arch = "sparc",
        target_arch = "hexagon",
        target_arch = "m68k",
        target_arch = "s390x",
    )),
    repr(align(64))
)]
#[derive(Debug, Default, PartialEq, Eq, PartialOrd, Ord, Hash)]
pub struct CachePadded<T>(pub T);

impl<T> Deref for CachePadded<T> {
    type Target = T;

    fn deref(&self) -> &Self::Target {
        &self.0
    }
}

impl<T> DerefMut for CachePadded<T> {
    fn deref_mut(&mut self) -> &mut Self::Target {
        &mut self.0
    }
}

impl<T> From<T> for CachePadded<T> {
    fn from(value: T) -> Self {
        Self(value)
    }
}