On Wed, Oct 22, 2025 at 02:55:28PM +0200, Thomas Gleixner wrote:
> CID management OR's two cpumasks and then calculates the weight on the
> result. That's inefficient as that has to walk the same stuff twice. As
> this is done with runqueue lock held, there is a real benefit of speeding
> this up. Depending on the system this results in 10-20% less cycles spent
> with runqueue lock held for a 4K cpumask.
>
> Provide cpumask_or_and_calc_weight() and the corresponding bitmap functions
> which return the weight of the OR result right away.
>
> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
> Cc: Yury Norov <yury.norov@gmail.com>
> ---
> V2: Rename and use the BITMAP_WEIGHT() macro - Yury
> ---
> include/linux/bitmap.h | 16 ++++++++++++++++
> include/linux/cpumask.h | 16 ++++++++++++++++
> lib/bitmap.c | 6 ++++++
> 3 files changed, 38 insertions(+)
>
> --- a/include/linux/bitmap.h
> +++ b/include/linux/bitmap.h
> @@ -45,6 +45,8 @@ struct device;
> * bitmap_copy(dst, src, nbits) *dst = *src
> * bitmap_and(dst, src1, src2, nbits) *dst = *src1 & *src2
> * bitmap_or(dst, src1, src2, nbits) *dst = *src1 | *src2
> + * bitmap_or_and_calc_weight(dst, src1, src2, nbits)
> + * *dst = *src1 | *src2. Returns Hamming Weight of dst
> * bitmap_xor(dst, src1, src2, nbits) *dst = *src1 ^ *src2
> * bitmap_andnot(dst, src1, src2, nbits) *dst = *src1 & ~(*src2)
> * bitmap_complement(dst, src, nbits) *dst = ~(*src)
> @@ -165,6 +167,8 @@ bool __bitmap_and(unsigned long *dst, co
> const unsigned long *bitmap2, unsigned int nbits);
> void __bitmap_or(unsigned long *dst, const unsigned long *bitmap1,
> const unsigned long *bitmap2, unsigned int nbits);
> +unsigned int __bitmap_or_and_calc_weight(unsigned long *dst, const unsigned long *bitmap1,
> + const unsigned long *bitmap2, unsigned int nbits);
> void __bitmap_xor(unsigned long *dst, const unsigned long *bitmap1,
> const unsigned long *bitmap2, unsigned int nbits);
> bool __bitmap_andnot(unsigned long *dst, const unsigned long *bitmap1,
> @@ -338,6 +342,18 @@ void bitmap_or(unsigned long *dst, const
> }
>
> static __always_inline
> +unsigned int bitmap_or_and_calc_weight(unsigned long *dst, const unsigned long *src1,
> + const unsigned long *src2, unsigned int nbits)
> +{
> + if (small_const_nbits(nbits)) {
> + *dst = *src1 | *src2;
> + return hweight_long(*dst & BITMAP_LAST_WORD_MASK(nbits));
> + } else {
> + return __bitmap_or_and_calc_weight(dst, src1, src2, nbits);
> + }
> +}
> +
> +static __always_inline
> void bitmap_xor(unsigned long *dst, const unsigned long *src1,
> const unsigned long *src2, unsigned int nbits)
> {
> --- a/include/linux/cpumask.h
> +++ b/include/linux/cpumask.h
> @@ -729,6 +729,22 @@ void cpumask_or(struct cpumask *dstp, co
> }
>
> /**
> + * cpumask_or_and_calc_weight - *dstp = *src1p | *src2p and return the weight of the result
> + * @dstp: the cpumask result
> + * @src1p: the first input
> + * @src2p: the second input
> + *
> + * Return: The number of bits set in the resulting cpumask @dstp
> + */
> +static __always_inline
> +unsigned int cpumask_or_and_calc_weight(struct cpumask *dstp, const struct cpumask *src1p,
> + const struct cpumask *src2p)
> +{
> + return bitmap_or_and_calc_weight(cpumask_bits(dstp), cpumask_bits(src1p),
> + cpumask_bits(src2p), small_cpumask_bits);
> +}
> +
> +/**
> * cpumask_xor - *dstp = *src1p ^ *src2p
> * @dstp: the cpumask result
> * @src1p: the first input
> --- a/lib/bitmap.c
> +++ b/lib/bitmap.c
> @@ -355,6 +355,12 @@ unsigned int __bitmap_weight_andnot(cons
> }
> EXPORT_SYMBOL(__bitmap_weight_andnot);
>
> +unsigned int __bitmap_or_and_calc_weight(unsigned long *dst, const unsigned long *bitmap1,
> + const unsigned long *bitmap2, unsigned int bits)
> +{
> + return BITMAP_WEIGHT(({dst[idx] = bitmap1[idx] | bitmap2[idx]; dst[idx]; }), bits);
Nice!
> +}
> +
Reviewed-by: Yury Norov (NVIDIA) <yury.norov@gmail.com>
Maybe bitmap_weighted_or()?