linux-kernel - Re: [patch 07/19] cpumask: Introduce cpumask_or

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <aO_c3lTmvJyzsOdE@yury>
Date: Wed, 15 Oct 2025 13:41:50 -0400
From: Yury Norov <yury.norov@...il.com>
To: Thomas Gleixner <tglx@...utronix.de>
Cc: LKML <linux-kernel@...r.kernel.org>,
	Peter Zijlstra <peterz@...radead.org>,
	Gabriele Monaco <gmonaco@...hat.com>,
	Mathieu Desnoyers <mathieu.desnoyers@...icios.com>,
	Michael Jeanson <mjeanson@...icios.com>,
	Jens Axboe <axboe@...nel.dk>,
	"Paul E. McKenney" <paulmck@...nel.org>,
	"Gautham R. Shenoy" <gautham.shenoy@....com>,
	Florian Weimer <fweimer@...hat.com>,
	Tim Chen <tim.c.chen@...el.com>,
	TCMalloc Team <tcmalloc-eng@...gle.com>
Subject: Re: [patch 07/19] cpumask: Introduce cpumask_or_weight()

Hi Tomas,

On Wed, Oct 15, 2025 at 07:29:36PM +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.
> 
> Provide cpumask_or_weight() and the corresponding bitmap functions which
> return the weight of the OR result right away.
> 
> Signed-off-by: Thomas Gleixner <tglx@...utronix.de>
> Cc: Yury Norov <yury.norov@...il.com>
> ---
>  include/linux/bitmap.h  |   15 +++++++++++++++
>  include/linux/cpumask.h |   16 ++++++++++++++++
>  lib/bitmap.c            |   17 +++++++++++++++++
>  3 files changed, 48 insertions(+)
> 
> --- a/include/linux/bitmap.h
> +++ b/include/linux/bitmap.h
> @@ -45,6 +45,7 @@ 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_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 +166,8 @@ 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_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 +341,18 @@ void bitmap_or(unsigned long *dst, const
>  }
>  
>  static __always_inline
> +unsigned int bitmap_or_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_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_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_weight(struct cpumask *dstp, const struct cpumask *src1p,
> +			       const struct cpumask *src2p)
> +{
> +	return bitmap_or_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
> @@ -253,6 +253,23 @@ void __bitmap_or(unsigned long *dst, con
>  }
>  EXPORT_SYMBOL(__bitmap_or);
>  
> +unsigned int __bitmap_or_weight(unsigned long *dst, const unsigned long *bitmap1,
> +				const unsigned long *bitmap2, unsigned int bits)
> +{
> +	unsigned int k, w = 0;
> +
> +	for (k = 0; k < bits / BITS_PER_LONG; k++) {
> +		dst[k] = bitmap1[k] | bitmap2[k];
> +		w += hweight_long(dst[k]);
> +	}
> +
> +	if (bits % BITS_PER_LONG) {
> +		dst[k] = bitmap1[k] | bitmap2[k];
> +		w += hweight_long(dst[k] & BITMAP_LAST_WORD_MASK(bits));
> +	}
> +	return w;
> +}

We've got bitmap_weight_and() and bitmap_weight_andnot() already. Can
you align naming with the existing scheme: bitmap_weight_or().

Also, for outline implementation, can you employ the BITMAP_WEIGHT()
macro?

Thanks,
Yury