Re: [PATCH v3 05/35] sched: add cpumask_find_and_set() and use it in __mm_cid_get()

[Mathieu Desnoyers]

On 2023-12-11 21:27, Yury Norov wrote:
> __mm_cid_get() uses __mm_cid_try_get() helper to atomically acquire a
> bit in mm cid mask. Now that we have atomic find_and_set_bit(), we can
> easily extend it to cpumasks and use in the scheduler code.
>
> cpumask_find_and_set() considers cid mask as a volatile region of memory,
> as it actually is in this case. So, if it's changed while search is in
> progress, KCSAN wouldn't fire warning on it.
>
> CC: Mathieu Desnoyers <mathieu.desnoyers@xxxxxxxxxxxx>
> CC: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
> Signed-off-by: Yury Norov <yury.norov@xxxxxxxxx>

Reviewed-by: Mathieu Desnoyers <mathieu.desnoyers@xxxxxxxxxxxx>

> ---
>   include/linux/cpumask.h | 12 ++++++++++++
>   kernel/sched/sched.h    | 14 +++++---------
>   2 files changed, 17 insertions(+), 9 deletions(-)
>
> diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h
> index cfb545841a2c..c2acced8be4e 100644
> --- a/include/linux/cpumask.h
> +++ b/include/linux/cpumask.h
> @@ -271,6 +271,18 @@ unsigned int cpumask_next_and(int n, const struct cpumask *src1p,
>   		small_cpumask_bits, n + 1);
>   }
>   
> +/**
> + * cpumask_find_and_set - find the first unset cpu in a cpumask and
> + *			  set it atomically
> + * @srcp: the cpumask pointer
> + *
> + * Return: >= nr_cpu_ids if nothing is found.
> + */
> +static inline unsigned int cpumask_find_and_set(volatile struct cpumask *srcp)
> +{
> +	return find_and_set_bit(cpumask_bits(srcp), small_cpumask_bits);
> +}
> +
>   /**
>    * for_each_cpu - iterate over every cpu in a mask
>    * @cpu: the (optionally unsigned) integer iterator
> diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
> index 2e5a95486a42..2ce9112de89b 100644
> --- a/kernel/sched/sched.h
> +++ b/kernel/sched/sched.h
> @@ -3347,23 +3347,19 @@ static inline void mm_cid_put(struct mm_struct *mm)
>   
>   static inline int __mm_cid_try_get(struct mm_struct *mm)
>   {
> -	struct cpumask *cpumask;
> -	int cid;
> +	struct cpumask *cpumask = mm_cidmask(mm);
> +	int cid = nr_cpu_ids;
>   
> -	cpumask = mm_cidmask(mm);
>   	/*
>   	 * Retry finding first zero bit if the mask is temporarily
>   	 * filled. This only happens during concurrent remote-clear
>   	 * which owns a cid without holding a rq lock.
>   	 */
> -	for (;;) {
> -		cid = cpumask_first_zero(cpumask);
> -		if (cid < nr_cpu_ids)
> -			break;
> +	while (cid >= nr_cpu_ids) {
> +		cid = cpumask_find_and_set(cpumask);
>   		cpu_relax();
>   	}
> -	if (cpumask_test_and_set_cpu(cid, cpumask))
> -		return -1;
> +
>   	return cid;
>   }
>   

--
Mathieu Desnoyers
EfficiOS Inc.
https://www.efficios.com