Re: [PATCH v2 3/4] sched/isolation: Add HK_TYPE_WQ to isolcpus=domain

[Peter Zijlstra]

+ Frederic; who actually does most of this code

On Thu, Oct 13, 2022 at 03:40:28PM -0300, Leonardo Bras wrote:
> Housekeeping code keeps multiple cpumasks in order to keep track of which
> cpus can perform given housekeeping category.
> 
> Every time the HK_TYPE_WQ cpumask is checked before queueing work at a cpu
> WQ it also happens to check for HK_TYPE_DOMAIN. So It can be assumed that
> the Domain isolation also ends up isolating work queues.
> 
> Delegating current HK_TYPE_DOMAIN's work queue isolation to HK_TYPE_WQ
> makes it simpler to check if a cpu can run a task into an work queue, since
> code just need to go through a single HK_TYPE_* cpumask.
> 
> Make isolcpus=domain aggregate both HK_TYPE_DOMAIN and HK_TYPE_WQ, and
> remove a lot of cpumask_and calls.
> 
> Also, remove a unnecessary '|=' at housekeeping_isolcpus_setup() since we
> are sure that 'flags == 0' here.
> 
> Signed-off-by: Leonardo Bras <leobras@xxxxxxxxxx>

I've long maintained that having all these separate masks is daft;
Frederic do we really need that?

> ---
>  drivers/pci/pci-driver.c | 13 +------------
>  kernel/sched/isolation.c |  4 ++--
>  kernel/workqueue.c       |  1 -
>  net/core/net-sysfs.c     |  1 -
>  4 files changed, 3 insertions(+), 16 deletions(-)
> 
> diff --git a/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c
> index 107d77f3c8467..550bef2504b8d 100644
> --- a/drivers/pci/pci-driver.c
> +++ b/drivers/pci/pci-driver.c
> @@ -371,19 +371,8 @@ static int pci_call_probe(struct pci_driver *drv, struct pci_dev *dev,
>  	    pci_physfn_is_probed(dev)) {
>  		cpu = nr_cpu_ids;
>  	} else {
> -		cpumask_var_t wq_domain_mask;
> -
> -		if (!zalloc_cpumask_var(&wq_domain_mask, GFP_KERNEL)) {
> -			error = -ENOMEM;
> -			goto out;
> -		}
> -		cpumask_and(wq_domain_mask,
> -			    housekeeping_cpumask(HK_TYPE_WQ),
> -			    housekeeping_cpumask(HK_TYPE_DOMAIN));
> -
>  		cpu = cpumask_any_and(cpumask_of_node(node),
> -				      wq_domain_mask);
> -		free_cpumask_var(wq_domain_mask);
> +				      housekeeping_cpumask(HK_TYPE_WQ));
>  	}
>  
>  	if (cpu < nr_cpu_ids)
> diff --git a/kernel/sched/isolation.c b/kernel/sched/isolation.c
> index 373d42c707bc5..ced4b78564810 100644
> --- a/kernel/sched/isolation.c
> +++ b/kernel/sched/isolation.c
> @@ -204,7 +204,7 @@ static int __init housekeeping_isolcpus_setup(char *str)
>  
>  		if (!strncmp(str, "domain,", 7)) {
>  			str += 7;
> -			flags |= HK_FLAG_DOMAIN;
> +			flags |= HK_FLAG_DOMAIN | HK_FLAG_WQ;
>  			continue;
>  		}
>  
> @@ -234,7 +234,7 @@ static int __init housekeeping_isolcpus_setup(char *str)
>  
>  	/* Default behaviour for isolcpus without flags */
>  	if (!flags)
> -		flags |= HK_FLAG_DOMAIN;
> +		flags = HK_FLAG_DOMAIN | HK_FLAG_WQ;
>  
>  	return housekeeping_setup(str, flags);
>  }
> diff --git a/kernel/workqueue.c b/kernel/workqueue.c
> index 7cd5f5e7e0a1b..b557daa571f17 100644
> --- a/kernel/workqueue.c
> +++ b/kernel/workqueue.c
> @@ -6004,7 +6004,6 @@ void __init workqueue_init_early(void)
>  
>  	BUG_ON(!alloc_cpumask_var(&wq_unbound_cpumask, GFP_KERNEL));
>  	cpumask_copy(wq_unbound_cpumask, housekeeping_cpumask(HK_TYPE_WQ));
> -	cpumask_and(wq_unbound_cpumask, wq_unbound_cpumask, housekeeping_cpumask(HK_TYPE_DOMAIN));
>  
>  	pwq_cache = KMEM_CACHE(pool_workqueue, SLAB_PANIC);
>  
> diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
> index 8409d41405dfe..7b6fb62a118ab 100644
> --- a/net/core/net-sysfs.c
> +++ b/net/core/net-sysfs.c
> @@ -852,7 +852,6 @@ static ssize_t store_rps_map(struct netdev_rx_queue *queue,
>  	}
>  
>  	if (!cpumask_empty(mask)) {
> -		cpumask_and(mask, mask, housekeeping_cpumask(HK_TYPE_DOMAIN));
>  		cpumask_and(mask, mask, housekeeping_cpumask(HK_TYPE_WQ));
>  		if (cpumask_empty(mask)) {
>  			free_cpumask_var(mask);
> -- 
> 2.38.0
>