[PATCH v6 9/9] blk-mq: prevent offlining hk CPU with associated online isolated CPUs

[Hannes Reinecke]

On 4/24/25 20:19, Daniel Wagner wrote:
> When isolcpus=io_queue is enabled, and the last housekeeping CPU for a
> given hctx would go offline, there would be no CPU left which handles
> the IOs. To prevent IO stalls, prevent offlining housekeeping CPUs which
> are still severing isolated CPUs..
             serving

> 
> Signed-off-by: Daniel Wagner <wagi at kernel.org>
> ---
>   block/blk-mq.c | 46 ++++++++++++++++++++++++++++++++++++++++++++--
>   1 file changed, 44 insertions(+), 2 deletions(-)
> 
> diff --git a/block/blk-mq.c b/block/blk-mq.c
> index c2697db591091200cdb9f6e082e472b829701e4c..aff17673b773583dfb2b01cb2f5f010c456bd834 100644
> --- a/block/blk-mq.c
> +++ b/block/blk-mq.c
> @@ -3627,6 +3627,48 @@ static bool blk_mq_hctx_has_requests(struct blk_mq_hw_ctx *hctx)
>   	return data.has_rq;
>   }
>   
> +static bool blk_mq_hctx_check_isolcpus_online(struct blk_mq_hw_ctx *hctx, unsigned int cpu)
> +{
> +	const struct cpumask *hk_mask;
> +	int i;
> +
> +	if (!housekeeping_enabled(HK_TYPE_IO_QUEUE))
> +		return true;
> +
> +	hk_mask = housekeeping_cpumask(HK_TYPE_IO_QUEUE);
> +
> +	for (i = 0; i < hctx->nr_ctx; i++) {
> +		struct blk_mq_ctx *ctx = hctx->ctxs[i];
> +
> +		if (ctx->cpu == cpu)
> +			continue;
> +
> +		/*
> +		 * Check if this context has at least one online
> +		 * housekeeping CPU in this case the hardware context is
> +		 * usable.
> +		 */
> +		if (cpumask_test_cpu(ctx->cpu, hk_mask) &&
> +		    cpu_online(ctx->cpu))
> +			break;
> +
> +		/*
> +		 * The context doesn't have any online housekeeping CPUs
> +		 * but there might be an online isolated CPU mapped to
> +		 * it.
> +		 */
> +		if (cpu_is_offline(ctx->cpu))
> +			continue;
> +
> +		pr_warn("%s: trying to offline hctx%d but there is still an online isolcpu CPU %d mapped to it\n",
> +			hctx->queue->disk->disk_name,
> +			hctx->queue_num, ctx->cpu);
> +		return true;
> +	}
> +
> +	return false;
> +}
> +
>   static bool blk_mq_hctx_has_online_cpu(struct blk_mq_hw_ctx *hctx,
>   		unsigned int this_cpu)
>   {
> @@ -3647,7 +3689,7 @@ static bool blk_mq_hctx_has_online_cpu(struct blk_mq_hw_ctx *hctx,
>   
>   		/* this hctx has at least one online CPU */
>   		if (this_cpu != cpu)
> -			return true;
> +			return blk_mq_hctx_check_isolcpus_online(hctx, this_cpu);
>   	}
>   
>   	return false;
> @@ -3659,7 +3701,7 @@ static int blk_mq_hctx_notify_offline(unsigned int cpu, struct hlist_node *node)
>   			struct blk_mq_hw_ctx, cpuhp_online);
>   
>   	if (blk_mq_hctx_has_online_cpu(hctx, cpu))
> -		return 0;
> +		return -EINVAL;
>   
>   	/*
>   	 * Prevent new request from being allocated on the current hctx.
> 
Otherwise:

Reviewed-by: Hannes Reinecke <hare at suse.de>

Cheers,

Hannes
-- 
Dr. Hannes Reinecke                  Kernel Storage Architect
hare at suse.de                                +49 911 74053 688
SUSE Software Solutions GmbH, Frankenstr. 146, 90461 Nürnberg
HRB 36809 (AG Nürnberg), GF: I. Totev, A. McDonald, W. Knoblich