[PATCH V2] nvme-pci: fix race condition between reset and nvme_dev_disable()

[Keith Busch]

On Tue, Oct 15, 2024 at 01:21:00PM +0200, Maurizio Lombardi wrote:
> -static void nvme_pci_update_nr_queues(struct nvme_dev *dev)
> +static bool nvme_pci_update_nr_queues(struct nvme_dev *dev)
>  {
>  	if (!dev->ctrl.tagset) {
>  		nvme_alloc_io_tag_set(&dev->ctrl, &dev->tagset, &nvme_mq_ops,
>  				nvme_pci_nr_maps(dev), sizeof(struct nvme_iod));
> -		return;
> +		return true;
> +	}
> +
> +	/* Give up if we are racing with nvme_dev_disable() */
> +	if (!mutex_trylock(&dev->shutdown_lock))
> +		return false;
> +
> +	/* Check if nvme_dev_disable() has been executed already */
> +	if (!dev->online_queues) {
> +		mutex_unlock(&dev->shutdown_lock);
> +		return false;
>  	}
>  
>  	blk_mq_update_nr_hw_queues(&dev->tagset, dev->online_queues - 1);
>  	/* free previously allocated queues that are no longer usable */
>  	nvme_free_queues(dev, dev->online_queues);
> +	mutex_unlock(&dev->shutdown_lock);

I believe mutex_unlock needs to be above blk_mq_update_nr_hw_queues().
That function needs all the queues to be frozen, so any older IO that
times out is going to need this lock in order to reclaim it.