static int nvme_setup_io_queues()

in host/pci.c [2338:2449]

• 77 lines of code
• 17 McCabe index (conditional complexity)

static int nvme_setup_io_queues(struct nvme_dev *dev)
{
	struct nvme_queue *adminq = &dev->queues[0];
	struct pci_dev *pdev = to_pci_dev(dev->dev);
	unsigned int nr_io_queues;
	unsigned long size;
	int result;

	/*
	 * Sample the module parameters once at reset time so that we have
	 * stable values to work with.
	 */
	dev->nr_write_queues = write_queues;
	dev->nr_poll_queues = poll_queues;

	nr_io_queues = dev->nr_allocated_queues - 1;
	result = nvme_set_queue_count(&dev->ctrl, &nr_io_queues);
	if (result < 0)
		return result;

	if (nr_io_queues == 0)
		return 0;

	/*
	 * Free IRQ resources as soon as NVMEQ_ENABLED bit transitions
	 * from set to unset. If there is a window to it is truely freed,
	 * pci_free_irq_vectors() jumping into this window will crash.
	 * And take lock to avoid racing with pci_free_irq_vectors() in
	 * nvme_dev_disable() path.
	 */
	result = nvme_setup_io_queues_trylock(dev);
	if (result)
		return result;
	if (test_and_clear_bit(NVMEQ_ENABLED, &adminq->flags))
		pci_free_irq(pdev, 0, adminq);

	if (dev->cmb_use_sqes) {
		result = nvme_cmb_qdepth(dev, nr_io_queues,
				sizeof(struct nvme_command));
		if (result > 0)
			dev->q_depth = result;
		else
			dev->cmb_use_sqes = false;
	}

	do {
		size = db_bar_size(dev, nr_io_queues);
		result = nvme_remap_bar(dev, size);
		if (!result)
			break;
		if (!--nr_io_queues) {
			result = -ENOMEM;
			goto out_unlock;
		}
	} while (1);
	adminq->q_db = dev->dbs;

 retry:
	/* Deregister the admin queue's interrupt */
	if (test_and_clear_bit(NVMEQ_ENABLED, &adminq->flags))
		pci_free_irq(pdev, 0, adminq);

	/*
	 * If we enable msix early due to not intx, disable it again before
	 * setting up the full range we need.
	 */
	pci_free_irq_vectors(pdev);

	result = nvme_setup_irqs(dev, nr_io_queues);
	if (result <= 0) {
		result = -EIO;
		goto out_unlock;
	}

	dev->num_vecs = result;
	result = max(result - 1, 1);
	dev->max_qid = result + dev->io_queues[HCTX_TYPE_POLL];

	/*
	 * Should investigate if there's a performance win from allocating
	 * more queues than interrupt vectors; it might allow the submission
	 * path to scale better, even if the receive path is limited by the
	 * number of interrupts.
	 */
	result = queue_request_irq(adminq);
	if (result)
		goto out_unlock;
	set_bit(NVMEQ_ENABLED, &adminq->flags);
	mutex_unlock(&dev->shutdown_lock);

	result = nvme_create_io_queues(dev);
	if (result || dev->online_queues < 2)
		return result;

	if (dev->online_queues - 1 < dev->max_qid) {
		nr_io_queues = dev->online_queues - 1;
		nvme_disable_io_queues(dev);
		result = nvme_setup_io_queues_trylock(dev);
		if (result)
			return result;
		nvme_suspend_io_queues(dev);
		goto retry;
	}
	dev_info(dev->ctrl.device, "%d/%d/%d default/read/poll queues\n",
					dev->io_queues[HCTX_TYPE_DEFAULT],
					dev->io_queues[HCTX_TYPE_READ],
					dev->io_queues[HCTX_TYPE_POLL]);
	return 0;
out_unlock:
	mutex_unlock(&dev->shutdown_lock);
	return result;
}