On 10/30/18 7:57 PM, Sagi Grimberg wrote:

quoted

+static int queue_irq_offset(struct nvme_dev *dev)
+{
+	/* if we have more than 1 vec, admin queue offsets us 1 */

offsets us by 1?

Fixed

quoted

@@ -1934,13 +2048,48 @@ static int nvme_setup_io_queues(struct nvme_dev *dev)
  	 * setting up the full range we need.
  	 */
  	pci_free_irq_vectors(pdev);
-	result = pci_alloc_irq_vectors_affinity(pdev, 1, nr_io_queues + 1,
-			PCI_IRQ_ALL_TYPES | PCI_IRQ_AFFINITY, &affd);
-	if (result <= 0)
-		return -EIO;
+
+	/*
+	 * For irq sets, we have to ask for minvec == maxvec. This passes
+	 * any reduction back to us, so we can adjust our queue counts and
+	 * IRQ vector needs.
+	 */
+	do {
+		nvme_calc_io_queues(dev, nr_io_queues);
+		irq_sets[0] = dev->io_queues[NVMEQ_TYPE_READ];
+		irq_sets[1] = dev->io_queues[NVMEQ_TYPE_WRITE];
+		if (!irq_sets[1])
+			affd.nr_sets = 1;
+
+		/*
+		 * Need IRQs for read+write queues, and one for the admin queue
+		 */
+		nr_io_queues = irq_sets[0] + irq_sets[1] + 1;
+
+		result = pci_alloc_irq_vectors_affinity(pdev, nr_io_queues,
+				nr_io_queues,
+				PCI_IRQ_ALL_TYPES | PCI_IRQ_AFFINITY, &affd);
+
+		/*
+		 * Need to reduce our vec counts
+		 */
+		if (result == -ENOSPC) {
+			nr_io_queues--;
+			if (!nr_io_queues)
+				return result;
+			continue;
+		} else if (result <= 0)
+			return -EIO;
+		break;
+	} while (1);
+
  	dev->num_vecs = result;
  	dev->max_qid = max(result - 1, 1);
  
+	dev_info(dev->ctrl.device, "%d/%d/%d read/write queues\n",
+					dev->io_queues[NVMEQ_TYPE_READ],
+					dev->io_queues[NVMEQ_TYPE_WRITE]);
+

Perhaps it would be better if we move this code into a function.

Agree, I've done that now.

-- 
Jens Axboe