[PATCH V3] nvme-pci: allow unmanaged interrupts

[Ming Lei]

From: Keith Busch <kbusch at kernel.org>

People _really_ want to control their interrupt affinity in some
cases, such as Openshift with Performance profile, in which each
irq's affinity is completely specified from userspace. Turns out
that 'isolcpus=managed_irqs' isn't enough.

Add module parameter to allow unmanaged interrupts, just as some
SCSI drivers are doing.

Cc: Marcelo Tosatti <mtosatti at redhat.com>
Signed-off-by: Keith Busch <kbusch at kernel.org>
Signed-off-by: Ming Lei <ming.lei at redhat.com>
---
v2->v3:
	- rebase on for-next
	- add openshift use case

v1->v2: skip the the AFFINITY vector allocation if the parameter is
provided instead trying to make the vector code handle all post_vectors.

 drivers/nvme/host/pci.c | 18 ++++++++++++++++--
 1 file changed, 16 insertions(+), 2 deletions(-)

diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 5d8035218de9..a39c99c9b64d 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -63,6 +63,11 @@ MODULE_PARM_DESC(sgl_threshold,
 		"Use SGLs when average request segment size is larger or equal to "
 		"this size. Use 0 to disable SGLs.");
 
+static bool managed_irqs = true;
+module_param(managed_irqs, bool, 0444);
+MODULE_PARM_DESC(managed_irqs,
+		 "set to false for user controlled irq affinity");
+
 #define NVME_PCI_MIN_QUEUE_SIZE 2
 #define NVME_PCI_MAX_QUEUE_SIZE 4095
 static int io_queue_depth_set(const char *val, const struct kernel_param *kp);
@@ -456,7 +461,7 @@ static void nvme_pci_map_queues(struct blk_mq_tag_set *set)
 		 * affinity), so use the regular blk-mq cpu mapping
 		 */
 		map->queue_offset = qoff;
-		if (i != HCTX_TYPE_POLL && offset)
+		if (managed_irqs && i != HCTX_TYPE_POLL && offset)
 			blk_mq_pci_map_queues(map, to_pci_dev(dev->dev), offset);
 		else
 			blk_mq_map_queues(map);
@@ -2226,6 +2231,7 @@ static int nvme_setup_irqs(struct nvme_dev *dev, unsigned int nr_io_queues)
 	};
 	unsigned int irq_queues, poll_queues;
 	unsigned int flags = PCI_IRQ_ALL_TYPES | PCI_IRQ_AFFINITY;
+	int ret;
 
 	/*
 	 * Poll queues don't need interrupts, but we need at least one I/O queue
@@ -2251,8 +2257,16 @@ static int nvme_setup_irqs(struct nvme_dev *dev, unsigned int nr_io_queues)
 		irq_queues += (nr_io_queues - poll_queues);
 	if (dev->ctrl.quirks & NVME_QUIRK_BROKEN_MSI)
 		flags &= ~PCI_IRQ_MSI;
-	return pci_alloc_irq_vectors_affinity(pdev, 1, irq_queues, flags,
+
+	if (managed_irqs)
+		return pci_alloc_irq_vectors_affinity(pdev, 1, irq_queues, flags,
 					      &affd);
+
+	flags &= ~PCI_IRQ_AFFINITY;
+	ret = pci_alloc_irq_vectors(pdev, 1, irq_queues, flags);
+	if (ret > 0)
+		nvme_calc_irq_sets(&affd, ret - 1);
+	return ret;
 }
 
 static unsigned int nvme_max_io_queues(struct nvme_dev *dev)
-- 
2.44.0