blk-mq: Allow PCI vector offset for mapping queues

All nvme queue memory is allocated up front. We don't take the node into consideration when creating queues anymore, so removing the unused parameter.

Signed-off-by Keith Busch <[email protected]>

---
 drivers/nvme/host/pci.c | 10 +++-------
 1 file changed, 3 insertions(+), 7 deletions(-)

drivers/nvme/host/pci.c +2 -4

index cef5ce851a92..632166f7d8f2 100644
@@ -1379,8 +1379,7 @@ static int nvme_alloc_sq_cmds(struct nvme_dev *dev, struct nvme_queue *nvmeq,
 	return 0;
 }
 
-static int nvme_alloc_queue(struct nvme_dev *dev, int qid,
-		int depth, int node)
+static int nvme_alloc_queue(struct nvme_dev *dev, int qid, int depth)
 {
 	struct nvme_queue *nvmeq = &dev->queues[qid];
 

@@ -1595,8 +1594,7 @@ static int nvme_pci_configure_admin_queue(struct nvme_dev *dev)
 	if (result < 0)
 		return result;
 
-	result = nvme_alloc_queue(dev, 0, NVME_AQ_DEPTH,
-			dev_to_node(dev->dev));
+	result = nvme_alloc_queue(dev, 0, NVME_AQ_DEPTH);
 	if (result)
 		return result;
 

Quoted 3 lines · Keith Busch

drivers/nvme/host/pci.c +0 -0

@@ -1629,9 +1627,7 @@ static int nvme_create_io_queues(struct nvme_dev *dev)
 	int ret = 0;
 

drivers/nvme/host/pci.c static int nvme_create_io_queues(struct nvme_dev *dev) · line 1633

Quoted 8 lines

drivers/nvme/host/pci.c +1 -3

 	for (i = dev->ctrl.queue_count; i <= dev->max_qid; i++) {
-		/* vector == qid - 1, match nvme_create_queue */
-		if (nvme_alloc_queue(dev, i, dev->q_depth,
-		     pci_irq_get_node(to_pci_dev(dev->dev), i - 1))) {
+		if (nvme_alloc_queue(dev, i, dev->q_depth)) {
 			ret = -ENOMEM;
 			break;
 		}

nvme_create_io_queues() is called after pci_alloc_irq_vectors() returns, and the above pci_irq_get_node() should return the correct node info, right?

The PCI interrupt vectors intended to be associated with a queue may not start at 0. This patch adds an offset parameter so blk-mq may find the intended affinity mask. The default value is 0 so existing drivers that don't care about this parameter don't need to change.

Signed-off-by Keith Busch <[email protected]>

---
 block/blk-mq-pci.c         | 12 ++++++++++--
 include/linux/blk-mq-pci.h |  2 ++
 2 files changed, 12 insertions(+), 2 deletions(-)

block/blk-mq-pci.c +3 -1

index 76944e3271bf..1040a7705c13 100644
@@ -21,6 +21,7 @@
  * blk_mq_pci_map_queues - provide a default queue mapping for PCI device
  * @set:	tagset to provide the mapping for
  * @pdev:	PCI device associated with @set.
+ * @offset:	PCI irq starting vector offset
  *
  * This function assumes the PCI device @pdev has at least as many available
  * interrupt vectors as @set has queues.  It will then query the vector

@@ -28,13 +29,14 @@
  * that maps a queue to the CPUs that have irq affinity for the corresponding
  * vector.
  */
-int blk_mq_pci_map_queues(struct blk_mq_tag_set *set, struct pci_dev *pdev)
+int __blk_mq_pci_map_queues(struct blk_mq_tag_set *set, struct pci_dev *pdev,
+			    int offset)

Maybe we could provide a callback parameter for __blk_mq_pci_map_queues which give the mapping from hctx queue num to device-relative interrupt vector index.

The PCI interrupt vectors intended to be associated with a queue may not start at 0. This patch adds an offset parameter so blk-mq may find the intended affinity mask. The default value is 0 so existing drivers that don't care about this parameter don't need to change.

Signed-off-by Keith Busch <[email protected]>

---
 block/blk-mq-pci.c         | 12 ++++++++++--
 include/linux/blk-mq-pci.h |  2 ++
 2 files changed, 12 insertions(+), 2 deletions(-)

block/blk-mq-pci.c +10 -2

index 76944e3271bf..1040a7705c13 100644
@@ -21,6 +21,7 @@
  * blk_mq_pci_map_queues - provide a default queue mapping for PCI device
  * @set:	tagset to provide the mapping for
  * @pdev:	PCI device associated with @set.
+ * @offset:	PCI irq starting vector offset
  *
  * This function assumes the PCI device @pdev has at least as many available
  * interrupt vectors as @set has queues.  It will then query the vector

@@ -28,13 +29,14 @@
  * that maps a queue to the CPUs that have irq affinity for the corresponding
  * vector.
  */
-int blk_mq_pci_map_queues(struct blk_mq_tag_set *set, struct pci_dev *pdev)
+int __blk_mq_pci_map_queues(struct blk_mq_tag_set *set, struct pci_dev *pdev,
+			    int offset)
 {
 	const struct cpumask *mask;
 	unsigned int queue, cpu;
 
 	for (queue = 0; queue < set->nr_hw_queues; queue++) {
-		mask = pci_irq_get_affinity(pdev, queue);
+		mask = pci_irq_get_affinity(pdev, queue + offset);
 		if (!mask)
 			goto fallback;
 

@@ -50,4 +52,10 @@ int blk_mq_pci_map_queues(struct blk_mq_tag_set *set, struct pci_dev *pdev)
 		set->mq_map[cpu] = 0;
 	return 0;
 }
+EXPORT_SYMBOL_GPL(__blk_mq_pci_map_queues);
+
+int blk_mq_pci_map_queues(struct blk_mq_tag_set *set, struct pci_dev *pdev)
+{
+	return __blk_mq_pci_map_queues(set, pdev, 0);
+}
 EXPORT_SYMBOL_GPL(blk_mq_pci_map_queues);

include/linux/blk-mq-pci.h +2 -0

index 6338551e0fb9..5a92ecdbd78e 100644
@@ -5,6 +5,8 @@
 struct blk_mq_tag_set;
 struct pci_dev;
 
+int __blk_mq_pci_map_queues(struct blk_mq_tag_set *set, struct pci_dev *pdev,
+			    int offset);
 int blk_mq_pci_map_queues(struct blk_mq_tag_set *set, struct pci_dev *pdev);
 
 #endif /* _LINUX_BLK_MQ_PCI_H */

Signature · 1 line

2.14.3

Given no many callers of blk_mq_pci_map_queues(), I suggest to add the parameter of 'offset' to this API directly, then people may keep the '.pre_vectors' stuff in mind, and avoid to misuse it.

The PCI interrupt vectors intended to be associated with a queue may not start at 0. This patch adds an offset parameter so blk-mq may find the intended affinity mask. The default value is 0 so existing drivers that don't care about this parameter don't need to change.

Signed-off-by Keith Busch <[email protected]>

---
 block/blk-mq-pci.c         | 12 ++++++++++--
 include/linux/blk-mq-pci.h |  2 ++
 2 files changed, 12 insertions(+), 2 deletions(-)

block/blk-mq-pci.c +1 -0

index 76944e3271bf..1040a7705c13 100644
@@ -21,6 +21,7 @@
  * blk_mq_pci_map_queues - provide a default queue mapping for PCI device
  * @set:	tagset to provide the mapping for
  * @pdev:	PCI device associated with @set.
+ * @offset:	PCI irq starting vector offset
  *
  * This function assumes the PCI device @pdev has at least as many available
  * interrupt vectors as @set has queues.  It will then query the vector