Merge branch 'for-4.9/block-irq' of git://git.kernel.dk/linux-block

Pull blk-mq irq/cpu mapping updates from Jens Axboe:
 "This is the block-irq topic branch for 4.9-rc. It's mostly from
  Christoph, and it allows drivers to specify their own mappings, and
  more importantly, to share the blk-mq mappings with the IRQ affinity
  mappings. It's a good step towards making this work better out of the
  box"

* 'for-4.9/block-irq' of git://git.kernel.dk/linux-block:
  blk_mq: linux/blk-mq.h does not include all the headers it depends on
  blk-mq: kill unused blk_mq_create_mq_map()
  blk-mq: get rid of the cpumask in struct blk_mq_tags
  nvme: remove the post_scan callout
  nvme: switch to use pci_alloc_irq_vectors
  blk-mq: provide a default queue mapping for PCI device
  blk-mq: allow the driver to pass in a queue mapping
  blk-mq: remove ->map_queue
  blk-mq: only allocate a single mq_map per tag_set
  blk-mq: don't redistribute hardware queues on a CPU hotplug event

5 files changed, 36 insertions, 81 deletions

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 4669c052239e..329381a28edf 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -1851,9 +1851,6 @@ static void nvme_scan_work(struct work_struct *work)
 	list_sort(NULL, &ctrl->namespaces, ns_cmp);
 	mutex_unlock(&ctrl->namespaces_mutex);
 	kfree(id);
-
-	if (ctrl->ops->post_scan)
-		ctrl->ops->post_scan(ctrl);
 }
 
 void nvme_queue_scan(struct nvme_ctrl *ctrl)
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index b0a9ec681685..d47f5a5d18c7 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -185,7 +185,6 @@ struct nvme_ctrl_ops {
 	int (*reg_read64)(struct nvme_ctrl *ctrl, u32 off, u64 *val);
 	int (*reset_ctrl)(struct nvme_ctrl *ctrl);
 	void (*free_ctrl)(struct nvme_ctrl *ctrl);
-	void (*post_scan)(struct nvme_ctrl *ctrl);
 	void (*submit_async_event)(struct nvme_ctrl *ctrl, int aer_idx);
 	int (*delete_ctrl)(struct nvme_ctrl *ctrl);
 	const char *(*get_subsysnqn)(struct nvme_ctrl *ctrl);
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 60f7eab11865..68ef1875e8a8 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -16,6 +16,7 @@
 #include <linux/bitops.h>
 #include <linux/blkdev.h>
 #include <linux/blk-mq.h>
+#include <linux/blk-mq-pci.h>
 #include <linux/cpu.h>
 #include <linux/delay.h>
 #include <linux/errno.h>
@@ -88,7 +89,6 @@ struct nvme_dev {
 	unsigned max_qid;
 	int q_depth;
 	u32 db_stride;
-	struct msix_entry *entry;
 	void __iomem *bar;
 	struct work_struct reset_work;
 	struct work_struct remove_work;
@@ -201,6 +201,11 @@ static unsigned int nvme_cmd_size(struct nvme_dev *dev)
 		nvme_iod_alloc_size(dev, NVME_INT_BYTES(dev), NVME_INT_PAGES);
 }
 
+static int nvmeq_irq(struct nvme_queue *nvmeq)
+{
+	return pci_irq_vector(to_pci_dev(nvmeq->dev->dev), nvmeq->cq_vector);
+}
+
 static int nvme_admin_init_hctx(struct blk_mq_hw_ctx *hctx, void *data,
 				unsigned int hctx_idx)
 {
@@ -263,6 +268,13 @@ static int nvme_init_request(void *data, struct request *req,
 	return 0;
 }
 
+static int nvme_pci_map_queues(struct blk_mq_tag_set *set)
+{
+	struct nvme_dev *dev = set->driver_data;
+
+	return blk_mq_pci_map_queues(set, to_pci_dev(dev->dev));
+}
+
 /**
  * __nvme_submit_cmd() - Copy a command into a queue and ring the doorbell
  * @nvmeq: The queue to use
@@ -960,7 +972,7 @@ static int nvme_suspend_queue(struct nvme_queue *nvmeq)
 		spin_unlock_irq(&nvmeq->q_lock);
 		return 1;
 	}
-	vector = nvmeq->dev->entry[nvmeq->cq_vector].vector;
+	vector = nvmeq_irq(nvmeq);
 	nvmeq->dev->online_queues--;
 	nvmeq->cq_vector = -1;
 	spin_unlock_irq(&nvmeq->q_lock);
@@ -968,7 +980,6 @@ static int nvme_suspend_queue(struct nvme_queue *nvmeq)
 	if (!nvmeq->qid && nvmeq->dev->ctrl.admin_q)
 		blk_mq_stop_hw_queues(nvmeq->dev->ctrl.admin_q);
 
-	irq_set_affinity_hint(vector, NULL);
 	free_irq(vector, nvmeq);
 
 	return 0;
@@ -1075,15 +1086,14 @@ static struct nvme_queue *nvme_alloc_queue(struct nvme_dev *dev, int qid,
 	return NULL;
 }
 
-static int queue_request_irq(struct nvme_dev *dev, struct nvme_queue *nvmeq,
-							const char *name)
+static int queue_request_irq(struct nvme_queue *nvmeq)
 {
 	if (use_threaded_interrupts)
-		return request_threaded_irq(dev->entry[nvmeq->cq_vector].vector,
-					nvme_irq_check, nvme_irq, IRQF_SHARED,
-					name, nvmeq);
-	return request_irq(dev->entry[nvmeq->cq_vector].vector, nvme_irq,
-				IRQF_SHARED, name, nvmeq);
+		return request_threaded_irq(nvmeq_irq(nvmeq), nvme_irq_check,
+				nvme_irq, IRQF_SHARED, nvmeq->irqname, nvmeq);
+	else
+		return request_irq(nvmeq_irq(nvmeq), nvme_irq, IRQF_SHARED,
+				nvmeq->irqname, nvmeq);
 }
 
 static void nvme_init_queue(struct nvme_queue *nvmeq, u16 qid)
@@ -1114,7 +1124,7 @@ static int nvme_create_queue(struct nvme_queue *nvmeq, int qid)
 	if (result < 0)
 		goto release_cq;
 
-	result = queue_request_irq(dev, nvmeq, nvmeq->irqname);
+	result = queue_request_irq(nvmeq);
 	if (result < 0)
 		goto release_sq;
 
@@ -1131,7 +1141,6 @@ static int nvme_create_queue(struct nvme_queue *nvmeq, int qid)
 static struct blk_mq_ops nvme_mq_admin_ops = {
 	.queue_rq	= nvme_queue_rq,
 	.complete	= nvme_complete_rq,
-	.map_queue	= blk_mq_map_queue,
 	.init_hctx	= nvme_admin_init_hctx,
 	.exit_hctx      = nvme_admin_exit_hctx,
 	.init_request	= nvme_admin_init_request,
@@ -1141,9 +1150,9 @@ static struct blk_mq_ops nvme_mq_admin_ops = {
 static struct blk_mq_ops nvme_mq_ops = {
 	.queue_rq	= nvme_queue_rq,
 	.complete	= nvme_complete_rq,
-	.map_queue	= blk_mq_map_queue,
 	.init_hctx	= nvme_init_hctx,
 	.init_request	= nvme_init_request,
+	.map_queues	= nvme_pci_map_queues,
 	.timeout	= nvme_timeout,
 	.poll		= nvme_poll,
 };
@@ -1234,7 +1243,7 @@ static int nvme_configure_admin_queue(struct nvme_dev *dev)
 		goto free_nvmeq;
 
 	nvmeq->cq_vector = 0;
-	result = queue_request_irq(dev, nvmeq, nvmeq->irqname);
+	result = queue_request_irq(nvmeq);
 	if (result) {
 		nvmeq->cq_vector = -1;
 		goto free_nvmeq;
@@ -1382,7 +1391,7 @@ 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);
-	int result, i, vecs, nr_io_queues, size;
+	int result, nr_io_queues, size;
 
 	nr_io_queues = num_online_cpus();
 	result = nvme_set_queue_count(&dev->ctrl, &nr_io_queues);
@@ -1417,29 +1426,18 @@ static int nvme_setup_io_queues(struct nvme_dev *dev)
 	}
 
 	/* Deregister the admin queue's interrupt */
-	free_irq(dev->entry[0].vector, adminq);
+	free_irq(pci_irq_vector(pdev, 0), adminq);
 
 	/*
 	 * If we enable msix early due to not intx, disable it again before
 	 * setting up the full range we need.
 	 */
-	if (pdev->msi_enabled)
-		pci_disable_msi(pdev);
-	else if (pdev->msix_enabled)
-		pci_disable_msix(pdev);
-
-	for (i = 0; i < nr_io_queues; i++)
-		dev->entry[i].entry = i;
-	vecs = pci_enable_msix_range(pdev, dev->entry, 1, nr_io_queues);
-	if (vecs < 0) {
-		vecs = pci_enable_msi_range(pdev, 1, min(nr_io_queues, 32));
-		if (vecs < 0) {
-			vecs = 1;
-		} else {
-			for (i = 0; i < vecs; i++)
-				dev->entry[i].vector = i + pdev->irq;
-		}
-	}
+	pci_free_irq_vectors(pdev);
+	nr_io_queues = pci_alloc_irq_vectors(pdev, 1, nr_io_queues,
+			PCI_IRQ_ALL_TYPES | PCI_IRQ_AFFINITY);
+	if (nr_io_queues <= 0)
+		return -EIO;
+	dev->max_qid = nr_io_queues;
 
 	/*
 	 * Should investigate if there's a performance win from allocating
@@ -1447,10 +1445,8 @@ static int nvme_setup_io_queues(struct nvme_dev *dev)
 	 * path to scale better, even if the receive path is limited by the
 	 * number of interrupts.
 	 */
-	nr_io_queues = vecs;
-	dev->max_qid = nr_io_queues;
 
-	result = queue_request_irq(dev, adminq, adminq->irqname);
+	result = queue_request_irq(adminq);
 	if (result) {
 		adminq->cq_vector = -1;
 		goto free_queues;
@@ -1462,23 +1458,6 @@ static int nvme_setup_io_queues(struct nvme_dev *dev)
 	return result;
 }
 
-static void nvme_pci_post_scan(struct nvme_ctrl *ctrl)
-{
-	struct nvme_dev *dev = to_nvme_dev(ctrl);
-	struct nvme_queue *nvmeq;
-	int i;
-
-	for (i = 0; i < dev->online_queues; i++) {
-		nvmeq = dev->queues[i];
-
-		if (!nvmeq->tags || !(*nvmeq->tags))
-			continue;
-
-		irq_set_affinity_hint(dev->entry[nvmeq->cq_vector].vector,
-					blk_mq_tags_cpumask(*nvmeq->tags));
-	}
-}
-
 static void nvme_del_queue_end(struct request *req, int error)
 {
 	struct nvme_queue *nvmeq = req->end_io_data;
@@ -1615,15 +1594,9 @@ static int nvme_pci_enable(struct nvme_dev *dev)
 	 * interrupts. Pre-enable a single MSIX or MSI vec for setup. We'll
 	 * adjust this later.
 	 */
-	if (pci_enable_msix(pdev, dev->entry, 1)) {
-		pci_enable_msi(pdev);
-		dev->entry[0].vector = pdev->irq;
-	}
-
-	if (!dev->entry[0].vector) {
-		result = -ENODEV;
-		goto disable;
-	}
+	result = pci_alloc_irq_vectors(pdev, 1, 1, PCI_IRQ_ALL_TYPES);
+	if (result < 0)
+		return result;
 
 	cap = lo_hi_readq(dev->bar + NVME_REG_CAP);
 
@@ -1665,10 +1638,7 @@ static void nvme_pci_disable(struct nvme_dev *dev)
 {
 	struct pci_dev *pdev = to_pci_dev(dev->dev);
 
-	if (pdev->msi_enabled)
-		pci_disable_msi(pdev);
-	else if (pdev->msix_enabled)
-		pci_disable_msix(pdev);
+	pci_free_irq_vectors(pdev);
 
 	if (pci_is_enabled(pdev)) {
 		pci_disable_pcie_error_reporting(pdev);
@@ -1743,7 +1713,6 @@ static void nvme_pci_free_ctrl(struct nvme_ctrl *ctrl)
 	if (dev->ctrl.admin_q)
 		blk_put_queue(dev->ctrl.admin_q);
 	kfree(dev->queues);
-	kfree(dev->entry);
 	kfree(dev);
 }
 
@@ -1887,7 +1856,6 @@ static const struct nvme_ctrl_ops nvme_pci_ctrl_ops = {
 	.reg_read64		= nvme_pci_reg_read64,
 	.reset_ctrl		= nvme_pci_reset_ctrl,
 	.free_ctrl		= nvme_pci_free_ctrl,
-	.post_scan		= nvme_pci_post_scan,
 	.submit_async_event	= nvme_pci_submit_async_event,
 };
 
@@ -1920,10 +1888,6 @@ static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	dev = kzalloc_node(sizeof(*dev), GFP_KERNEL, node);
 	if (!dev)
 		return -ENOMEM;
-	dev->entry = kzalloc_node(num_possible_cpus() * sizeof(*dev->entry),
-							GFP_KERNEL, node);
-	if (!dev->entry)
-		goto free;
 	dev->queues = kzalloc_node((num_possible_cpus() + 1) * sizeof(void *),
 							GFP_KERNEL, node);
 	if (!dev->queues)
@@ -1964,7 +1928,6 @@ static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	nvme_dev_unmap(dev);
  free:
 	kfree(dev->queues);
-	kfree(dev->entry);
 	kfree(dev);
 	return result;
 }
diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c
index 28632292e85e..5a8388177959 100644
--- a/drivers/nvme/host/rdma.c
+++ b/drivers/nvme/host/rdma.c
@@ -1480,7 +1480,6 @@ static void nvme_rdma_complete_rq(struct request *rq)
 static struct blk_mq_ops nvme_rdma_mq_ops = {
 	.queue_rq	= nvme_rdma_queue_rq,
 	.complete	= nvme_rdma_complete_rq,
-	.map_queue	= blk_mq_map_queue,
 	.init_request	= nvme_rdma_init_request,
 	.exit_request	= nvme_rdma_exit_request,
 	.reinit_request	= nvme_rdma_reinit_request,
@@ -1492,7 +1491,6 @@ static struct blk_mq_ops nvme_rdma_mq_ops = {
 static struct blk_mq_ops nvme_rdma_admin_mq_ops = {
 	.queue_rq	= nvme_rdma_queue_rq,
 	.complete	= nvme_rdma_complete_rq,
-	.map_queue	= blk_mq_map_queue,
 	.init_request	= nvme_rdma_init_admin_request,
 	.exit_request	= nvme_rdma_exit_admin_request,
 	.reinit_request	= nvme_rdma_reinit_request,
diff --git a/drivers/nvme/target/loop.c b/drivers/nvme/target/loop.c
index 395e60dad835..d5df77d686b2 100644
--- a/drivers/nvme/target/loop.c
+++ b/drivers/nvme/target/loop.c
@@ -273,7 +273,6 @@ static int nvme_loop_init_admin_hctx(struct blk_mq_hw_ctx *hctx, void *data,
 static struct blk_mq_ops nvme_loop_mq_ops = {
 	.queue_rq	= nvme_loop_queue_rq,
 	.complete	= nvme_loop_complete_rq,
-	.map_queue	= blk_mq_map_queue,
 	.init_request	= nvme_loop_init_request,
 	.init_hctx	= nvme_loop_init_hctx,
 	.timeout	= nvme_loop_timeout,
@@ -282,7 +281,6 @@ static struct blk_mq_ops nvme_loop_mq_ops = {
 static struct blk_mq_ops nvme_loop_admin_mq_ops = {
 	.queue_rq	= nvme_loop_queue_rq,
 	.complete	= nvme_loop_complete_rq,
-	.map_queue	= blk_mq_map_queue,
 	.init_request	= nvme_loop_init_admin_request,
 	.init_hctx	= nvme_loop_init_admin_hctx,
 	.timeout	= nvme_loop_timeout,