nvme: switch to use pci_alloc_irq_vectors

Use the new helper to automatically select the right interrupt type, as
well as to use the automatic interupt affinity assignment.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Keith Busch <keith.busch@intel.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
This commit is contained in:
Christoph Hellwig 2016-09-14 16:18:57 +02:00 committed by Jens Axboe
parent 973c4e372c
commit dca51e7892
1 changed files with 36 additions and 71 deletions

View File

@ -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;
@ -1142,6 +1152,7 @@ static struct blk_mq_ops nvme_mq_ops = {
.complete = nvme_complete_rq,
.init_hctx = nvme_init_hctx,
.init_request = nvme_init_request,
.map_queues = nvme_pci_map_queues,
.timeout = nvme_timeout,
.poll = nvme_poll,
};
@ -1232,7 +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;
@ -1380,7 +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);
@ -1415,29 +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
@ -1445,10 +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;
@ -1460,23 +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;
@ -1613,15 +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);
@ -1663,10 +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);
@ -1736,7 +1708,6 @@ 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);
}
@ -1880,7 +1851,6 @@ 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,
};
@ -1913,10 +1883,6 @@ 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)
@ -1957,7 +1923,6 @@ 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;
}