struct nvme_queue {
struct device *q_dmadev;
struct nvme_dev *dev;
+ char irqname[24]; /* nvme4294967295-65535\0 */
spinlock_t q_lock;
struct nvme_command *sq_cmds;
volatile struct nvme_completion *cqes;
return total_len;
}
-struct nvme_bio_pair {
- struct bio b1, b2, *parent;
- struct bio_vec *bv1, *bv2;
- int err;
- atomic_t cnt;
-};
-
-static void nvme_bio_pair_endio(struct bio *bio, int err)
-{
- struct nvme_bio_pair *bp = bio->bi_private;
-
- if (err)
- bp->err = err;
-
- if (atomic_dec_and_test(&bp->cnt)) {
- bio_endio(bp->parent, bp->err);
- kfree(bp->bv1);
- kfree(bp->bv2);
- kfree(bp);
- }
-}
-
-static struct nvme_bio_pair *nvme_bio_split(struct bio *bio, int idx,
- int len, int offset)
-{
- struct nvme_bio_pair *bp;
-
- BUG_ON(len > bio->bi_size);
- BUG_ON(idx > bio->bi_vcnt);
-
- bp = kmalloc(sizeof(*bp), GFP_ATOMIC);
- if (!bp)
- return NULL;
- bp->err = 0;
-
- bp->b1 = *bio;
- bp->b2 = *bio;
-
- bp->b1.bi_size = len;
- bp->b2.bi_size -= len;
- bp->b1.bi_vcnt = idx;
- bp->b2.bi_idx = idx;
- bp->b2.bi_sector += len >> 9;
-
- if (offset) {
- bp->bv1 = kmalloc(bio->bi_max_vecs * sizeof(struct bio_vec),
- GFP_ATOMIC);
- if (!bp->bv1)
- goto split_fail_1;
-
- bp->bv2 = kmalloc(bio->bi_max_vecs * sizeof(struct bio_vec),
- GFP_ATOMIC);
- if (!bp->bv2)
- goto split_fail_2;
-
- memcpy(bp->bv1, bio->bi_io_vec,
- bio->bi_max_vecs * sizeof(struct bio_vec));
- memcpy(bp->bv2, bio->bi_io_vec,
- bio->bi_max_vecs * sizeof(struct bio_vec));
-
- bp->b1.bi_io_vec = bp->bv1;
- bp->b2.bi_io_vec = bp->bv2;
- bp->b2.bi_io_vec[idx].bv_offset += offset;
- bp->b2.bi_io_vec[idx].bv_len -= offset;
- bp->b1.bi_io_vec[idx].bv_len = offset;
- bp->b1.bi_vcnt++;
- } else
- bp->bv1 = bp->bv2 = NULL;
-
- bp->b1.bi_private = bp;
- bp->b2.bi_private = bp;
-
- bp->b1.bi_end_io = nvme_bio_pair_endio;
- bp->b2.bi_end_io = nvme_bio_pair_endio;
-
- bp->parent = bio;
- atomic_set(&bp->cnt, 2);
-
- return bp;
-
- split_fail_2:
- kfree(bp->bv1);
- split_fail_1:
- kfree(bp);
- return NULL;
-}
-
static int nvme_split_and_submit(struct bio *bio, struct nvme_queue *nvmeq,
- int idx, int len, int offset)
+ int len)
{
- struct nvme_bio_pair *bp = nvme_bio_split(bio, idx, len, offset);
- if (!bp)
+ struct bio *split = bio_split(bio, len >> 9, GFP_ATOMIC, NULL);
+ if (!split)
return -ENOMEM;
+ bio_chain(split, bio);
+
if (bio_list_empty(&nvmeq->sq_cong))
add_wait_queue(&nvmeq->sq_full, &nvmeq->sq_cong_wait);
- bio_list_add(&nvmeq->sq_cong, &bp->b1);
- bio_list_add(&nvmeq->sq_cong, &bp->b2);
+ bio_list_add(&nvmeq->sq_cong, split);
+ bio_list_add(&nvmeq->sq_cong, bio);
return 0;
}
static int nvme_map_bio(struct nvme_queue *nvmeq, struct nvme_iod *iod,
struct bio *bio, enum dma_data_direction dma_dir, int psegs)
{
- struct bio_vec *bvec, *bvprv = NULL;
+ struct bio_vec bvec, bvprv;
+ struct bvec_iter iter;
struct scatterlist *sg = NULL;
- int i, length = 0, nsegs = 0, split_len = bio->bi_size;
+ int length = 0, nsegs = 0, split_len = bio->bi_iter.bi_size;
+ int first = 1;
if (nvmeq->dev->stripe_size)
split_len = nvmeq->dev->stripe_size -
- ((bio->bi_sector << 9) & (nvmeq->dev->stripe_size - 1));
+ ((bio->bi_iter.bi_sector << 9) &
+ (nvmeq->dev->stripe_size - 1));
sg_init_table(iod->sg, psegs);
- bio_for_each_segment(bvec, bio, i) {
- if (bvprv && BIOVEC_PHYS_MERGEABLE(bvprv, bvec)) {
- sg->length += bvec->bv_len;
+ bio_for_each_segment(bvec, bio, iter) {
+ if (!first && BIOVEC_PHYS_MERGEABLE(&bvprv, &bvec)) {
+ sg->length += bvec.bv_len;
} else {
- if (bvprv && BIOVEC_NOT_VIRT_MERGEABLE(bvprv, bvec))
- return nvme_split_and_submit(bio, nvmeq, i,
- length, 0);
+ if (!first && BIOVEC_NOT_VIRT_MERGEABLE(&bvprv, &bvec))
+ return nvme_split_and_submit(bio, nvmeq,
+ length);
sg = sg ? sg + 1 : iod->sg;
- sg_set_page(sg, bvec->bv_page, bvec->bv_len,
- bvec->bv_offset);
+ sg_set_page(sg, bvec.bv_page,
+ bvec.bv_len, bvec.bv_offset);
nsegs++;
}
- if (split_len - length < bvec->bv_len)
- return nvme_split_and_submit(bio, nvmeq, i, split_len,
- split_len - length);
- length += bvec->bv_len;
+ if (split_len - length < bvec.bv_len)
+ return nvme_split_and_submit(bio, nvmeq, split_len);
+ length += bvec.bv_len;
bvprv = bvec;
+ first = 0;
}
iod->nents = nsegs;
sg_mark_end(sg);
if (dma_map_sg(nvmeq->q_dmadev, iod->sg, iod->nents, dma_dir) == 0)
return -ENOMEM;
- BUG_ON(length != bio->bi_size);
+ BUG_ON(length != bio->bi_iter.bi_size);
return length;
}
iod->npages = 0;
range->cattr = cpu_to_le32(0);
- range->nlb = cpu_to_le32(bio->bi_size >> ns->lba_shift);
- range->slba = cpu_to_le64(nvme_block_nr(ns, bio->bi_sector));
+ range->nlb = cpu_to_le32(bio->bi_iter.bi_size >> ns->lba_shift);
+ range->slba = cpu_to_le64(nvme_block_nr(ns, bio->bi_iter.bi_sector));
memset(cmnd, 0, sizeof(*cmnd));
cmnd->dsm.opcode = nvme_cmd_dsm;
}
result = -ENOMEM;
- iod = nvme_alloc_iod(psegs, bio->bi_size, GFP_ATOMIC);
+ iod = nvme_alloc_iod(psegs, bio->bi_iter.bi_size, GFP_ATOMIC);
if (!iod)
goto nomem;
iod->private = bio;
cmnd->rw.nsid = cpu_to_le32(ns->ns_id);
length = nvme_setup_prps(nvmeq->dev, &cmnd->common, iod, length,
GFP_ATOMIC);
- cmnd->rw.slba = cpu_to_le64(nvme_block_nr(ns, bio->bi_sector));
+ cmnd->rw.slba = cpu_to_le64(nvme_block_nr(ns, bio->bi_iter.bi_sector));
cmnd->rw.length = cpu_to_le16((length >> ns->lba_shift) - 1);
cmnd->rw.control = cpu_to_le16(control);
cmnd->rw.dsmgmt = cpu_to_le32(dsmgmt);
dev_warn(&dev->pci_dev->dev,
"I/O %d QID %d timeout, reset controller\n", cmdid,
nvmeq->qid);
- INIT_WORK(&dev->reset_work, nvme_reset_failed_dev);
+ PREPARE_WORK(&dev->reset_work, nvme_reset_failed_dev);
queue_work(nvme_workq, &dev->reset_work);
return;
}
nvmeq->q_dmadev = dmadev;
nvmeq->dev = dev;
+ snprintf(nvmeq->irqname, sizeof(nvmeq->irqname), "nvme%dq%d",
+ dev->instance, qid);
spin_lock_init(&nvmeq->q_lock);
nvmeq->cq_head = 0;
nvmeq->cq_phase = 1;
if (result < 0)
goto release_cq;
- result = queue_request_irq(dev, nvmeq, "nvme");
+ result = queue_request_irq(dev, nvmeq, nvmeq->irqname);
if (result < 0)
goto release_sq;
if (result)
return result;
- result = queue_request_irq(dev, nvmeq, "nvme admin");
+ result = queue_request_irq(dev, nvmeq, nvmeq->irqname);
if (result)
return result;
#define nvme_compat_ioctl NULL
#endif
+static int nvme_open(struct block_device *bdev, fmode_t mode)
+{
+ struct nvme_ns *ns = bdev->bd_disk->private_data;
+ struct nvme_dev *dev = ns->dev;
+
+ kref_get(&dev->kref);
+ return 0;
+}
+
+static void nvme_free_dev(struct kref *kref);
+
+static void nvme_release(struct gendisk *disk, fmode_t mode)
+{
+ struct nvme_ns *ns = disk->private_data;
+ struct nvme_dev *dev = ns->dev;
+
+ kref_put(&dev->kref, nvme_free_dev);
+}
+
static const struct block_device_operations nvme_fops = {
.owner = THIS_MODULE,
.ioctl = nvme_ioctl,
.compat_ioctl = nvme_compat_ioctl,
+ .open = nvme_open,
+ .release = nvme_release,
};
static void nvme_resubmit_bios(struct nvme_queue *nvmeq)
list_del_init(&dev->node);
dev_warn(&dev->pci_dev->dev,
"Failed status, reset controller\n");
- INIT_WORK(&dev->reset_work,
+ PREPARE_WORK(&dev->reset_work,
nvme_reset_failed_dev);
queue_work(nvme_workq, &dev->reset_work);
continue;
return NULL;
}
-static void nvme_ns_free(struct nvme_ns *ns)
-{
- put_disk(ns->disk);
- blk_cleanup_queue(ns->queue);
- kfree(ns);
-}
-
static int set_queue_count(struct nvme_dev *dev, int count)
{
int status;
static int nvme_setup_io_queues(struct nvme_dev *dev)
{
+ struct nvme_queue *adminq = dev->queues[0];
struct pci_dev *pdev = dev->pci_dev;
int result, cpu, i, vecs, nr_io_queues, size, q_depth;
}
/* Deregister the admin queue's interrupt */
- free_irq(dev->entry[0].vector, dev->queues[0]);
+ free_irq(dev->entry[0].vector, adminq);
vecs = nr_io_queues;
for (i = 0; i < vecs; i++)
*/
nr_io_queues = vecs;
- result = queue_request_irq(dev, dev->queues[0], "nvme admin");
+ result = queue_request_irq(dev, adminq, adminq->irqname);
if (result) {
- dev->queues[0]->q_suspended = 1;
+ adminq->q_suspended = 1;
goto free_queues;
}
static void nvme_dev_remove(struct nvme_dev *dev)
{
- struct nvme_ns *ns, *next;
+ struct nvme_ns *ns;
- list_for_each_entry_safe(ns, next, &dev->namespaces, list) {
- list_del(&ns->list);
- del_gendisk(ns->disk);
- nvme_ns_free(ns);
+ list_for_each_entry(ns, &dev->namespaces, list) {
+ if (ns->disk->flags & GENHD_FL_UP)
+ del_gendisk(ns->disk);
+ if (!blk_queue_dying(ns->queue))
+ blk_cleanup_queue(ns->queue);
}
}
spin_unlock(&dev_list_lock);
}
+static void nvme_free_namespaces(struct nvme_dev *dev)
+{
+ struct nvme_ns *ns, *next;
+
+ list_for_each_entry_safe(ns, next, &dev->namespaces, list) {
+ list_del(&ns->list);
+ put_disk(ns->disk);
+ kfree(ns);
+ }
+}
+
static void nvme_free_dev(struct kref *kref)
{
struct nvme_dev *dev = container_of(kref, struct nvme_dev, kref);
+
+ nvme_free_namespaces(dev);
kfree(dev->queues);
kfree(dev->entry);
kfree(dev);
return ret;
if (ret == -EBUSY) {
spin_lock(&dev_list_lock);
- INIT_WORK(&dev->reset_work, nvme_remove_disks);
+ PREPARE_WORK(&dev->reset_work, nvme_remove_disks);
queue_work(nvme_workq, &dev->reset_work);
spin_unlock(&dev_list_lock);
}
goto free;
INIT_LIST_HEAD(&dev->namespaces);
+ INIT_WORK(&dev->reset_work, nvme_reset_failed_dev);
dev->pci_dev = pdev;
pci_set_drvdata(pdev, dev);
result = nvme_set_instance(dev);
goto release_pools;
}
+ kref_init(&dev->kref);
result = nvme_dev_add(dev);
if (result)
goto shutdown;
goto remove;
dev->initialized = 1;
- kref_init(&dev->kref);
return 0;
remove:
nvme_dev_remove(dev);
+ nvme_free_namespaces(dev);
shutdown:
nvme_dev_shutdown(dev);
release_pools:
return result;
}
+static void nvme_shutdown(struct pci_dev *pdev)
+{
+ struct nvme_dev *dev = pci_get_drvdata(pdev);
+ nvme_dev_shutdown(dev);
+}
+
static void nvme_remove(struct pci_dev *pdev)
{
struct nvme_dev *dev = pci_get_drvdata(pdev);
struct nvme_dev *ndev = pci_get_drvdata(pdev);
if (nvme_dev_resume(ndev) && !work_busy(&ndev->reset_work)) {
- INIT_WORK(&ndev->reset_work, nvme_reset_failed_dev);
+ PREPARE_WORK(&ndev->reset_work, nvme_reset_failed_dev);
queue_work(nvme_workq, &ndev->reset_work);
}
return 0;
.id_table = nvme_id_table,
.probe = nvme_probe,
.remove = nvme_remove,
+ .shutdown = nvme_shutdown,
.driver = {
.pm = &nvme_dev_pm_ops,
},
projects / ~andy / linux / blobdiff