Merge branch 'for-linus' of git://git.kernel.dk/linux-block
Pull block fixes from Jens Axboe: "A selection of fixes/changes that should make it into this series. This contains: - NVMe, two merges, containing: - pci-e, rdma, and fc fixes - Device quirks - Fix for a badblocks leak in null_blk - bcache fix from Rui Hua for a race condition regression where -EINTR was returned to upper layers that didn't expect it. - Regression fix for blktrace for a bug introduced in this series. - blktrace cleanup for cgroup id. - bdi registration error handling. - Small series with cleanups for blk-wbt. - Various little fixes for typos and the like. Nothing earth shattering, most important are the NVMe and bcache fixes" * 'for-linus' of git://git.kernel.dk/linux-block: (34 commits) nvme-pci: fix NULL pointer dereference in nvme_free_host_mem() nvme-rdma: fix memory leak during queue allocation blktrace: fix trace mutex deadlock nvme-rdma: Use mr pool nvme-rdma: Check remotely invalidated rkey matches our expected rkey nvme-rdma: wait for local invalidation before completing a request nvme-rdma: don't complete requests before a send work request has completed nvme-rdma: don't suppress send completions bcache: check return value of register_shrinker bcache: recover data from backing when data is clean bcache: Fix building error on MIPS bcache: add a comment in journal bucket reading nvme-fc: don't use bit masks for set/test_bit() numbers blk-wbt: fix comments typo blk-wbt: move wbt_clear_stat to common place in wbt_done blk-sysfs: remove NULL pointer checking in queue_wb_lat_store blk-wbt: remove duplicated setting in wbt_init nvme-pci: add quirk for delay before CHK RDY for WDC SN200 block: remove useless assignment in bio_split null_blk: fix dev->badblocks leak ...
This commit is contained in:
commit
75f64f68af
|
@ -1819,7 +1819,7 @@ EXPORT_SYMBOL(bio_endio);
|
|||
struct bio *bio_split(struct bio *bio, int sectors,
|
||||
gfp_t gfp, struct bio_set *bs)
|
||||
{
|
||||
struct bio *split = NULL;
|
||||
struct bio *split;
|
||||
|
||||
BUG_ON(sectors <= 0);
|
||||
BUG_ON(sectors >= bio_sectors(bio));
|
||||
|
|
|
@ -450,12 +450,9 @@ static ssize_t queue_wb_lat_store(struct request_queue *q, const char *page,
|
|||
ret = wbt_init(q);
|
||||
if (ret)
|
||||
return ret;
|
||||
|
||||
rwb = q->rq_wb;
|
||||
if (!rwb)
|
||||
return -EINVAL;
|
||||
}
|
||||
|
||||
rwb = q->rq_wb;
|
||||
if (val == -1)
|
||||
rwb->min_lat_nsec = wbt_default_latency_nsec(q);
|
||||
else if (val >= 0)
|
||||
|
|
|
@ -178,12 +178,11 @@ void wbt_done(struct rq_wb *rwb, struct blk_issue_stat *stat)
|
|||
|
||||
if (wbt_is_read(stat))
|
||||
wb_timestamp(rwb, &rwb->last_comp);
|
||||
wbt_clear_state(stat);
|
||||
} else {
|
||||
WARN_ON_ONCE(stat == rwb->sync_cookie);
|
||||
__wbt_done(rwb, wbt_stat_to_mask(stat));
|
||||
wbt_clear_state(stat);
|
||||
}
|
||||
wbt_clear_state(stat);
|
||||
}
|
||||
|
||||
/*
|
||||
|
@ -482,7 +481,7 @@ static inline unsigned int get_limit(struct rq_wb *rwb, unsigned long rw)
|
|||
|
||||
/*
|
||||
* At this point we know it's a buffered write. If this is
|
||||
* kswapd trying to free memory, or REQ_SYNC is set, set, then
|
||||
* kswapd trying to free memory, or REQ_SYNC is set, then
|
||||
* it's WB_SYNC_ALL writeback, and we'll use the max limit for
|
||||
* that. If the write is marked as a background write, then use
|
||||
* the idle limit, or go to normal if we haven't had competing
|
||||
|
@ -723,8 +722,6 @@ int wbt_init(struct request_queue *q)
|
|||
init_waitqueue_head(&rwb->rq_wait[i].wait);
|
||||
}
|
||||
|
||||
rwb->wc = 1;
|
||||
rwb->queue_depth = RWB_DEF_DEPTH;
|
||||
rwb->last_comp = rwb->last_issue = jiffies;
|
||||
rwb->queue = q;
|
||||
rwb->win_nsec = RWB_WINDOW_NSEC;
|
||||
|
|
|
@ -671,10 +671,13 @@ void device_add_disk(struct device *parent, struct gendisk *disk)
|
|||
disk->flags |= GENHD_FL_SUPPRESS_PARTITION_INFO;
|
||||
disk->flags |= GENHD_FL_NO_PART_SCAN;
|
||||
} else {
|
||||
int ret;
|
||||
|
||||
/* Register BDI before referencing it from bdev */
|
||||
disk_to_dev(disk)->devt = devt;
|
||||
bdi_register_owner(disk->queue->backing_dev_info,
|
||||
disk_to_dev(disk));
|
||||
ret = bdi_register_owner(disk->queue->backing_dev_info,
|
||||
disk_to_dev(disk));
|
||||
WARN_ON(ret);
|
||||
blk_register_region(disk_devt(disk), disk->minors, NULL,
|
||||
exact_match, exact_lock, disk);
|
||||
}
|
||||
|
@ -1389,7 +1392,7 @@ struct gendisk *__alloc_disk_node(int minors, int node_id)
|
|||
|
||||
if (minors > DISK_MAX_PARTS) {
|
||||
printk(KERN_ERR
|
||||
"block: can't allocated more than %d partitions\n",
|
||||
"block: can't allocate more than %d partitions\n",
|
||||
DISK_MAX_PARTS);
|
||||
minors = DISK_MAX_PARTS;
|
||||
}
|
||||
|
|
|
@ -471,7 +471,6 @@ static void nullb_device_release(struct config_item *item)
|
|||
{
|
||||
struct nullb_device *dev = to_nullb_device(item);
|
||||
|
||||
badblocks_exit(&dev->badblocks);
|
||||
null_free_device_storage(dev, false);
|
||||
null_free_dev(dev);
|
||||
}
|
||||
|
@ -582,6 +581,10 @@ static struct nullb_device *null_alloc_dev(void)
|
|||
|
||||
static void null_free_dev(struct nullb_device *dev)
|
||||
{
|
||||
if (!dev)
|
||||
return;
|
||||
|
||||
badblocks_exit(&dev->badblocks);
|
||||
kfree(dev);
|
||||
}
|
||||
|
||||
|
|
|
@ -490,7 +490,7 @@ int __bch_bucket_alloc_set(struct cache_set *c, unsigned reserve,
|
|||
if (b == -1)
|
||||
goto err;
|
||||
|
||||
k->ptr[i] = PTR(ca->buckets[b].gen,
|
||||
k->ptr[i] = MAKE_PTR(ca->buckets[b].gen,
|
||||
bucket_to_sector(c, b),
|
||||
ca->sb.nr_this_dev);
|
||||
|
||||
|
|
|
@ -807,7 +807,10 @@ int bch_btree_cache_alloc(struct cache_set *c)
|
|||
c->shrink.scan_objects = bch_mca_scan;
|
||||
c->shrink.seeks = 4;
|
||||
c->shrink.batch = c->btree_pages * 2;
|
||||
register_shrinker(&c->shrink);
|
||||
|
||||
if (register_shrinker(&c->shrink))
|
||||
pr_warn("bcache: %s: could not register shrinker",
|
||||
__func__);
|
||||
|
||||
return 0;
|
||||
}
|
||||
|
|
|
@ -585,7 +585,7 @@ static bool bch_extent_merge(struct btree_keys *bk, struct bkey *l, struct bkey
|
|||
return false;
|
||||
|
||||
for (i = 0; i < KEY_PTRS(l); i++)
|
||||
if (l->ptr[i] + PTR(0, KEY_SIZE(l), 0) != r->ptr[i] ||
|
||||
if (l->ptr[i] + MAKE_PTR(0, KEY_SIZE(l), 0) != r->ptr[i] ||
|
||||
PTR_BUCKET_NR(b->c, l, i) != PTR_BUCKET_NR(b->c, r, i))
|
||||
return false;
|
||||
|
||||
|
|
|
@ -170,6 +170,11 @@ int bch_journal_read(struct cache_set *c, struct list_head *list)
|
|||
* find a sequence of buckets with valid journal entries
|
||||
*/
|
||||
for (i = 0; i < ca->sb.njournal_buckets; i++) {
|
||||
/*
|
||||
* We must try the index l with ZERO first for
|
||||
* correctness due to the scenario that the journal
|
||||
* bucket is circular buffer which might have wrapped
|
||||
*/
|
||||
l = (i * 2654435769U) % ca->sb.njournal_buckets;
|
||||
|
||||
if (test_bit(l, bitmap))
|
||||
|
@ -507,7 +512,7 @@ static void journal_reclaim(struct cache_set *c)
|
|||
continue;
|
||||
|
||||
ja->cur_idx = next;
|
||||
k->ptr[n++] = PTR(0,
|
||||
k->ptr[n++] = MAKE_PTR(0,
|
||||
bucket_to_sector(c, ca->sb.d[ja->cur_idx]),
|
||||
ca->sb.nr_this_dev);
|
||||
}
|
||||
|
|
|
@ -708,16 +708,15 @@ static void cached_dev_read_error(struct closure *cl)
|
|||
{
|
||||
struct search *s = container_of(cl, struct search, cl);
|
||||
struct bio *bio = &s->bio.bio;
|
||||
struct cached_dev *dc = container_of(s->d, struct cached_dev, disk);
|
||||
|
||||
/*
|
||||
* If cache device is dirty (dc->has_dirty is non-zero), then
|
||||
* recovery a failed read request from cached device may get a
|
||||
* stale data back. So read failure recovery is only permitted
|
||||
* when cache device is clean.
|
||||
* If read request hit dirty data (s->read_dirty_data is true),
|
||||
* then recovery a failed read request from cached device may
|
||||
* get a stale data back. So read failure recovery is only
|
||||
* permitted when read request hit clean data in cache device,
|
||||
* or when cache read race happened.
|
||||
*/
|
||||
if (s->recoverable &&
|
||||
(dc && !atomic_read(&dc->has_dirty))) {
|
||||
if (s->recoverable && !s->read_dirty_data) {
|
||||
/* Retry from the backing device: */
|
||||
trace_bcache_read_retry(s->orig_bio);
|
||||
|
||||
|
|
|
@ -1449,19 +1449,19 @@ static int nvme_pr_command(struct block_device *bdev, u32 cdw10,
|
|||
int srcu_idx, ret;
|
||||
u8 data[16] = { 0, };
|
||||
|
||||
ns = nvme_get_ns_from_disk(bdev->bd_disk, &head, &srcu_idx);
|
||||
if (unlikely(!ns))
|
||||
return -EWOULDBLOCK;
|
||||
|
||||
put_unaligned_le64(key, &data[0]);
|
||||
put_unaligned_le64(sa_key, &data[8]);
|
||||
|
||||
memset(&c, 0, sizeof(c));
|
||||
c.common.opcode = op;
|
||||
c.common.nsid = cpu_to_le32(head->ns_id);
|
||||
c.common.nsid = cpu_to_le32(ns->head->ns_id);
|
||||
c.common.cdw10[0] = cpu_to_le32(cdw10);
|
||||
|
||||
ns = nvme_get_ns_from_disk(bdev->bd_disk, &head, &srcu_idx);
|
||||
if (unlikely(!ns))
|
||||
ret = -EWOULDBLOCK;
|
||||
else
|
||||
ret = nvme_submit_sync_cmd(ns->queue, &c, data, 16);
|
||||
ret = nvme_submit_sync_cmd(ns->queue, &c, data, 16);
|
||||
nvme_put_ns_from_disk(head, srcu_idx);
|
||||
return ret;
|
||||
}
|
||||
|
@ -2961,8 +2961,6 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid)
|
|||
|
||||
static void nvme_ns_remove(struct nvme_ns *ns)
|
||||
{
|
||||
struct nvme_ns_head *head = ns->head;
|
||||
|
||||
if (test_and_set_bit(NVME_NS_REMOVING, &ns->flags))
|
||||
return;
|
||||
|
||||
|
@ -2980,15 +2978,14 @@ static void nvme_ns_remove(struct nvme_ns *ns)
|
|||
|
||||
mutex_lock(&ns->ctrl->subsys->lock);
|
||||
nvme_mpath_clear_current_path(ns);
|
||||
if (head)
|
||||
list_del_rcu(&ns->siblings);
|
||||
list_del_rcu(&ns->siblings);
|
||||
mutex_unlock(&ns->ctrl->subsys->lock);
|
||||
|
||||
mutex_lock(&ns->ctrl->namespaces_mutex);
|
||||
list_del_init(&ns->list);
|
||||
mutex_unlock(&ns->ctrl->namespaces_mutex);
|
||||
|
||||
synchronize_srcu(&head->srcu);
|
||||
synchronize_srcu(&ns->head->srcu);
|
||||
nvme_put_ns(ns);
|
||||
}
|
||||
|
||||
|
|
|
@ -156,4 +156,34 @@ void nvmf_free_options(struct nvmf_ctrl_options *opts);
|
|||
int nvmf_get_address(struct nvme_ctrl *ctrl, char *buf, int size);
|
||||
bool nvmf_should_reconnect(struct nvme_ctrl *ctrl);
|
||||
|
||||
static inline blk_status_t nvmf_check_init_req(struct nvme_ctrl *ctrl,
|
||||
struct request *rq)
|
||||
{
|
||||
struct nvme_command *cmd = nvme_req(rq)->cmd;
|
||||
|
||||
/*
|
||||
* We cannot accept any other command until the connect command has
|
||||
* completed, so only allow connect to pass.
|
||||
*/
|
||||
if (!blk_rq_is_passthrough(rq) ||
|
||||
cmd->common.opcode != nvme_fabrics_command ||
|
||||
cmd->fabrics.fctype != nvme_fabrics_type_connect) {
|
||||
/*
|
||||
* Reconnecting state means transport disruption, which can take
|
||||
* a long time and even might fail permanently, fail fast to
|
||||
* give upper layers a chance to failover.
|
||||
* Deleting state means that the ctrl will never accept commands
|
||||
* again, fail it permanently.
|
||||
*/
|
||||
if (ctrl->state == NVME_CTRL_RECONNECTING ||
|
||||
ctrl->state == NVME_CTRL_DELETING) {
|
||||
nvme_req(rq)->status = NVME_SC_ABORT_REQ;
|
||||
return BLK_STS_IOERR;
|
||||
}
|
||||
return BLK_STS_RESOURCE; /* try again later */
|
||||
}
|
||||
|
||||
return BLK_STS_OK;
|
||||
}
|
||||
|
||||
#endif /* _NVME_FABRICS_H */
|
||||
|
|
|
@ -31,7 +31,8 @@
|
|||
|
||||
|
||||
enum nvme_fc_queue_flags {
|
||||
NVME_FC_Q_CONNECTED = (1 << 0),
|
||||
NVME_FC_Q_CONNECTED = 0,
|
||||
NVME_FC_Q_LIVE,
|
||||
};
|
||||
|
||||
#define NVMEFC_QUEUE_DELAY 3 /* ms units */
|
||||
|
@ -1927,6 +1928,7 @@ nvme_fc_free_queue(struct nvme_fc_queue *queue)
|
|||
if (!test_and_clear_bit(NVME_FC_Q_CONNECTED, &queue->flags))
|
||||
return;
|
||||
|
||||
clear_bit(NVME_FC_Q_LIVE, &queue->flags);
|
||||
/*
|
||||
* Current implementation never disconnects a single queue.
|
||||
* It always terminates a whole association. So there is never
|
||||
|
@ -1934,7 +1936,6 @@ nvme_fc_free_queue(struct nvme_fc_queue *queue)
|
|||
*/
|
||||
|
||||
queue->connection_id = 0;
|
||||
clear_bit(NVME_FC_Q_CONNECTED, &queue->flags);
|
||||
}
|
||||
|
||||
static void
|
||||
|
@ -2013,6 +2014,8 @@ nvme_fc_connect_io_queues(struct nvme_fc_ctrl *ctrl, u16 qsize)
|
|||
ret = nvmf_connect_io_queue(&ctrl->ctrl, i);
|
||||
if (ret)
|
||||
break;
|
||||
|
||||
set_bit(NVME_FC_Q_LIVE, &ctrl->queues[i].flags);
|
||||
}
|
||||
|
||||
return ret;
|
||||
|
@ -2320,6 +2323,14 @@ busy:
|
|||
return BLK_STS_RESOURCE;
|
||||
}
|
||||
|
||||
static inline blk_status_t nvme_fc_is_ready(struct nvme_fc_queue *queue,
|
||||
struct request *rq)
|
||||
{
|
||||
if (unlikely(!test_bit(NVME_FC_Q_LIVE, &queue->flags)))
|
||||
return nvmf_check_init_req(&queue->ctrl->ctrl, rq);
|
||||
return BLK_STS_OK;
|
||||
}
|
||||
|
||||
static blk_status_t
|
||||
nvme_fc_queue_rq(struct blk_mq_hw_ctx *hctx,
|
||||
const struct blk_mq_queue_data *bd)
|
||||
|
@ -2335,6 +2346,10 @@ nvme_fc_queue_rq(struct blk_mq_hw_ctx *hctx,
|
|||
u32 data_len;
|
||||
blk_status_t ret;
|
||||
|
||||
ret = nvme_fc_is_ready(queue, rq);
|
||||
if (unlikely(ret))
|
||||
return ret;
|
||||
|
||||
ret = nvme_setup_cmd(ns, rq, sqe);
|
||||
if (ret)
|
||||
return ret;
|
||||
|
@ -2727,6 +2742,8 @@ nvme_fc_create_association(struct nvme_fc_ctrl *ctrl)
|
|||
if (ret)
|
||||
goto out_disconnect_admin_queue;
|
||||
|
||||
set_bit(NVME_FC_Q_LIVE, &ctrl->queues[0].flags);
|
||||
|
||||
/*
|
||||
* Check controller capabilities
|
||||
*
|
||||
|
|
|
@ -131,7 +131,7 @@ static blk_qc_t nvme_ns_head_make_request(struct request_queue *q,
|
|||
bio->bi_opf |= REQ_NVME_MPATH;
|
||||
ret = direct_make_request(bio);
|
||||
} else if (!list_empty_careful(&head->list)) {
|
||||
dev_warn_ratelimited(dev, "no path available - requeing I/O\n");
|
||||
dev_warn_ratelimited(dev, "no path available - requeuing I/O\n");
|
||||
|
||||
spin_lock_irq(&head->requeue_lock);
|
||||
bio_list_add(&head->requeue_list, bio);
|
||||
|
|
|
@ -114,7 +114,7 @@ static inline struct nvme_request *nvme_req(struct request *req)
|
|||
* NVME_QUIRK_DELAY_BEFORE_CHK_RDY quirk enabled. The value (in ms) was
|
||||
* found empirically.
|
||||
*/
|
||||
#define NVME_QUIRK_DELAY_AMOUNT 2000
|
||||
#define NVME_QUIRK_DELAY_AMOUNT 2300
|
||||
|
||||
enum nvme_ctrl_state {
|
||||
NVME_CTRL_NEW,
|
||||
|
|
|
@ -1759,6 +1759,7 @@ static void nvme_free_host_mem(struct nvme_dev *dev)
|
|||
dev->nr_host_mem_descs * sizeof(*dev->host_mem_descs),
|
||||
dev->host_mem_descs, dev->host_mem_descs_dma);
|
||||
dev->host_mem_descs = NULL;
|
||||
dev->nr_host_mem_descs = 0;
|
||||
}
|
||||
|
||||
static int __nvme_alloc_host_mem(struct nvme_dev *dev, u64 preferred,
|
||||
|
@ -1787,7 +1788,7 @@ static int __nvme_alloc_host_mem(struct nvme_dev *dev, u64 preferred,
|
|||
if (!bufs)
|
||||
goto out_free_descs;
|
||||
|
||||
for (size = 0; size < preferred; size += len) {
|
||||
for (size = 0; size < preferred && i < max_entries; size += len) {
|
||||
dma_addr_t dma_addr;
|
||||
|
||||
len = min_t(u64, chunk_size, preferred - size);
|
||||
|
@ -2428,7 +2429,7 @@ static int nvme_dev_map(struct nvme_dev *dev)
|
|||
return -ENODEV;
|
||||
}
|
||||
|
||||
static unsigned long check_dell_samsung_bug(struct pci_dev *pdev)
|
||||
static unsigned long check_vendor_combination_bug(struct pci_dev *pdev)
|
||||
{
|
||||
if (pdev->vendor == 0x144d && pdev->device == 0xa802) {
|
||||
/*
|
||||
|
@ -2443,6 +2444,14 @@ static unsigned long check_dell_samsung_bug(struct pci_dev *pdev)
|
|||
(dmi_match(DMI_PRODUCT_NAME, "XPS 15 9550") ||
|
||||
dmi_match(DMI_PRODUCT_NAME, "Precision 5510")))
|
||||
return NVME_QUIRK_NO_DEEPEST_PS;
|
||||
} else if (pdev->vendor == 0x144d && pdev->device == 0xa804) {
|
||||
/*
|
||||
* Samsung SSD 960 EVO drops off the PCIe bus after system
|
||||
* suspend on a Ryzen board, ASUS PRIME B350M-A.
|
||||
*/
|
||||
if (dmi_match(DMI_BOARD_VENDOR, "ASUSTeK COMPUTER INC.") &&
|
||||
dmi_match(DMI_BOARD_NAME, "PRIME B350M-A"))
|
||||
return NVME_QUIRK_NO_APST;
|
||||
}
|
||||
|
||||
return 0;
|
||||
|
@ -2482,7 +2491,7 @@ static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id)
|
|||
if (result)
|
||||
goto unmap;
|
||||
|
||||
quirks |= check_dell_samsung_bug(pdev);
|
||||
quirks |= check_vendor_combination_bug(pdev);
|
||||
|
||||
result = nvme_init_ctrl(&dev->ctrl, &pdev->dev, &nvme_pci_ctrl_ops,
|
||||
quirks);
|
||||
|
@ -2665,6 +2674,8 @@ static const struct pci_device_id nvme_id_table[] = {
|
|||
.driver_data = NVME_QUIRK_IDENTIFY_CNS, },
|
||||
{ PCI_DEVICE(0x1c58, 0x0003), /* HGST adapter */
|
||||
.driver_data = NVME_QUIRK_DELAY_BEFORE_CHK_RDY, },
|
||||
{ PCI_DEVICE(0x1c58, 0x0023), /* WDC SN200 adapter */
|
||||
.driver_data = NVME_QUIRK_DELAY_BEFORE_CHK_RDY, },
|
||||
{ PCI_DEVICE(0x1c5f, 0x0540), /* Memblaze Pblaze4 adapter */
|
||||
.driver_data = NVME_QUIRK_DELAY_BEFORE_CHK_RDY, },
|
||||
{ PCI_DEVICE(0x144d, 0xa821), /* Samsung PM1725 */
|
||||
|
|
|
@ -15,6 +15,7 @@
|
|||
#include <linux/module.h>
|
||||
#include <linux/init.h>
|
||||
#include <linux/slab.h>
|
||||
#include <rdma/mr_pool.h>
|
||||
#include <linux/err.h>
|
||||
#include <linux/string.h>
|
||||
#include <linux/atomic.h>
|
||||
|
@ -59,6 +60,9 @@ struct nvme_rdma_request {
|
|||
struct nvme_request req;
|
||||
struct ib_mr *mr;
|
||||
struct nvme_rdma_qe sqe;
|
||||
union nvme_result result;
|
||||
__le16 status;
|
||||
refcount_t ref;
|
||||
struct ib_sge sge[1 + NVME_RDMA_MAX_INLINE_SEGMENTS];
|
||||
u32 num_sge;
|
||||
int nents;
|
||||
|
@ -73,11 +77,11 @@ struct nvme_rdma_request {
|
|||
enum nvme_rdma_queue_flags {
|
||||
NVME_RDMA_Q_ALLOCATED = 0,
|
||||
NVME_RDMA_Q_LIVE = 1,
|
||||
NVME_RDMA_Q_TR_READY = 2,
|
||||
};
|
||||
|
||||
struct nvme_rdma_queue {
|
||||
struct nvme_rdma_qe *rsp_ring;
|
||||
atomic_t sig_count;
|
||||
int queue_size;
|
||||
size_t cmnd_capsule_len;
|
||||
struct nvme_rdma_ctrl *ctrl;
|
||||
|
@ -258,32 +262,6 @@ static int nvme_rdma_create_qp(struct nvme_rdma_queue *queue, const int factor)
|
|||
return ret;
|
||||
}
|
||||
|
||||
static int nvme_rdma_reinit_request(void *data, struct request *rq)
|
||||
{
|
||||
struct nvme_rdma_ctrl *ctrl = data;
|
||||
struct nvme_rdma_device *dev = ctrl->device;
|
||||
struct nvme_rdma_request *req = blk_mq_rq_to_pdu(rq);
|
||||
int ret = 0;
|
||||
|
||||
if (WARN_ON_ONCE(!req->mr))
|
||||
return 0;
|
||||
|
||||
ib_dereg_mr(req->mr);
|
||||
|
||||
req->mr = ib_alloc_mr(dev->pd, IB_MR_TYPE_MEM_REG,
|
||||
ctrl->max_fr_pages);
|
||||
if (IS_ERR(req->mr)) {
|
||||
ret = PTR_ERR(req->mr);
|
||||
req->mr = NULL;
|
||||
goto out;
|
||||
}
|
||||
|
||||
req->mr->need_inval = false;
|
||||
|
||||
out:
|
||||
return ret;
|
||||
}
|
||||
|
||||
static void nvme_rdma_exit_request(struct blk_mq_tag_set *set,
|
||||
struct request *rq, unsigned int hctx_idx)
|
||||
{
|
||||
|
@ -293,9 +271,6 @@ static void nvme_rdma_exit_request(struct blk_mq_tag_set *set,
|
|||
struct nvme_rdma_queue *queue = &ctrl->queues[queue_idx];
|
||||
struct nvme_rdma_device *dev = queue->device;
|
||||
|
||||
if (req->mr)
|
||||
ib_dereg_mr(req->mr);
|
||||
|
||||
nvme_rdma_free_qe(dev->dev, &req->sqe, sizeof(struct nvme_command),
|
||||
DMA_TO_DEVICE);
|
||||
}
|
||||
|
@ -317,21 +292,9 @@ static int nvme_rdma_init_request(struct blk_mq_tag_set *set,
|
|||
if (ret)
|
||||
return ret;
|
||||
|
||||
req->mr = ib_alloc_mr(dev->pd, IB_MR_TYPE_MEM_REG,
|
||||
ctrl->max_fr_pages);
|
||||
if (IS_ERR(req->mr)) {
|
||||
ret = PTR_ERR(req->mr);
|
||||
goto out_free_qe;
|
||||
}
|
||||
|
||||
req->queue = queue;
|
||||
|
||||
return 0;
|
||||
|
||||
out_free_qe:
|
||||
nvme_rdma_free_qe(dev->dev, &req->sqe, sizeof(struct nvme_command),
|
||||
DMA_TO_DEVICE);
|
||||
return -ENOMEM;
|
||||
}
|
||||
|
||||
static int nvme_rdma_init_hctx(struct blk_mq_hw_ctx *hctx, void *data,
|
||||
|
@ -428,10 +391,23 @@ out_err:
|
|||
|
||||
static void nvme_rdma_destroy_queue_ib(struct nvme_rdma_queue *queue)
|
||||
{
|
||||
struct nvme_rdma_device *dev = queue->device;
|
||||
struct ib_device *ibdev = dev->dev;
|
||||
struct nvme_rdma_device *dev;
|
||||
struct ib_device *ibdev;
|
||||
|
||||
rdma_destroy_qp(queue->cm_id);
|
||||
if (!test_and_clear_bit(NVME_RDMA_Q_TR_READY, &queue->flags))
|
||||
return;
|
||||
|
||||
dev = queue->device;
|
||||
ibdev = dev->dev;
|
||||
|
||||
ib_mr_pool_destroy(queue->qp, &queue->qp->rdma_mrs);
|
||||
|
||||
/*
|
||||
* The cm_id object might have been destroyed during RDMA connection
|
||||
* establishment error flow to avoid getting other cma events, thus
|
||||
* the destruction of the QP shouldn't use rdma_cm API.
|
||||
*/
|
||||
ib_destroy_qp(queue->qp);
|
||||
ib_free_cq(queue->ib_cq);
|
||||
|
||||
nvme_rdma_free_ring(ibdev, queue->rsp_ring, queue->queue_size,
|
||||
|
@ -440,6 +416,12 @@ static void nvme_rdma_destroy_queue_ib(struct nvme_rdma_queue *queue)
|
|||
nvme_rdma_dev_put(dev);
|
||||
}
|
||||
|
||||
static int nvme_rdma_get_max_fr_pages(struct ib_device *ibdev)
|
||||
{
|
||||
return min_t(u32, NVME_RDMA_MAX_SEGMENTS,
|
||||
ibdev->attrs.max_fast_reg_page_list_len);
|
||||
}
|
||||
|
||||
static int nvme_rdma_create_queue_ib(struct nvme_rdma_queue *queue)
|
||||
{
|
||||
struct ib_device *ibdev;
|
||||
|
@ -482,8 +464,24 @@ static int nvme_rdma_create_queue_ib(struct nvme_rdma_queue *queue)
|
|||
goto out_destroy_qp;
|
||||
}
|
||||
|
||||
ret = ib_mr_pool_init(queue->qp, &queue->qp->rdma_mrs,
|
||||
queue->queue_size,
|
||||
IB_MR_TYPE_MEM_REG,
|
||||
nvme_rdma_get_max_fr_pages(ibdev));
|
||||
if (ret) {
|
||||
dev_err(queue->ctrl->ctrl.device,
|
||||
"failed to initialize MR pool sized %d for QID %d\n",
|
||||
queue->queue_size, idx);
|
||||
goto out_destroy_ring;
|
||||
}
|
||||
|
||||
set_bit(NVME_RDMA_Q_TR_READY, &queue->flags);
|
||||
|
||||
return 0;
|
||||
|
||||
out_destroy_ring:
|
||||
nvme_rdma_free_ring(ibdev, queue->rsp_ring, queue->queue_size,
|
||||
sizeof(struct nvme_completion), DMA_FROM_DEVICE);
|
||||
out_destroy_qp:
|
||||
rdma_destroy_qp(queue->cm_id);
|
||||
out_destroy_ib_cq:
|
||||
|
@ -510,7 +508,6 @@ static int nvme_rdma_alloc_queue(struct nvme_rdma_ctrl *ctrl,
|
|||
queue->cmnd_capsule_len = sizeof(struct nvme_command);
|
||||
|
||||
queue->queue_size = queue_size;
|
||||
atomic_set(&queue->sig_count, 0);
|
||||
|
||||
queue->cm_id = rdma_create_id(&init_net, nvme_rdma_cm_handler, queue,
|
||||
RDMA_PS_TCP, IB_QPT_RC);
|
||||
|
@ -546,6 +543,7 @@ static int nvme_rdma_alloc_queue(struct nvme_rdma_ctrl *ctrl,
|
|||
|
||||
out_destroy_cm_id:
|
||||
rdma_destroy_id(queue->cm_id);
|
||||
nvme_rdma_destroy_queue_ib(queue);
|
||||
return ret;
|
||||
}
|
||||
|
||||
|
@ -756,8 +754,7 @@ static int nvme_rdma_configure_admin_queue(struct nvme_rdma_ctrl *ctrl,
|
|||
|
||||
ctrl->device = ctrl->queues[0].device;
|
||||
|
||||
ctrl->max_fr_pages = min_t(u32, NVME_RDMA_MAX_SEGMENTS,
|
||||
ctrl->device->dev->attrs.max_fast_reg_page_list_len);
|
||||
ctrl->max_fr_pages = nvme_rdma_get_max_fr_pages(ctrl->device->dev);
|
||||
|
||||
if (new) {
|
||||
ctrl->ctrl.admin_tagset = nvme_rdma_alloc_tagset(&ctrl->ctrl, true);
|
||||
|
@ -771,10 +768,6 @@ static int nvme_rdma_configure_admin_queue(struct nvme_rdma_ctrl *ctrl,
|
|||
error = PTR_ERR(ctrl->ctrl.admin_q);
|
||||
goto out_free_tagset;
|
||||
}
|
||||
} else {
|
||||
error = nvme_reinit_tagset(&ctrl->ctrl, ctrl->ctrl.admin_tagset);
|
||||
if (error)
|
||||
goto out_free_queue;
|
||||
}
|
||||
|
||||
error = nvme_rdma_start_queue(ctrl, 0);
|
||||
|
@ -854,10 +847,6 @@ static int nvme_rdma_configure_io_queues(struct nvme_rdma_ctrl *ctrl, bool new)
|
|||
goto out_free_tag_set;
|
||||
}
|
||||
} else {
|
||||
ret = nvme_reinit_tagset(&ctrl->ctrl, ctrl->ctrl.tagset);
|
||||
if (ret)
|
||||
goto out_free_io_queues;
|
||||
|
||||
blk_mq_update_nr_hw_queues(&ctrl->tag_set,
|
||||
ctrl->ctrl.queue_count - 1);
|
||||
}
|
||||
|
@ -1018,8 +1007,18 @@ static void nvme_rdma_memreg_done(struct ib_cq *cq, struct ib_wc *wc)
|
|||
|
||||
static void nvme_rdma_inv_rkey_done(struct ib_cq *cq, struct ib_wc *wc)
|
||||
{
|
||||
if (unlikely(wc->status != IB_WC_SUCCESS))
|
||||
struct nvme_rdma_request *req =
|
||||
container_of(wc->wr_cqe, struct nvme_rdma_request, reg_cqe);
|
||||
struct request *rq = blk_mq_rq_from_pdu(req);
|
||||
|
||||
if (unlikely(wc->status != IB_WC_SUCCESS)) {
|
||||
nvme_rdma_wr_error(cq, wc, "LOCAL_INV");
|
||||
return;
|
||||
}
|
||||
|
||||
if (refcount_dec_and_test(&req->ref))
|
||||
nvme_end_request(rq, req->status, req->result);
|
||||
|
||||
}
|
||||
|
||||
static int nvme_rdma_inv_rkey(struct nvme_rdma_queue *queue,
|
||||
|
@ -1030,7 +1029,7 @@ static int nvme_rdma_inv_rkey(struct nvme_rdma_queue *queue,
|
|||
.opcode = IB_WR_LOCAL_INV,
|
||||
.next = NULL,
|
||||
.num_sge = 0,
|
||||
.send_flags = 0,
|
||||
.send_flags = IB_SEND_SIGNALED,
|
||||
.ex.invalidate_rkey = req->mr->rkey,
|
||||
};
|
||||
|
||||
|
@ -1044,22 +1043,15 @@ static void nvme_rdma_unmap_data(struct nvme_rdma_queue *queue,
|
|||
struct request *rq)
|
||||
{
|
||||
struct nvme_rdma_request *req = blk_mq_rq_to_pdu(rq);
|
||||
struct nvme_rdma_ctrl *ctrl = queue->ctrl;
|
||||
struct nvme_rdma_device *dev = queue->device;
|
||||
struct ib_device *ibdev = dev->dev;
|
||||
int res;
|
||||
|
||||
if (!blk_rq_bytes(rq))
|
||||
return;
|
||||
|
||||
if (req->mr->need_inval && test_bit(NVME_RDMA_Q_LIVE, &req->queue->flags)) {
|
||||
res = nvme_rdma_inv_rkey(queue, req);
|
||||
if (unlikely(res < 0)) {
|
||||
dev_err(ctrl->ctrl.device,
|
||||
"Queueing INV WR for rkey %#x failed (%d)\n",
|
||||
req->mr->rkey, res);
|
||||
nvme_rdma_error_recovery(queue->ctrl);
|
||||
}
|
||||
if (req->mr) {
|
||||
ib_mr_pool_put(queue->qp, &queue->qp->rdma_mrs, req->mr);
|
||||
req->mr = NULL;
|
||||
}
|
||||
|
||||
ib_dma_unmap_sg(ibdev, req->sg_table.sgl,
|
||||
|
@ -1118,12 +1110,18 @@ static int nvme_rdma_map_sg_fr(struct nvme_rdma_queue *queue,
|
|||
struct nvme_keyed_sgl_desc *sg = &c->common.dptr.ksgl;
|
||||
int nr;
|
||||
|
||||
req->mr = ib_mr_pool_get(queue->qp, &queue->qp->rdma_mrs);
|
||||
if (WARN_ON_ONCE(!req->mr))
|
||||
return -EAGAIN;
|
||||
|
||||
/*
|
||||
* Align the MR to a 4K page size to match the ctrl page size and
|
||||
* the block virtual boundary.
|
||||
*/
|
||||
nr = ib_map_mr_sg(req->mr, req->sg_table.sgl, count, NULL, SZ_4K);
|
||||
if (unlikely(nr < count)) {
|
||||
ib_mr_pool_put(queue->qp, &queue->qp->rdma_mrs, req->mr);
|
||||
req->mr = NULL;
|
||||
if (nr < 0)
|
||||
return nr;
|
||||
return -EINVAL;
|
||||
|
@ -1142,8 +1140,6 @@ static int nvme_rdma_map_sg_fr(struct nvme_rdma_queue *queue,
|
|||
IB_ACCESS_REMOTE_READ |
|
||||
IB_ACCESS_REMOTE_WRITE;
|
||||
|
||||
req->mr->need_inval = true;
|
||||
|
||||
sg->addr = cpu_to_le64(req->mr->iova);
|
||||
put_unaligned_le24(req->mr->length, sg->length);
|
||||
put_unaligned_le32(req->mr->rkey, sg->key);
|
||||
|
@ -1163,7 +1159,7 @@ static int nvme_rdma_map_data(struct nvme_rdma_queue *queue,
|
|||
|
||||
req->num_sge = 1;
|
||||
req->inline_data = false;
|
||||
req->mr->need_inval = false;
|
||||
refcount_set(&req->ref, 2); /* send and recv completions */
|
||||
|
||||
c->common.flags |= NVME_CMD_SGL_METABUF;
|
||||
|
||||
|
@ -1200,25 +1196,24 @@ static int nvme_rdma_map_data(struct nvme_rdma_queue *queue,
|
|||
|
||||
static void nvme_rdma_send_done(struct ib_cq *cq, struct ib_wc *wc)
|
||||
{
|
||||
if (unlikely(wc->status != IB_WC_SUCCESS))
|
||||
struct nvme_rdma_qe *qe =
|
||||
container_of(wc->wr_cqe, struct nvme_rdma_qe, cqe);
|
||||
struct nvme_rdma_request *req =
|
||||
container_of(qe, struct nvme_rdma_request, sqe);
|
||||
struct request *rq = blk_mq_rq_from_pdu(req);
|
||||
|
||||
if (unlikely(wc->status != IB_WC_SUCCESS)) {
|
||||
nvme_rdma_wr_error(cq, wc, "SEND");
|
||||
}
|
||||
return;
|
||||
}
|
||||
|
||||
/*
|
||||
* We want to signal completion at least every queue depth/2. This returns the
|
||||
* largest power of two that is not above half of (queue size + 1) to optimize
|
||||
* (avoid divisions).
|
||||
*/
|
||||
static inline bool nvme_rdma_queue_sig_limit(struct nvme_rdma_queue *queue)
|
||||
{
|
||||
int limit = 1 << ilog2((queue->queue_size + 1) / 2);
|
||||
|
||||
return (atomic_inc_return(&queue->sig_count) & (limit - 1)) == 0;
|
||||
if (refcount_dec_and_test(&req->ref))
|
||||
nvme_end_request(rq, req->status, req->result);
|
||||
}
|
||||
|
||||
static int nvme_rdma_post_send(struct nvme_rdma_queue *queue,
|
||||
struct nvme_rdma_qe *qe, struct ib_sge *sge, u32 num_sge,
|
||||
struct ib_send_wr *first, bool flush)
|
||||
struct ib_send_wr *first)
|
||||
{
|
||||
struct ib_send_wr wr, *bad_wr;
|
||||
int ret;
|
||||
|
@ -1227,31 +1222,12 @@ static int nvme_rdma_post_send(struct nvme_rdma_queue *queue,
|
|||
sge->length = sizeof(struct nvme_command),
|
||||
sge->lkey = queue->device->pd->local_dma_lkey;
|
||||
|
||||
qe->cqe.done = nvme_rdma_send_done;
|
||||
|
||||
wr.next = NULL;
|
||||
wr.wr_cqe = &qe->cqe;
|
||||
wr.sg_list = sge;
|
||||
wr.num_sge = num_sge;
|
||||
wr.opcode = IB_WR_SEND;
|
||||
wr.send_flags = 0;
|
||||
|
||||
/*
|
||||
* Unsignalled send completions are another giant desaster in the
|
||||
* IB Verbs spec: If we don't regularly post signalled sends
|
||||
* the send queue will fill up and only a QP reset will rescue us.
|
||||
* Would have been way to obvious to handle this in hardware or
|
||||
* at least the RDMA stack..
|
||||
*
|
||||
* Always signal the flushes. The magic request used for the flush
|
||||
* sequencer is not allocated in our driver's tagset and it's
|
||||
* triggered to be freed by blk_cleanup_queue(). So we need to
|
||||
* always mark it as signaled to ensure that the "wr_cqe", which is
|
||||
* embedded in request's payload, is not freed when __ib_process_cq()
|
||||
* calls wr_cqe->done().
|
||||
*/
|
||||
if (nvme_rdma_queue_sig_limit(queue) || flush)
|
||||
wr.send_flags |= IB_SEND_SIGNALED;
|
||||
wr.send_flags = IB_SEND_SIGNALED;
|
||||
|
||||
if (first)
|
||||
first->next = ≀
|
||||
|
@ -1301,6 +1277,12 @@ static struct blk_mq_tags *nvme_rdma_tagset(struct nvme_rdma_queue *queue)
|
|||
return queue->ctrl->tag_set.tags[queue_idx - 1];
|
||||
}
|
||||
|
||||
static void nvme_rdma_async_done(struct ib_cq *cq, struct ib_wc *wc)
|
||||
{
|
||||
if (unlikely(wc->status != IB_WC_SUCCESS))
|
||||
nvme_rdma_wr_error(cq, wc, "ASYNC");
|
||||
}
|
||||
|
||||
static void nvme_rdma_submit_async_event(struct nvme_ctrl *arg)
|
||||
{
|
||||
struct nvme_rdma_ctrl *ctrl = to_rdma_ctrl(arg);
|
||||
|
@ -1319,10 +1301,12 @@ static void nvme_rdma_submit_async_event(struct nvme_ctrl *arg)
|
|||
cmd->common.flags |= NVME_CMD_SGL_METABUF;
|
||||
nvme_rdma_set_sg_null(cmd);
|
||||
|
||||
sqe->cqe.done = nvme_rdma_async_done;
|
||||
|
||||
ib_dma_sync_single_for_device(dev, sqe->dma, sizeof(*cmd),
|
||||
DMA_TO_DEVICE);
|
||||
|
||||
ret = nvme_rdma_post_send(queue, sqe, &sge, 1, NULL, false);
|
||||
ret = nvme_rdma_post_send(queue, sqe, &sge, 1, NULL);
|
||||
WARN_ON_ONCE(ret);
|
||||
}
|
||||
|
||||
|
@ -1343,14 +1327,34 @@ static int nvme_rdma_process_nvme_rsp(struct nvme_rdma_queue *queue,
|
|||
}
|
||||
req = blk_mq_rq_to_pdu(rq);
|
||||
|
||||
if (rq->tag == tag)
|
||||
ret = 1;
|
||||
req->status = cqe->status;
|
||||
req->result = cqe->result;
|
||||
|
||||
if ((wc->wc_flags & IB_WC_WITH_INVALIDATE) &&
|
||||
wc->ex.invalidate_rkey == req->mr->rkey)
|
||||
req->mr->need_inval = false;
|
||||
if (wc->wc_flags & IB_WC_WITH_INVALIDATE) {
|
||||
if (unlikely(wc->ex.invalidate_rkey != req->mr->rkey)) {
|
||||
dev_err(queue->ctrl->ctrl.device,
|
||||
"Bogus remote invalidation for rkey %#x\n",
|
||||
req->mr->rkey);
|
||||
nvme_rdma_error_recovery(queue->ctrl);
|
||||
}
|
||||
} else if (req->mr) {
|
||||
ret = nvme_rdma_inv_rkey(queue, req);
|
||||
if (unlikely(ret < 0)) {
|
||||
dev_err(queue->ctrl->ctrl.device,
|
||||
"Queueing INV WR for rkey %#x failed (%d)\n",
|
||||
req->mr->rkey, ret);
|
||||
nvme_rdma_error_recovery(queue->ctrl);
|
||||
}
|
||||
/* the local invalidation completion will end the request */
|
||||
return 0;
|
||||
}
|
||||
|
||||
if (refcount_dec_and_test(&req->ref)) {
|
||||
if (rq->tag == tag)
|
||||
ret = 1;
|
||||
nvme_end_request(rq, req->status, req->result);
|
||||
}
|
||||
|
||||
nvme_end_request(rq, cqe->status, cqe->result);
|
||||
return ret;
|
||||
}
|
||||
|
||||
|
@ -1591,31 +1595,11 @@ nvme_rdma_timeout(struct request *rq, bool reserved)
|
|||
* We cannot accept any other command until the Connect command has completed.
|
||||
*/
|
||||
static inline blk_status_t
|
||||
nvme_rdma_queue_is_ready(struct nvme_rdma_queue *queue, struct request *rq)
|
||||
nvme_rdma_is_ready(struct nvme_rdma_queue *queue, struct request *rq)
|
||||
{
|
||||
if (unlikely(!test_bit(NVME_RDMA_Q_LIVE, &queue->flags))) {
|
||||
struct nvme_command *cmd = nvme_req(rq)->cmd;
|
||||
|
||||
if (!blk_rq_is_passthrough(rq) ||
|
||||
cmd->common.opcode != nvme_fabrics_command ||
|
||||
cmd->fabrics.fctype != nvme_fabrics_type_connect) {
|
||||
/*
|
||||
* reconnecting state means transport disruption, which
|
||||
* can take a long time and even might fail permanently,
|
||||
* fail fast to give upper layers a chance to failover.
|
||||
* deleting state means that the ctrl will never accept
|
||||
* commands again, fail it permanently.
|
||||
*/
|
||||
if (queue->ctrl->ctrl.state == NVME_CTRL_RECONNECTING ||
|
||||
queue->ctrl->ctrl.state == NVME_CTRL_DELETING) {
|
||||
nvme_req(rq)->status = NVME_SC_ABORT_REQ;
|
||||
return BLK_STS_IOERR;
|
||||
}
|
||||
return BLK_STS_RESOURCE; /* try again later */
|
||||
}
|
||||
}
|
||||
|
||||
return 0;
|
||||
if (unlikely(!test_bit(NVME_RDMA_Q_LIVE, &queue->flags)))
|
||||
return nvmf_check_init_req(&queue->ctrl->ctrl, rq);
|
||||
return BLK_STS_OK;
|
||||
}
|
||||
|
||||
static blk_status_t nvme_rdma_queue_rq(struct blk_mq_hw_ctx *hctx,
|
||||
|
@ -1627,14 +1611,13 @@ static blk_status_t nvme_rdma_queue_rq(struct blk_mq_hw_ctx *hctx,
|
|||
struct nvme_rdma_request *req = blk_mq_rq_to_pdu(rq);
|
||||
struct nvme_rdma_qe *sqe = &req->sqe;
|
||||
struct nvme_command *c = sqe->data;
|
||||
bool flush = false;
|
||||
struct ib_device *dev;
|
||||
blk_status_t ret;
|
||||
int err;
|
||||
|
||||
WARN_ON_ONCE(rq->tag < 0);
|
||||
|
||||
ret = nvme_rdma_queue_is_ready(queue, rq);
|
||||
ret = nvme_rdma_is_ready(queue, rq);
|
||||
if (unlikely(ret))
|
||||
return ret;
|
||||
|
||||
|
@ -1656,13 +1639,13 @@ static blk_status_t nvme_rdma_queue_rq(struct blk_mq_hw_ctx *hctx,
|
|||
goto err;
|
||||
}
|
||||
|
||||
sqe->cqe.done = nvme_rdma_send_done;
|
||||
|
||||
ib_dma_sync_single_for_device(dev, sqe->dma,
|
||||
sizeof(struct nvme_command), DMA_TO_DEVICE);
|
||||
|
||||
if (req_op(rq) == REQ_OP_FLUSH)
|
||||
flush = true;
|
||||
err = nvme_rdma_post_send(queue, sqe, req->sge, req->num_sge,
|
||||
req->mr->need_inval ? &req->reg_wr.wr : NULL, flush);
|
||||
req->mr ? &req->reg_wr.wr : NULL);
|
||||
if (unlikely(err)) {
|
||||
nvme_rdma_unmap_data(queue, rq);
|
||||
goto err;
|
||||
|
@ -1810,7 +1793,6 @@ static const struct nvme_ctrl_ops nvme_rdma_ctrl_ops = {
|
|||
.submit_async_event = nvme_rdma_submit_async_event,
|
||||
.delete_ctrl = nvme_rdma_delete_ctrl,
|
||||
.get_address = nvmf_get_address,
|
||||
.reinit_request = nvme_rdma_reinit_request,
|
||||
};
|
||||
|
||||
static inline bool
|
||||
|
|
|
@ -533,15 +533,15 @@ nvmet_fc_free_fcp_iod(struct nvmet_fc_tgt_queue *queue,
|
|||
|
||||
tgtport->ops->fcp_req_release(&tgtport->fc_target_port, fcpreq);
|
||||
|
||||
/* release the queue lookup reference on the completed IO */
|
||||
nvmet_fc_tgt_q_put(queue);
|
||||
|
||||
spin_lock_irqsave(&queue->qlock, flags);
|
||||
deferfcp = list_first_entry_or_null(&queue->pending_cmd_list,
|
||||
struct nvmet_fc_defer_fcp_req, req_list);
|
||||
if (!deferfcp) {
|
||||
list_add_tail(&fod->fcp_list, &fod->queue->fod_list);
|
||||
spin_unlock_irqrestore(&queue->qlock, flags);
|
||||
|
||||
/* Release reference taken at queue lookup and fod allocation */
|
||||
nvmet_fc_tgt_q_put(queue);
|
||||
return;
|
||||
}
|
||||
|
||||
|
@ -760,6 +760,9 @@ nvmet_fc_delete_target_queue(struct nvmet_fc_tgt_queue *queue)
|
|||
tgtport->ops->fcp_req_release(&tgtport->fc_target_port,
|
||||
deferfcp->fcp_req);
|
||||
|
||||
/* release the queue lookup reference */
|
||||
nvmet_fc_tgt_q_put(queue);
|
||||
|
||||
kfree(deferfcp);
|
||||
|
||||
spin_lock_irqsave(&queue->qlock, flags);
|
||||
|
|
|
@ -52,10 +52,15 @@ static inline struct nvme_loop_ctrl *to_loop_ctrl(struct nvme_ctrl *ctrl)
|
|||
return container_of(ctrl, struct nvme_loop_ctrl, ctrl);
|
||||
}
|
||||
|
||||
enum nvme_loop_queue_flags {
|
||||
NVME_LOOP_Q_LIVE = 0,
|
||||
};
|
||||
|
||||
struct nvme_loop_queue {
|
||||
struct nvmet_cq nvme_cq;
|
||||
struct nvmet_sq nvme_sq;
|
||||
struct nvme_loop_ctrl *ctrl;
|
||||
unsigned long flags;
|
||||
};
|
||||
|
||||
static struct nvmet_port *nvmet_loop_port;
|
||||
|
@ -144,6 +149,14 @@ nvme_loop_timeout(struct request *rq, bool reserved)
|
|||
return BLK_EH_HANDLED;
|
||||
}
|
||||
|
||||
static inline blk_status_t nvme_loop_is_ready(struct nvme_loop_queue *queue,
|
||||
struct request *rq)
|
||||
{
|
||||
if (unlikely(!test_bit(NVME_LOOP_Q_LIVE, &queue->flags)))
|
||||
return nvmf_check_init_req(&queue->ctrl->ctrl, rq);
|
||||
return BLK_STS_OK;
|
||||
}
|
||||
|
||||
static blk_status_t nvme_loop_queue_rq(struct blk_mq_hw_ctx *hctx,
|
||||
const struct blk_mq_queue_data *bd)
|
||||
{
|
||||
|
@ -153,6 +166,10 @@ static blk_status_t nvme_loop_queue_rq(struct blk_mq_hw_ctx *hctx,
|
|||
struct nvme_loop_iod *iod = blk_mq_rq_to_pdu(req);
|
||||
blk_status_t ret;
|
||||
|
||||
ret = nvme_loop_is_ready(queue, req);
|
||||
if (unlikely(ret))
|
||||
return ret;
|
||||
|
||||
ret = nvme_setup_cmd(ns, req, &iod->cmd);
|
||||
if (ret)
|
||||
return ret;
|
||||
|
@ -267,6 +284,7 @@ static const struct blk_mq_ops nvme_loop_admin_mq_ops = {
|
|||
|
||||
static void nvme_loop_destroy_admin_queue(struct nvme_loop_ctrl *ctrl)
|
||||
{
|
||||
clear_bit(NVME_LOOP_Q_LIVE, &ctrl->queues[0].flags);
|
||||
nvmet_sq_destroy(&ctrl->queues[0].nvme_sq);
|
||||
blk_cleanup_queue(ctrl->ctrl.admin_q);
|
||||
blk_mq_free_tag_set(&ctrl->admin_tag_set);
|
||||
|
@ -297,8 +315,10 @@ static void nvme_loop_destroy_io_queues(struct nvme_loop_ctrl *ctrl)
|
|||
{
|
||||
int i;
|
||||
|
||||
for (i = 1; i < ctrl->ctrl.queue_count; i++)
|
||||
for (i = 1; i < ctrl->ctrl.queue_count; i++) {
|
||||
clear_bit(NVME_LOOP_Q_LIVE, &ctrl->queues[i].flags);
|
||||
nvmet_sq_destroy(&ctrl->queues[i].nvme_sq);
|
||||
}
|
||||
}
|
||||
|
||||
static int nvme_loop_init_io_queues(struct nvme_loop_ctrl *ctrl)
|
||||
|
@ -338,6 +358,7 @@ static int nvme_loop_connect_io_queues(struct nvme_loop_ctrl *ctrl)
|
|||
ret = nvmf_connect_io_queue(&ctrl->ctrl, i);
|
||||
if (ret)
|
||||
return ret;
|
||||
set_bit(NVME_LOOP_Q_LIVE, &ctrl->queues[i].flags);
|
||||
}
|
||||
|
||||
return 0;
|
||||
|
@ -380,6 +401,8 @@ static int nvme_loop_configure_admin_queue(struct nvme_loop_ctrl *ctrl)
|
|||
if (error)
|
||||
goto out_cleanup_queue;
|
||||
|
||||
set_bit(NVME_LOOP_Q_LIVE, &ctrl->queues[0].flags);
|
||||
|
||||
error = nvmf_reg_read64(&ctrl->ctrl, NVME_REG_CAP, &ctrl->ctrl.cap);
|
||||
if (error) {
|
||||
dev_err(ctrl->ctrl.device,
|
||||
|
|
|
@ -91,7 +91,7 @@ PTR_FIELD(PTR_GEN, 0, 8)
|
|||
|
||||
#define PTR_CHECK_DEV ((1 << PTR_DEV_BITS) - 1)
|
||||
|
||||
#define PTR(gen, offset, dev) \
|
||||
#define MAKE_PTR(gen, offset, dev) \
|
||||
((((__u64) dev) << 51) | ((__u64) offset) << 8 | gen)
|
||||
|
||||
/* Bkey utility code */
|
||||
|
|
|
@ -591,7 +591,7 @@ static int __blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
|
|||
return ret;
|
||||
|
||||
if (copy_to_user(arg, &buts, sizeof(buts))) {
|
||||
blk_trace_remove(q);
|
||||
__blk_trace_remove(q);
|
||||
return -EFAULT;
|
||||
}
|
||||
return 0;
|
||||
|
@ -637,7 +637,7 @@ static int compat_blk_trace_setup(struct request_queue *q, char *name,
|
|||
return ret;
|
||||
|
||||
if (copy_to_user(arg, &buts.name, ARRAY_SIZE(buts.name))) {
|
||||
blk_trace_remove(q);
|
||||
__blk_trace_remove(q);
|
||||
return -EFAULT;
|
||||
}
|
||||
|
||||
|
@ -872,7 +872,7 @@ static void blk_add_trace_rq_complete(void *ignore, struct request *rq,
|
|||
*
|
||||
**/
|
||||
static void blk_add_trace_bio(struct request_queue *q, struct bio *bio,
|
||||
u32 what, int error, union kernfs_node_id *cgid)
|
||||
u32 what, int error)
|
||||
{
|
||||
struct blk_trace *bt = q->blk_trace;
|
||||
|
||||
|
@ -880,22 +880,21 @@ static void blk_add_trace_bio(struct request_queue *q, struct bio *bio,
|
|||
return;
|
||||
|
||||
__blk_add_trace(bt, bio->bi_iter.bi_sector, bio->bi_iter.bi_size,
|
||||
bio_op(bio), bio->bi_opf, what, error, 0, NULL, cgid);
|
||||
bio_op(bio), bio->bi_opf, what, error, 0, NULL,
|
||||
blk_trace_bio_get_cgid(q, bio));
|
||||
}
|
||||
|
||||
static void blk_add_trace_bio_bounce(void *ignore,
|
||||
struct request_queue *q, struct bio *bio)
|
||||
{
|
||||
blk_add_trace_bio(q, bio, BLK_TA_BOUNCE, 0,
|
||||
blk_trace_bio_get_cgid(q, bio));
|
||||
blk_add_trace_bio(q, bio, BLK_TA_BOUNCE, 0);
|
||||
}
|
||||
|
||||
static void blk_add_trace_bio_complete(void *ignore,
|
||||
struct request_queue *q, struct bio *bio,
|
||||
int error)
|
||||
{
|
||||
blk_add_trace_bio(q, bio, BLK_TA_COMPLETE, error,
|
||||
blk_trace_bio_get_cgid(q, bio));
|
||||
blk_add_trace_bio(q, bio, BLK_TA_COMPLETE, error);
|
||||
}
|
||||
|
||||
static void blk_add_trace_bio_backmerge(void *ignore,
|
||||
|
@ -903,8 +902,7 @@ static void blk_add_trace_bio_backmerge(void *ignore,
|
|||
struct request *rq,
|
||||
struct bio *bio)
|
||||
{
|
||||
blk_add_trace_bio(q, bio, BLK_TA_BACKMERGE, 0,
|
||||
blk_trace_bio_get_cgid(q, bio));
|
||||
blk_add_trace_bio(q, bio, BLK_TA_BACKMERGE, 0);
|
||||
}
|
||||
|
||||
static void blk_add_trace_bio_frontmerge(void *ignore,
|
||||
|
@ -912,15 +910,13 @@ static void blk_add_trace_bio_frontmerge(void *ignore,
|
|||
struct request *rq,
|
||||
struct bio *bio)
|
||||
{
|
||||
blk_add_trace_bio(q, bio, BLK_TA_FRONTMERGE, 0,
|
||||
blk_trace_bio_get_cgid(q, bio));
|
||||
blk_add_trace_bio(q, bio, BLK_TA_FRONTMERGE, 0);
|
||||
}
|
||||
|
||||
static void blk_add_trace_bio_queue(void *ignore,
|
||||
struct request_queue *q, struct bio *bio)
|
||||
{
|
||||
blk_add_trace_bio(q, bio, BLK_TA_QUEUE, 0,
|
||||
blk_trace_bio_get_cgid(q, bio));
|
||||
blk_add_trace_bio(q, bio, BLK_TA_QUEUE, 0);
|
||||
}
|
||||
|
||||
static void blk_add_trace_getrq(void *ignore,
|
||||
|
@ -928,8 +924,7 @@ static void blk_add_trace_getrq(void *ignore,
|
|||
struct bio *bio, int rw)
|
||||
{
|
||||
if (bio)
|
||||
blk_add_trace_bio(q, bio, BLK_TA_GETRQ, 0,
|
||||
blk_trace_bio_get_cgid(q, bio));
|
||||
blk_add_trace_bio(q, bio, BLK_TA_GETRQ, 0);
|
||||
else {
|
||||
struct blk_trace *bt = q->blk_trace;
|
||||
|
||||
|
@ -945,8 +940,7 @@ static void blk_add_trace_sleeprq(void *ignore,
|
|||
struct bio *bio, int rw)
|
||||
{
|
||||
if (bio)
|
||||
blk_add_trace_bio(q, bio, BLK_TA_SLEEPRQ, 0,
|
||||
blk_trace_bio_get_cgid(q, bio));
|
||||
blk_add_trace_bio(q, bio, BLK_TA_SLEEPRQ, 0);
|
||||
else {
|
||||
struct blk_trace *bt = q->blk_trace;
|
||||
|
||||
|
|
|
@ -113,11 +113,23 @@ static const struct file_operations bdi_debug_stats_fops = {
|
|||
.release = single_release,
|
||||
};
|
||||
|
||||
static void bdi_debug_register(struct backing_dev_info *bdi, const char *name)
|
||||
static int bdi_debug_register(struct backing_dev_info *bdi, const char *name)
|
||||
{
|
||||
if (!bdi_debug_root)
|
||||
return -ENOMEM;
|
||||
|
||||
bdi->debug_dir = debugfs_create_dir(name, bdi_debug_root);
|
||||
if (!bdi->debug_dir)
|
||||
return -ENOMEM;
|
||||
|
||||
bdi->debug_stats = debugfs_create_file("stats", 0444, bdi->debug_dir,
|
||||
bdi, &bdi_debug_stats_fops);
|
||||
if (!bdi->debug_stats) {
|
||||
debugfs_remove(bdi->debug_dir);
|
||||
return -ENOMEM;
|
||||
}
|
||||
|
||||
return 0;
|
||||
}
|
||||
|
||||
static void bdi_debug_unregister(struct backing_dev_info *bdi)
|
||||
|
@ -129,9 +141,10 @@ static void bdi_debug_unregister(struct backing_dev_info *bdi)
|
|||
static inline void bdi_debug_init(void)
|
||||
{
|
||||
}
|
||||
static inline void bdi_debug_register(struct backing_dev_info *bdi,
|
||||
static inline int bdi_debug_register(struct backing_dev_info *bdi,
|
||||
const char *name)
|
||||
{
|
||||
return 0;
|
||||
}
|
||||
static inline void bdi_debug_unregister(struct backing_dev_info *bdi)
|
||||
{
|
||||
|
@ -869,10 +882,13 @@ int bdi_register_va(struct backing_dev_info *bdi, const char *fmt, va_list args)
|
|||
if (IS_ERR(dev))
|
||||
return PTR_ERR(dev);
|
||||
|
||||
if (bdi_debug_register(bdi, dev_name(dev))) {
|
||||
device_destroy(bdi_class, dev->devt);
|
||||
return -ENOMEM;
|
||||
}
|
||||
cgwb_bdi_register(bdi);
|
||||
bdi->dev = dev;
|
||||
|
||||
bdi_debug_register(bdi, dev_name(dev));
|
||||
set_bit(WB_registered, &bdi->wb.state);
|
||||
|
||||
spin_lock_bh(&bdi_lock);
|
||||
|
|
Loading…
Reference in New Issue