UbiquitousOS
/
OpenCloudOS-Kernel
mirror of https://gitee.com/OpenCloudOS/OpenCloudOS-Kernel.git
11
0
Fork 0
Code Issues Projects Releases Wiki Activity

nvme updates for 5.11 

- nvmet passthrough improvements (Chaitanya Kulkarni)
  - fcloop error injection support (James Smart)
  - read-only support for zoned namespaces without Zone Append
    (Javier González)
  - improve some error message (Minwoo Im)
  - reject I/O to offline fabrics namespaces (Victor Gladkov)
  - PCI queue allocation cleanups (Niklas Schnelle)
  - remove an unused allocation in nvmet (Amit Engel)
  - a Kconfig spelling fix (Colin Ian King)
  - nvme_req_qid simplication (Baolin Wang)
 -----BEGIN PGP SIGNATURE-----
 
 iQI/BAABCgApFiEEgdbnc3r/njty3Iq9D55TZVIEUYMFAl/HlQELHGhjaEBsc3Qu
 ZGUACgkQD55TZVIEUYNCBw/9EZOktC2njGkQW3uHfliw9kvbKgPeHQfjMtG2NH6Q
 bDSOrEgw9KyxTDb+GBjF0gQZQCpbASKTMH7MPn5/84K5s1zFeocR/itC8CPB9fOv
 nCeh4shdAn5a8oYQ+kDT8MoSQE05k2CNnuP086Wn/51aW7g4X9yfXHutO8HbkYxn
 HPWzlz4jIE8LWDXV0c3VCSaSWVPyyxTCGEDiNz8ThpKR7DtIzIPfeSf6YRgxZx75
 G1lnYoLWoM+bxNGbzRkombjomLgcQwfvEqZ7POXDv21AFxnr7qlKEFpoB2bIOLCH
 2Si2qgk2fxiUibkWcx50p1nNMnSNChIzoPce36PNAJrNl7GC7srIWxBFbkrLqmtZ
 c/V/KSW5CYneVObwGWQUCRPY2O/GB0+pdjFbXUzw/UZHk+GKe+WrxSIowdU4BaBZ
 ejjZCYOI2zPh+dkfRL4qQVl+74LrIGXQdNt9sKO7jRlUmp9HK6MaBW27m0czH4jx
 FJ+2ICx7KWSrcRWSmtvBHhYGt4PFGMHA+0FmsjH+dRqhTiYhVOOyw5J2MA6GQ8jl
 z5w4tFIE+F/1l+dQwo8LY/96cGTOeKW4t3E7zETMF3pQhYksnwrld1lpU3fAJ8vi
 tlCPn9UfadmTzSBFO8Ek8f0Hy2ZwP3+axuG7fsgkJG0ItEc1vW5r1jiI4+pBXpPD
 wR8=
 =aN11
 -----END PGP SIGNATURE-----

Merge tag 'nvme-5.11-20201202' of git://git.infradead.org/nvme into for-5.11/drivers

Pull NVMe updates from Christoph:

"nvme updates for 5.11

 - nvmet passthrough improvements (Chaitanya Kulkarni)
 - fcloop error injection support (James Smart)
 - read-only support for zoned namespaces without Zone Append
   (Javier González)
 - improve some error message (Minwoo Im)
 - reject I/O to offline fabrics namespaces (Victor Gladkov)
 - PCI queue allocation cleanups (Niklas Schnelle)
 - remove an unused allocation in nvmet (Amit Engel)
 - a Kconfig spelling fix (Colin Ian King)
 - nvme_req_qid simplication (Baolin Wang)"

* tag 'nvme-5.11-20201202' of git://git.infradead.org/nvme: (23 commits)
  nvme: export zoned namespaces without Zone Append support read-only
  nvme: rename bdev operations
  nvme: rename controller base dev_t char device
  nvme: remove unnecessary return values
  nvme: print a warning for when listing active namespaces fails
  nvme: improve an error message on Identify failure
  nvme-fabrics: reject I/O to offline device
  nvmet: fix a spelling mistake "incuding" -> "including" in Kconfig
  nvmet: make sure discovery change log event is protected
  nvmet: remove unused ctrl->cqs
  nvme-pci: don't allocate unused I/O queues
  nvme-pci: drop min() from nr_io_queues assignment
  nvmet: use inline bio for passthru fast path
  nvmet: use blk_rq_bio_prep instead of blk_rq_append_bio
  nvmet: remove op_flags for passthru commands
  nvme: split nvme_alloc_request()
  block: move blk_rq_bio_prep() to linux/blk-mq.h
  nvmet: add passthru io timeout value attr
  nvmet: add passthru admin timeout value attr
  nvme: use consistent macro name for timeout
  ...
This commit is contained in:
Jens Axboe 2020-12-02 08:56:55 -07:00
parent 48332ff295 2f4c9ba23b
commit 3b9351f0fd
21 changed files with 336 additions and 117 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
block/blk.h
View File

@ -91,18 +91,6 @@ static inline bool bvec_gap_to_prev(struct request_queue *q,
return __bvec_gap_to_prev(q, bprv, offset);
}
static inline void blk_rq_bio_prep(struct request *rq, struct bio *bio,
unsigned int nr_segs)
{
rq->nr_phys_segments = nr_segs;
rq->__data_len = bio->bi_iter.bi_size;
rq->bio = rq->biotail = bio;
rq->ioprio = bio_prio(bio);
if (bio->bi_disk)
rq->rq_disk = bio->bi_disk;
}
#ifdef CONFIG_BLK_DEV_INTEGRITY
void blk_flush_integrity(void);
bool __bio_integrity_endio(struct bio *);

150
drivers/nvme/host/core.c
View File

@ -85,7 +85,7 @@ static LIST_HEAD(nvme_subsystems);
static DEFINE_MUTEX(nvme_subsystems_lock);
static DEFINE_IDA(nvme_instance_ida);
static dev_t nvme_chr_devt;
static dev_t nvme_ctrl_base_chr_devt;
static struct class *nvme_class;
static struct class *nvme_subsys_class;
@ -148,6 +148,38 @@ int nvme_try_sched_reset(struct nvme_ctrl *ctrl)
}
EXPORT_SYMBOL_GPL(nvme_try_sched_reset);
static void nvme_failfast_work(struct work_struct *work)
{
struct nvme_ctrl *ctrl = container_of(to_delayed_work(work),
struct nvme_ctrl, failfast_work);
if (ctrl->state != NVME_CTRL_CONNECTING)
return;
set_bit(NVME_CTRL_FAILFAST_EXPIRED, &ctrl->flags);
dev_info(ctrl->device, "failfast expired\n");
nvme_kick_requeue_lists(ctrl);
}
static inline void nvme_start_failfast_work(struct nvme_ctrl *ctrl)
{
if (!ctrl->opts || ctrl->opts->fast_io_fail_tmo == -1)
return;
schedule_delayed_work(&ctrl->failfast_work,
ctrl->opts->fast_io_fail_tmo * HZ);
}
static inline void nvme_stop_failfast_work(struct nvme_ctrl *ctrl)
{
if (!ctrl->opts)
return;
cancel_delayed_work_sync(&ctrl->failfast_work);
clear_bit(NVME_CTRL_FAILFAST_EXPIRED, &ctrl->flags);
}
int nvme_reset_ctrl(struct nvme_ctrl *ctrl)
{
if (!nvme_change_ctrl_state(ctrl, NVME_CTRL_RESETTING))
@ -433,8 +465,17 @@ bool nvme_change_ctrl_state(struct nvme_ctrl *ctrl,
}
spin_unlock_irqrestore(&ctrl->lock, flags);
if (changed && ctrl->state == NVME_CTRL_LIVE)
if (!changed)
return false;
if (ctrl->state == NVME_CTRL_LIVE) {
if (old_state == NVME_CTRL_CONNECTING)
nvme_stop_failfast_work(ctrl);
nvme_kick_requeue_lists(ctrl);
} else if (ctrl->state == NVME_CTRL_CONNECTING &&
old_state == NVME_CTRL_RESETTING) {
nvme_start_failfast_work(ctrl);
}
return changed;
}
EXPORT_SYMBOL_GPL(nvme_change_ctrl_state);
@ -518,29 +559,49 @@ static inline void nvme_clear_nvme_request(struct request *req)
}
}
struct request *nvme_alloc_request(struct request_queue *q,
struct nvme_command *cmd, blk_mq_req_flags_t flags, int qid)
static inline unsigned int nvme_req_op(struct nvme_command *cmd)
{
unsigned op = nvme_is_write(cmd) ? REQ_OP_DRV_OUT : REQ_OP_DRV_IN;
struct request *req;
return nvme_is_write(cmd) ? REQ_OP_DRV_OUT : REQ_OP_DRV_IN;
}
if (qid == NVME_QID_ANY) {
req = blk_mq_alloc_request(q, op, flags);
} else {
req = blk_mq_alloc_request_hctx(q, op, flags,
qid ? qid - 1 : 0);
}
if (IS_ERR(req))
return req;
static inline void nvme_init_request(struct request *req,
struct nvme_command *cmd)
{
if (req->q->queuedata)
req->timeout = NVME_IO_TIMEOUT;
else /* no queuedata implies admin queue */
req->timeout = NVME_ADMIN_TIMEOUT;
req->cmd_flags |= REQ_FAILFAST_DRIVER;
nvme_clear_nvme_request(req);
nvme_req(req)->cmd = cmd;
}
struct request *nvme_alloc_request(struct request_queue *q,
struct nvme_command *cmd, blk_mq_req_flags_t flags)
{
struct request *req;
req = blk_mq_alloc_request(q, nvme_req_op(cmd), flags);
if (!IS_ERR(req))
nvme_init_request(req, cmd);
return req;
}
EXPORT_SYMBOL_GPL(nvme_alloc_request);
struct request *nvme_alloc_request_qid(struct request_queue *q,
struct nvme_command *cmd, blk_mq_req_flags_t flags, int qid)
{
struct request *req;
req = blk_mq_alloc_request_hctx(q, nvme_req_op(cmd), flags,
qid ? qid - 1 : 0);
if (!IS_ERR(req))
nvme_init_request(req, cmd);
return req;
}
EXPORT_SYMBOL_GPL(nvme_alloc_request_qid);
static int nvme_toggle_streams(struct nvme_ctrl *ctrl, bool enable)
{
struct nvme_command c;
@ -897,11 +958,15 @@ int __nvme_submit_sync_cmd(struct request_queue *q, struct nvme_command *cmd,
struct request *req;
int ret;
req = nvme_alloc_request(q, cmd, flags, qid);
if (qid == NVME_QID_ANY)
req = nvme_alloc_request(q, cmd, flags);
else
req = nvme_alloc_request_qid(q, cmd, flags, qid);
if (IS_ERR(req))
return PTR_ERR(req);
req->timeout = timeout ? timeout : ADMIN_TIMEOUT;
if (timeout)
req->timeout = timeout;
if (buffer && bufflen) {
ret = blk_rq_map_kern(q, req, buffer, bufflen, GFP_KERNEL);
@ -1067,11 +1132,12 @@ static int nvme_submit_user_cmd(struct request_queue *q,
void *meta = NULL;
int ret;
req = nvme_alloc_request(q, cmd, 0, NVME_QID_ANY);
req = nvme_alloc_request(q, cmd, 0);
if (IS_ERR(req))
return PTR_ERR(req);
req->timeout = timeout ? timeout : ADMIN_TIMEOUT;
if (timeout)
req->timeout = timeout;
nvme_req(req)->flags |= NVME_REQ_USERCMD;
if (ubuffer && bufflen) {
@ -1141,8 +1207,8 @@ static int nvme_keep_alive(struct nvme_ctrl *ctrl)
{
struct request *rq;
rq = nvme_alloc_request(ctrl->admin_q, &ctrl->ka_cmd, BLK_MQ_REQ_RESERVED,
NVME_QID_ANY);
rq = nvme_alloc_request(ctrl->admin_q, &ctrl->ka_cmd,
BLK_MQ_REQ_RESERVED);
if (IS_ERR(rq))
return PTR_ERR(rq);
@ -1302,7 +1368,8 @@ static int nvme_identify_ns_descs(struct nvme_ctrl *ctrl, unsigned nsid,
NVME_IDENTIFY_DATA_SIZE);
if (status) {
dev_warn(ctrl->device,
"Identify Descriptors failed (%d)\n", status);
"Identify Descriptors failed (nsid=%u, status=0x%x)\n",
nsid, status);
goto free_data;
}
@ -2058,7 +2125,8 @@ static void nvme_update_disk_info(struct gendisk *disk,
nvme_config_discard(disk, ns);
nvme_config_write_zeroes(disk, ns);
if (id->nsattr & NVME_NS_ATTR_RO)
if ((id->nsattr & NVME_NS_ATTR_RO) ||
test_bit(NVME_NS_FORCE_RO, &ns->flags))
set_disk_ro(disk, true);
}
@ -2261,13 +2329,13 @@ int nvme_sec_submit(void *data, u16 spsp, u8 secp, void *buffer, size_t len,
cmd.common.cdw10 = cpu_to_le32(((u32)secp) << 24 | ((u32)spsp) << 8);
cmd.common.cdw11 = cpu_to_le32(len);
return __nvme_submit_sync_cmd(ctrl->admin_q, &cmd, NULL, buffer, len,
ADMIN_TIMEOUT, NVME_QID_ANY, 1, 0, false);
return __nvme_submit_sync_cmd(ctrl->admin_q, &cmd, NULL, buffer, len, 0,
NVME_QID_ANY, 1, 0, false);
}
EXPORT_SYMBOL_GPL(nvme_sec_submit);
#endif /* CONFIG_BLK_SED_OPAL */
static const struct block_device_operations nvme_fops = {
static const struct block_device_operations nvme_bdev_ops = {
.owner = THIS_MODULE,
.ioctl = nvme_ioctl,
.compat_ioctl = nvme_compat_ioctl,
@ -3275,7 +3343,7 @@ static inline struct nvme_ns_head *dev_to_ns_head(struct device *dev)
{
struct gendisk *disk = dev_to_disk(dev);
if (disk->fops == &nvme_fops)
if (disk->fops == &nvme_bdev_ops)
return nvme_get_ns_from_dev(dev)->head;
else
return disk->private_data;
@ -3384,7 +3452,7 @@ static umode_t nvme_ns_id_attrs_are_visible(struct kobject *kobj,
}
#ifdef CONFIG_NVME_MULTIPATH
if (a == &dev_attr_ana_grpid.attr || a == &dev_attr_ana_state.attr) {
if (dev_to_disk(dev)->fops != &nvme_fops) /* per-path attr */
if (dev_to_disk(dev)->fops != &nvme_bdev_ops) /* per-path attr */
return 0;
if (!nvme_ctrl_use_ana(nvme_get_ns_from_dev(dev)->ctrl))
return 0;
@ -3805,7 +3873,7 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid,
struct gendisk *disk;
struct nvme_id_ns *id;
char disk_name[DISK_NAME_LEN];
int node = ctrl->numa_node, flags = GENHD_FL_EXT_DEVT, ret;
int node = ctrl->numa_node, flags = GENHD_FL_EXT_DEVT;
if (nvme_identify_ns(ctrl, nsid, ids, &id))
return;
@ -3829,8 +3897,7 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid,
ns->ctrl = ctrl;
kref_init(&ns->kref);
ret = nvme_init_ns_head(ns, nsid, ids, id->nmic & NVME_NS_NMIC_SHARED);
if (ret)
if (nvme_init_ns_head(ns, nsid, ids, id->nmic & NVME_NS_NMIC_SHARED))
goto out_free_queue;
nvme_set_disk_name(disk_name, ns, ctrl, &flags);
@ -3838,7 +3905,7 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid,
if (!disk)
goto out_unlink_ns;
disk->fops = &nvme_fops;
disk->fops = &nvme_bdev_ops;
disk->private_data = ns;
disk->queue = ns->queue;
disk->flags = flags;
@ -3849,8 +3916,7 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid,
goto out_put_disk;
if ((ctrl->quirks & NVME_QUIRK_LIGHTNVM) && id->vs[0] == 0x1) {
ret = nvme_nvm_register(ns, disk_name, node);
if (ret) {
if (nvme_nvm_register(ns, disk_name, node)) {
dev_warn(ctrl->device, "LightNVM init failure\n");
goto out_put_disk;
}
@ -4043,8 +4109,11 @@ static int nvme_scan_ns_list(struct nvme_ctrl *ctrl)
ret = nvme_submit_sync_cmd(ctrl->admin_q, &cmd, ns_list,
NVME_IDENTIFY_DATA_SIZE);
if (ret)
if (ret) {
dev_warn(ctrl->device,
"Identify NS List failed (status=0x%x)\n", ret);
goto free;
}
for (i = 0; i < nr_entries; i++) {
u32 nsid = le32_to_cpu(ns_list[i]);
@ -4347,6 +4416,7 @@ void nvme_stop_ctrl(struct nvme_ctrl *ctrl)
{
nvme_mpath_stop(ctrl);
nvme_stop_keep_alive(ctrl);
nvme_stop_failfast_work(ctrl);
flush_work(&ctrl->async_event_work);
cancel_work_sync(&ctrl->fw_act_work);
}
@ -4412,6 +4482,7 @@ int nvme_init_ctrl(struct nvme_ctrl *ctrl, struct device *dev,
int ret;
ctrl->state = NVME_CTRL_NEW;
clear_bit(NVME_CTRL_FAILFAST_EXPIRED, &ctrl->flags);
spin_lock_init(&ctrl->lock);
mutex_init(&ctrl->scan_lock);
INIT_LIST_HEAD(&ctrl->namespaces);
@ -4428,6 +4499,7 @@ int nvme_init_ctrl(struct nvme_ctrl *ctrl, struct device *dev,
init_waitqueue_head(&ctrl->state_wq);
INIT_DELAYED_WORK(&ctrl->ka_work, nvme_keep_alive_work);
INIT_DELAYED_WORK(&ctrl->failfast_work, nvme_failfast_work);
memset(&ctrl->ka_cmd, 0, sizeof(ctrl->ka_cmd));
ctrl->ka_cmd.common.opcode = nvme_admin_keep_alive;
@ -4446,7 +4518,8 @@ int nvme_init_ctrl(struct nvme_ctrl *ctrl, struct device *dev,
device_initialize(&ctrl->ctrl_device);
ctrl->device = &ctrl->ctrl_device;
ctrl->device->devt = MKDEV(MAJOR(nvme_chr_devt), ctrl->instance);
ctrl->device->devt = MKDEV(MAJOR(nvme_ctrl_base_chr_devt),
ctrl->instance);
ctrl->device->class = nvme_class;
ctrl->device->parent = ctrl->dev;
ctrl->device->groups = nvme_dev_attr_groups;
@ -4655,7 +4728,8 @@ static int __init nvme_core_init(void)
if (!nvme_delete_wq)
goto destroy_reset_wq;
result = alloc_chrdev_region(&nvme_chr_devt, 0, NVME_MINORS, "nvme");
result = alloc_chrdev_region(&nvme_ctrl_base_chr_devt, 0,
NVME_MINORS, "nvme");
if (result < 0)
goto destroy_delete_wq;
@ -4676,7 +4750,7 @@ static int __init nvme_core_init(void)
destroy_class:
class_destroy(nvme_class);
unregister_chrdev:
unregister_chrdev_region(nvme_chr_devt, NVME_MINORS);
unregister_chrdev_region(nvme_ctrl_base_chr_devt, NVME_MINORS);
destroy_delete_wq:
destroy_workqueue(nvme_delete_wq);
destroy_reset_wq:
@ -4691,7 +4765,7 @@ static void __exit nvme_core_exit(void)
{
class_destroy(nvme_subsys_class);
class_destroy(nvme_class);
unregister_chrdev_region(nvme_chr_devt, NVME_MINORS);
unregister_chrdev_region(nvme_ctrl_base_chr_devt, NVME_MINORS);
destroy_workqueue(nvme_delete_wq);
destroy_workqueue(nvme_reset_wq);
destroy_workqueue(nvme_wq);

25
drivers/nvme/host/fabrics.c
View File

@ -549,6 +549,7 @@ blk_status_t nvmf_fail_nonready_command(struct nvme_ctrl *ctrl,
{
if (ctrl->state != NVME_CTRL_DELETING_NOIO &&
ctrl->state != NVME_CTRL_DEAD &&
!test_bit(NVME_CTRL_FAILFAST_EXPIRED, &ctrl->flags) &&
!blk_noretry_request(rq) && !(rq->cmd_flags & REQ_NVME_MPATH))
return BLK_STS_RESOURCE;
@ -615,6 +616,7 @@ static const match_table_t opt_tokens = {
{ NVMF_OPT_NR_WRITE_QUEUES, "nr_write_queues=%d" },
{ NVMF_OPT_NR_POLL_QUEUES, "nr_poll_queues=%d" },
{ NVMF_OPT_TOS, "tos=%d" },
{ NVMF_OPT_FAIL_FAST_TMO, "fast_io_fail_tmo=%d" },
{ NVMF_OPT_ERR, NULL }
};
@ -634,6 +636,7 @@ static int nvmf_parse_options(struct nvmf_ctrl_options *opts,
opts->reconnect_delay = NVMF_DEF_RECONNECT_DELAY;
opts->kato = NVME_DEFAULT_KATO;
opts->duplicate_connect = false;
opts->fast_io_fail_tmo = NVMF_DEF_FAIL_FAST_TMO;
opts->hdr_digest = false;
opts->data_digest = false;
opts->tos = -1; /* < 0 == use transport default */
@ -754,6 +757,17 @@ static int nvmf_parse_options(struct nvmf_ctrl_options *opts,
pr_warn("ctrl_loss_tmo < 0 will reconnect forever\n");
ctrl_loss_tmo = token;
break;
case NVMF_OPT_FAIL_FAST_TMO:
if (match_int(args, &token)) {
ret = -EINVAL;
goto out;
}
if (token >= 0)
pr_warn("I/O fail on reconnect controller after %d sec\n",
token);
opts->fast_io_fail_tmo = token;
break;
case NVMF_OPT_HOSTNQN:
if (opts->host) {
pr_err("hostnqn already user-assigned: %s\n",
@ -884,11 +898,15 @@ static int nvmf_parse_options(struct nvmf_ctrl_options *opts,
opts->nr_poll_queues = 0;
opts->duplicate_connect = true;
}
if (ctrl_loss_tmo < 0)
if (ctrl_loss_tmo < 0) {
opts->max_reconnects = -1;
else
} else {
opts->max_reconnects = DIV_ROUND_UP(ctrl_loss_tmo,
opts->reconnect_delay);
if (ctrl_loss_tmo < opts->fast_io_fail_tmo)
pr_warn("failfast tmo (%d) larger than controller loss tmo (%d)\n",
opts->fast_io_fail_tmo, ctrl_loss_tmo);
}
if (!opts->host) {
kref_get(&nvmf_default_host->ref);
@ -988,7 +1006,8 @@ EXPORT_SYMBOL_GPL(nvmf_free_options);
#define NVMF_ALLOWED_OPTS (NVMF_OPT_QUEUE_SIZE | NVMF_OPT_NR_IO_QUEUES | \
NVMF_OPT_KATO | NVMF_OPT_HOSTNQN | \
NVMF_OPT_HOST_ID | NVMF_OPT_DUP_CONNECT |\
NVMF_OPT_DISABLE_SQFLOW)
NVMF_OPT_DISABLE_SQFLOW |\
NVMF_OPT_FAIL_FAST_TMO)
static struct nvme_ctrl *
nvmf_create_ctrl(struct device *dev, const char *buf)

5
drivers/nvme/host/fabrics.h
View File

@ -15,6 +15,8 @@
#define NVMF_DEF_RECONNECT_DELAY 10
/* default to 600 seconds of reconnect attempts before giving up */
#define NVMF_DEF_CTRL_LOSS_TMO 600
/* default is -1: the fail fast mechanism is disabled */
#define NVMF_DEF_FAIL_FAST_TMO -1
/*
* Define a host as seen by the target. We allocate one at boot, but also
@ -56,6 +58,7 @@ enum {
NVMF_OPT_NR_WRITE_QUEUES = 1 << 17,
NVMF_OPT_NR_POLL_QUEUES = 1 << 18,
NVMF_OPT_TOS = 1 << 19,
NVMF_OPT_FAIL_FAST_TMO = 1 << 20,
};
/**
@ -89,6 +92,7 @@ enum {
* @nr_write_queues: number of queues for write I/O
* @nr_poll_queues: number of queues for polling I/O
* @tos: type of service
* @fast_io_fail_tmo: Fast I/O fail timeout in seconds
*/
struct nvmf_ctrl_options {
unsigned mask;
@ -111,6 +115,7 @@ struct nvmf_ctrl_options {
unsigned int nr_write_queues;
unsigned int nr_poll_queues;
int tos;
int fast_io_fail_tmo;
};
/*

2
drivers/nvme/host/fc.c
View File

@ -3479,7 +3479,7 @@ nvme_fc_init_ctrl(struct device *dev, struct nvmf_ctrl_options *opts,
ctrl->lport->ops->fcprqst_priv_sz);
ctrl->admin_tag_set.driver_data = ctrl;
ctrl->admin_tag_set.nr_hw_queues = 1;
ctrl->admin_tag_set.timeout = ADMIN_TIMEOUT;
ctrl->admin_tag_set.timeout = NVME_ADMIN_TIMEOUT;
ctrl->admin_tag_set.flags = BLK_MQ_F_NO_SCHED;
ret = blk_mq_alloc_tag_set(&ctrl->admin_tag_set);

8
drivers/nvme/host/lightnvm.c
View File

@ -653,7 +653,7 @@ static struct request *nvme_nvm_alloc_request(struct request_queue *q,
nvme_nvm_rqtocmd(rqd, ns, cmd);
rq = nvme_alloc_request(q, (struct nvme_command *)cmd, 0, NVME_QID_ANY);
rq = nvme_alloc_request(q, (struct nvme_command *)cmd, 0);
if (IS_ERR(rq))
return rq;
@ -767,14 +767,14 @@ static int nvme_nvm_submit_user_cmd(struct request_queue *q,
DECLARE_COMPLETION_ONSTACK(wait);
int ret = 0;
rq = nvme_alloc_request(q, (struct nvme_command *)vcmd, 0,
NVME_QID_ANY);
rq = nvme_alloc_request(q, (struct nvme_command *)vcmd, 0);
if (IS_ERR(rq)) {
ret = -ENOMEM;
goto err_cmd;
}
rq->timeout = timeout ? timeout : ADMIN_TIMEOUT;
if (timeout)
rq->timeout = timeout;
if (ppa_buf && ppa_len) {
ppa_list = dma_pool_alloc(dev->dma_pool, GFP_KERNEL, &ppa_dma);

2
drivers/nvme/host/multipath.c
View File

@ -279,6 +279,8 @@ static bool nvme_available_path(struct nvme_ns_head *head)
struct nvme_ns *ns;
list_for_each_entry_rcu(ns, &head->list, siblings) {
if (test_bit(NVME_CTRL_FAILFAST_EXPIRED, &ns->ctrl->flags))
continue;
switch (ns->ctrl->state) {
case NVME_CTRL_LIVE:
case NVME_CTRL_RESETTING:

11
drivers/nvme/host/nvme.h
View File

@ -24,7 +24,7 @@ extern unsigned int nvme_io_timeout;
#define NVME_IO_TIMEOUT (nvme_io_timeout * HZ)
extern unsigned int admin_timeout;
#define ADMIN_TIMEOUT (admin_timeout * HZ)
#define NVME_ADMIN_TIMEOUT (admin_timeout * HZ)
#define NVME_DEFAULT_KATO 5
#define NVME_KATO_GRACE 10
@ -178,7 +178,8 @@ static inline u16 nvme_req_qid(struct request *req)
{
if (!req->q->queuedata)
return 0;
return blk_mq_unique_tag_to_hwq(blk_mq_unique_tag(req)) + 1;
return req->mq_hctx->queue_num + 1;
}
/* The below value is the specific amount of delay needed before checking
@ -304,6 +305,7 @@ struct nvme_ctrl {
struct work_struct scan_work;
struct work_struct async_event_work;
struct delayed_work ka_work;
struct delayed_work failfast_work;
struct nvme_command ka_cmd;
struct work_struct fw_act_work;
unsigned long events;
@ -337,6 +339,8 @@ struct nvme_ctrl {
u16 icdoff;
u16 maxcmd;
int nr_reconnects;
unsigned long flags;
#define NVME_CTRL_FAILFAST_EXPIRED 0
struct nvmf_ctrl_options *opts;
struct page *discard_page;
@ -448,6 +452,7 @@ struct nvme_ns {
#define NVME_NS_REMOVING 0
#define NVME_NS_DEAD 1
#define NVME_NS_ANA_PENDING 2
#define NVME_NS_FORCE_RO 3
struct nvme_fault_inject fault_inject;
@ -610,6 +615,8 @@ void nvme_start_freeze(struct nvme_ctrl *ctrl);
#define NVME_QID_ANY -1
struct request *nvme_alloc_request(struct request_queue *q,
struct nvme_command *cmd, blk_mq_req_flags_t flags);
struct request *nvme_alloc_request_qid(struct request_queue *q,
struct nvme_command *cmd, blk_mq_req_flags_t flags, int qid);
void nvme_cleanup_cmd(struct request *req);
blk_status_t nvme_setup_cmd(struct nvme_ns *ns, struct request *req,

27
drivers/nvme/host/pci.c
View File

@ -1304,13 +1304,12 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req, bool reserved)
req->tag, nvmeq->qid);
abort_req = nvme_alloc_request(dev->ctrl.admin_q, &cmd,
BLK_MQ_REQ_NOWAIT, NVME_QID_ANY);
BLK_MQ_REQ_NOWAIT);
if (IS_ERR(abort_req)) {
atomic_inc(&dev->ctrl.abort_limit);
return BLK_EH_RESET_TIMER;
}
abort_req->timeout = ADMIN_TIMEOUT;
abort_req->end_io_data = NULL;
blk_execute_rq_nowait(abort_req->q, NULL, abort_req, 0, abort_endio);
@ -1607,7 +1606,7 @@ static int nvme_alloc_admin_tags(struct nvme_dev *dev)
dev->admin_tagset.nr_hw_queues = 1;
dev->admin_tagset.queue_depth = NVME_AQ_MQ_TAG_DEPTH;
dev->admin_tagset.timeout = ADMIN_TIMEOUT;
dev->admin_tagset.timeout = NVME_ADMIN_TIMEOUT;
dev->admin_tagset.numa_node = dev->ctrl.numa_node;
dev->admin_tagset.cmd_size = sizeof(struct nvme_iod);
dev->admin_tagset.flags = BLK_MQ_F_NO_SCHED;
@ -2089,6 +2088,12 @@ static void nvme_disable_io_queues(struct nvme_dev *dev)
static unsigned int nvme_max_io_queues(struct nvme_dev *dev)
{
/*
* If tags are shared with admin queue (Apple bug), then
* make sure we only use one IO queue.
*/
if (dev->ctrl.quirks & NVME_QUIRK_SHARED_TAGS)
return 1;
return num_possible_cpus() + dev->nr_write_queues + dev->nr_poll_queues;
}
@ -2107,16 +2112,7 @@ static int nvme_setup_io_queues(struct nvme_dev *dev)
dev->nr_write_queues = write_queues;
dev->nr_poll_queues = poll_queues;
/*
* If tags are shared with admin queue (Apple bug), then
* make sure we only use one IO queue.
*/
if (dev->ctrl.quirks & NVME_QUIRK_SHARED_TAGS)
nr_io_queues = 1;
else
nr_io_queues = min(nvme_max_io_queues(dev),
dev->nr_allocated_queues - 1);
nr_io_queues = dev->nr_allocated_queues - 1;
result = nvme_set_queue_count(&dev->ctrl, &nr_io_queues);
if (result < 0)
return result;
@ -2219,11 +2215,10 @@ static int nvme_delete_queue(struct nvme_queue *nvmeq, u8 opcode)
cmd.delete_queue.opcode = opcode;
cmd.delete_queue.qid = cpu_to_le16(nvmeq->qid);
req = nvme_alloc_request(q, &cmd, BLK_MQ_REQ_NOWAIT, NVME_QID_ANY);
req = nvme_alloc_request(q, &cmd, BLK_MQ_REQ_NOWAIT);
if (IS_ERR(req))
return PTR_ERR(req);
req->timeout = ADMIN_TIMEOUT;
req->end_io_data = nvmeq;
init_completion(&nvmeq->delete_done);
@ -2239,7 +2234,7 @@ static bool __nvme_disable_io_queues(struct nvme_dev *dev, u8 opcode)
unsigned long timeout;
retry:
timeout = ADMIN_TIMEOUT;
timeout = NVME_ADMIN_TIMEOUT;
while (nr_queues > 0) {
if (nvme_delete_queue(&dev->queues[nr_queues], opcode))
break;

2
drivers/nvme/host/rdma.c
View File

@ -797,7 +797,7 @@ static struct blk_mq_tag_set *nvme_rdma_alloc_tagset(struct nvme_ctrl *nctrl,
NVME_RDMA_DATA_SGL_SIZE;
set->driver_data = ctrl;
set->nr_hw_queues = 1;
set->timeout = ADMIN_TIMEOUT;
set->timeout = NVME_ADMIN_TIMEOUT;
set->flags = BLK_MQ_F_NO_SCHED;
} else {
set = &ctrl->tag_set;

2
drivers/nvme/host/tcp.c
View File

@ -1568,7 +1568,7 @@ static struct blk_mq_tag_set *nvme_tcp_alloc_tagset(struct nvme_ctrl *nctrl,
set->cmd_size = sizeof(struct nvme_tcp_request);
set->driver_data = ctrl;
set->nr_hw_queues = 1;
set->timeout = ADMIN_TIMEOUT;
set->timeout = NVME_ADMIN_TIMEOUT;
} else {
set = &ctrl->tag_set;
memset(set, 0, sizeof(*set));

13
drivers/nvme/host/zns.c
View File

@ -55,12 +55,17 @@ int nvme_update_zone_info(struct nvme_ns *ns, unsigned lbaf)
int status;
/* Driver requires zone append support */
if (!(le32_to_cpu(log->iocs[nvme_cmd_zone_append]) &
if ((le32_to_cpu(log->iocs[nvme_cmd_zone_append]) &
NVME_CMD_EFFECTS_CSUPP)) {
if (test_and_clear_bit(NVME_NS_FORCE_RO, &ns->flags))
dev_warn(ns->ctrl->device,
"Zone Append supported for zoned namespace:%d. Remove read-only mode\n",
ns->head->ns_id);
} else {
set_bit(NVME_NS_FORCE_RO, &ns->flags);
dev_warn(ns->ctrl->device,
"append not supported for zoned namespace:%d\n",
ns->head->ns_id);
return -EINVAL;
"Zone Append not supported for zoned namespace:%d. Forcing to read-only mode\n",
ns->head->ns_id);
}
/* Lazily query controller append limit for the first zoned namespace */

2
drivers/nvme/target/Kconfig
View File

@ -24,7 +24,7 @@ config NVME_TARGET_PASSTHRU
This enables target side NVMe passthru controller support for the
NVMe Over Fabrics protocol. It allows for hosts to manage and
directly access an actual NVMe controller residing on the target
side, incuding executing Vendor Unique Commands.
side, including executing Vendor Unique Commands.
If unsure, say N.

40
drivers/nvme/target/configfs.c
View File

@ -736,9 +736,49 @@ static ssize_t nvmet_passthru_enable_store(struct config_item *item,
}
CONFIGFS_ATTR(nvmet_passthru_, enable);
static ssize_t nvmet_passthru_admin_timeout_show(struct config_item *item,
char *page)
{
return sprintf(page, "%u\n", to_subsys(item->ci_parent)->admin_timeout);
}
static ssize_t nvmet_passthru_admin_timeout_store(struct config_item *item,
const char *page, size_t count)
{
struct nvmet_subsys *subsys = to_subsys(item->ci_parent);
unsigned int timeout;
if (kstrtouint(page, 0, &timeout))
return -EINVAL;
subsys->admin_timeout = timeout;
return count;
}
CONFIGFS_ATTR(nvmet_passthru_, admin_timeout);
static ssize_t nvmet_passthru_io_timeout_show(struct config_item *item,
char *page)
{
return sprintf(page, "%u\n", to_subsys(item->ci_parent)->io_timeout);
}
static ssize_t nvmet_passthru_io_timeout_store(struct config_item *item,
const char *page, size_t count)
{
struct nvmet_subsys *subsys = to_subsys(item->ci_parent);
unsigned int timeout;
if (kstrtouint(page, 0, &timeout))
return -EINVAL;
subsys->io_timeout = timeout;
return count;
}
CONFIGFS_ATTR(nvmet_passthru_, io_timeout);
static struct configfs_attribute *nvmet_passthru_attrs[] = {
&nvmet_passthru_attr_device_path,
&nvmet_passthru_attr_enable,
&nvmet_passthru_attr_admin_timeout,
&nvmet_passthru_attr_io_timeout,
NULL,
};

15
drivers/nvme/target/core.c
View File

@ -757,8 +757,6 @@ void nvmet_cq_setup(struct nvmet_ctrl *ctrl, struct nvmet_cq *cq,
{
cq->qid = qid;
cq->size = size;
ctrl->cqs[qid] = cq;
}
void nvmet_sq_setup(struct nvmet_ctrl *ctrl, struct nvmet_sq *sq,
@ -1344,20 +1342,14 @@ u16 nvmet_alloc_ctrl(const char *subsysnqn, const char *hostnqn,
if (!ctrl->changed_ns_list)
goto out_free_ctrl;
ctrl->cqs = kcalloc(subsys->max_qid + 1,
sizeof(struct nvmet_cq *),
GFP_KERNEL);
if (!ctrl->cqs)
goto out_free_changed_ns_list;
ctrl->sqs = kcalloc(subsys->max_qid + 1,
sizeof(struct nvmet_sq *),
GFP_KERNEL);
if (!ctrl->sqs)
goto out_free_cqs;
goto out_free_changed_ns_list;
if (subsys->cntlid_min > subsys->cntlid_max)
goto out_free_cqs;
goto out_free_changed_ns_list;
ret = ida_simple_get(&cntlid_ida,
subsys->cntlid_min, subsys->cntlid_max,
@ -1395,8 +1387,6 @@ u16 nvmet_alloc_ctrl(const char *subsysnqn, const char *hostnqn,
out_free_sqs:
kfree(ctrl->sqs);
out_free_cqs:
kfree(ctrl->cqs);
out_free_changed_ns_list:
kfree(ctrl->changed_ns_list);
out_free_ctrl:
@ -1426,7 +1416,6 @@ static void nvmet_ctrl_free(struct kref *ref)
nvmet_async_events_free(ctrl);
kfree(ctrl->sqs);
kfree(ctrl->cqs);
kfree(ctrl->changed_ns_list);
kfree(ctrl);

1
drivers/nvme/target/discovery.c
View File

@ -69,6 +69,7 @@ void nvmet_subsys_disc_changed(struct nvmet_subsys *subsys,
struct nvmet_port *port;
struct nvmet_subsys_link *s;
lockdep_assert_held(&nvmet_config_sem);
nvmet_genctr++;
list_for_each_entry(port, nvmet_ports, global_entry)

81
drivers/nvme/target/fcloop.c
View File

@ -564,6 +564,50 @@ fcloop_call_host_done(struct nvmefc_fcp_req *fcpreq,
fcloop_tfcp_req_put(tfcp_req);
}
static bool drop_fabric_opcode;
#define DROP_OPCODE_MASK 0x00FF
/* fabrics opcode will have a bit set above 1st byte */
static int drop_opcode = -1;
static int drop_instance;
static int drop_amount;
static int drop_current_cnt;
/*
* Routine to parse io and determine if the io is to be dropped.
* Returns:
* 0 if io is not obstructed
* 1 if io was dropped
*/
static int check_for_drop(struct fcloop_fcpreq *tfcp_req)
{
struct nvmefc_fcp_req *fcpreq = tfcp_req->fcpreq;
struct nvme_fc_cmd_iu *cmdiu = fcpreq->cmdaddr;
struct nvme_command *sqe = &cmdiu->sqe;
if (drop_opcode == -1)
return 0;
pr_info("%s: seq opcd x%02x fctype x%02x: drop F %s op x%02x "
"inst %d start %d amt %d\n",
__func__, sqe->common.opcode, sqe->fabrics.fctype,
drop_fabric_opcode ? "y" : "n",
drop_opcode, drop_current_cnt, drop_instance, drop_amount);
if ((drop_fabric_opcode &&
(sqe->common.opcode != nvme_fabrics_command ||
sqe->fabrics.fctype != drop_opcode)) ||
(!drop_fabric_opcode && sqe->common.opcode != drop_opcode))
return 0;
if (++drop_current_cnt >= drop_instance) {
if (drop_current_cnt >= drop_instance + drop_amount)
drop_opcode = -1;
return 1;
}
return 0;
}
static void
fcloop_fcp_recv_work(struct work_struct *work)
{
@ -590,10 +634,14 @@ fcloop_fcp_recv_work(struct work_struct *work)
if (unlikely(aborted))
ret = -ECANCELED;
else
ret = nvmet_fc_rcv_fcp_req(tfcp_req->tport->targetport,
else {
if (likely(!check_for_drop(tfcp_req)))
ret = nvmet_fc_rcv_fcp_req(tfcp_req->tport->targetport,
&tfcp_req->tgt_fcp_req,
fcpreq->cmdaddr, fcpreq->cmdlen);
else
pr_info("%s: dropped command ********\n", __func__);
}
if (ret)
fcloop_call_host_done(fcpreq, tfcp_req, ret);
@ -1449,6 +1497,33 @@ fcloop_delete_target_port(struct device *dev, struct device_attribute *attr,
return ret ? ret : count;
}
static ssize_t
fcloop_set_cmd_drop(struct device *dev, struct device_attribute *attr,
const char *buf, size_t count)
{
int opcode, starting, amount;
if (sscanf(buf, "%x:%d:%d", &opcode, &starting, &amount) != 3)
return -EBADRQC;
drop_current_cnt = 0;
drop_fabric_opcode = (opcode & ~DROP_OPCODE_MASK) ? true : false;
drop_opcode = (opcode & DROP_OPCODE_MASK);
drop_instance = starting;
/* the check to drop routine uses instance + count to know when
* to end. Thus, if dropping 1 instance, count should be 0.
* so subtract 1 from the count.
*/
drop_amount = amount - 1;
pr_info("%s: DROP: Starting at instance %d of%s opcode x%x drop +%d "
"instances\n",
__func__, drop_instance, drop_fabric_opcode ? " fabric" : "",
drop_opcode, drop_amount);
return count;
}
static DEVICE_ATTR(add_local_port, 0200, NULL, fcloop_create_local_port);
static DEVICE_ATTR(del_local_port, 0200, NULL, fcloop_delete_local_port);
@ -1456,6 +1531,7 @@ static DEVICE_ATTR(add_remote_port, 0200, NULL, fcloop_create_remote_port);
static DEVICE_ATTR(del_remote_port, 0200, NULL, fcloop_delete_remote_port);
static DEVICE_ATTR(add_target_port, 0200, NULL, fcloop_create_target_port);
static DEVICE_ATTR(del_target_port, 0200, NULL, fcloop_delete_target_port);
static DEVICE_ATTR(set_cmd_drop, 0200, NULL, fcloop_set_cmd_drop);
static struct attribute *fcloop_dev_attrs[] = {
&dev_attr_add_local_port.attr,
@ -1464,6 +1540,7 @@ static struct attribute *fcloop_dev_attrs[] = {
&dev_attr_del_remote_port.attr,
&dev_attr_add_target_port.attr,
&dev_attr_del_target_port.attr,
&dev_attr_set_cmd_drop.attr,
NULL
};

2
drivers/nvme/target/loop.c
View File

@ -345,7 +345,7 @@ static int nvme_loop_configure_admin_queue(struct nvme_loop_ctrl *ctrl)
NVME_INLINE_SG_CNT * sizeof(struct scatterlist);
ctrl->admin_tag_set.driver_data = ctrl;
ctrl->admin_tag_set.nr_hw_queues = 1;
ctrl->admin_tag_set.timeout = ADMIN_TIMEOUT;
ctrl->admin_tag_set.timeout = NVME_ADMIN_TIMEOUT;
ctrl->admin_tag_set.flags = BLK_MQ_F_NO_SCHED;
ctrl->queues[0].ctrl = ctrl;

4
drivers/nvme/target/nvmet.h
View File

@ -164,7 +164,6 @@ static inline struct nvmet_port *ana_groups_to_port(
struct nvmet_ctrl {
struct nvmet_subsys *subsys;
struct nvmet_cq **cqs;
struct nvmet_sq **sqs;
bool cmd_seen;
@ -249,6 +248,8 @@ struct nvmet_subsys {
struct nvme_ctrl *passthru_ctrl;
char *passthru_ctrl_path;
struct config_group passthru_group;
unsigned int admin_timeout;
unsigned int io_timeout;
#endif /* CONFIG_NVME_TARGET_PASSTHRU */
};
@ -330,6 +331,7 @@ struct nvmet_req {
struct work_struct work;
} f;
struct {
struct bio inline_bio;
struct request *rq;
struct work_struct work;
bool use_workqueue;

37
drivers/nvme/target/passthru.c
View File

@ -188,35 +188,31 @@ static void nvmet_passthru_req_done(struct request *rq,
static int nvmet_passthru_map_sg(struct nvmet_req *req, struct request *rq)
{
struct scatterlist *sg;
int op_flags = 0;
struct bio *bio;
int i, ret;
int i;
if (req->sg_cnt > BIO_MAX_PAGES)
return -EINVAL;
if (req->cmd->common.opcode == nvme_cmd_flush)
op_flags = REQ_FUA;
else if (nvme_is_write(req->cmd))
op_flags = REQ_SYNC | REQ_IDLE;
bio = bio_alloc(GFP_KERNEL, req->sg_cnt);
bio->bi_end_io = bio_put;
bio->bi_opf = req_op(rq) | op_flags;
if (req->transfer_len <= NVMET_MAX_INLINE_DATA_LEN) {
bio = &req->p.inline_bio;
bio_init(bio, req->inline_bvec, ARRAY_SIZE(req->inline_bvec));
} else {
bio = bio_alloc(GFP_KERNEL, min(req->sg_cnt, BIO_MAX_PAGES));
bio->bi_end_io = bio_put;
}
bio->bi_opf = req_op(rq);
for_each_sg(req->sg, sg, req->sg_cnt, i) {
if (bio_add_pc_page(rq->q, bio, sg_page(sg), sg->length,
sg->offset) < sg->length) {
bio_put(bio);
if (bio != &req->p.inline_bio)
bio_put(bio);
return -EINVAL;
}
}
ret = blk_rq_append_bio(rq, &bio);
if (unlikely(ret)) {
bio_put(bio);
return ret;
}
blk_rq_bio_prep(rq, bio, req->sg_cnt);
return 0;
}
@ -227,6 +223,7 @@ static void nvmet_passthru_execute_cmd(struct nvmet_req *req)
struct request_queue *q = ctrl->admin_q;
struct nvme_ns *ns = NULL;
struct request *rq = NULL;
unsigned int timeout;
u32 effects;
u16 status;
int ret;
@ -242,14 +239,20 @@ static void nvmet_passthru_execute_cmd(struct nvmet_req *req)
}
q = ns->queue;
timeout = req->sq->ctrl->subsys->io_timeout;
} else {
timeout = req->sq->ctrl->subsys->admin_timeout;
}
rq = nvme_alloc_request(q, req->cmd, 0, NVME_QID_ANY);
rq = nvme_alloc_request(q, req->cmd, 0);
if (IS_ERR(rq)) {
status = NVME_SC_INTERNAL;
goto out_put_ns;
}
if (timeout)
rq->timeout = timeout;
if (req->sg_cnt) {
ret = nvmet_passthru_map_sg(req, rq);
if (unlikely(ret)) {

12
include/linux/blk-mq.h
View File

@ -593,6 +593,18 @@ static inline void blk_mq_cleanup_rq(struct request *rq)
rq->q->mq_ops->cleanup_rq(rq);
}
static inline void blk_rq_bio_prep(struct request *rq, struct bio *bio,
unsigned int nr_segs)
{
rq->nr_phys_segments = nr_segs;
rq->__data_len = bio->bi_iter.bi_size;
rq->bio = rq->biotail = bio;
rq->ioprio = bio_prio(bio);
if (bio->bi_disk)
rq->rq_disk = bio->bi_disk;
}
blk_qc_t blk_mq_submit_bio(struct bio *bio);
#endif