MODULE_PARM_DESC(io_timeout, "timeout in seconds for I/O");
EXPORT_SYMBOL_GPL(nvme_io_timeout);
-unsigned char shutdown_timeout = 5;
+static unsigned char shutdown_timeout = 5;
module_param(shutdown_timeout, byte, 0644);
MODULE_PARM_DESC(shutdown_timeout, "timeout in seconds for controller shutdown");
static int nvme_char_major;
module_param(nvme_char_major, int, 0);
-static unsigned long default_ps_max_latency_us = 25000;
+static unsigned long default_ps_max_latency_us = 100000;
module_param(default_ps_max_latency_us, ulong, 0644);
MODULE_PARM_DESC(default_ps_max_latency_us,
"max power saving latency for new devices; use PM QOS to change per device");
module_param(force_apst, bool, 0644);
MODULE_PARM_DESC(force_apst, "allow APST for newly enumerated devices even if quirked off");
+struct workqueue_struct *nvme_wq;
+EXPORT_SYMBOL_GPL(nvme_wq);
+
static LIST_HEAD(nvme_ctrl_list);
static DEFINE_SPINLOCK(dev_list_lock);
static struct class *nvme_class;
-static int nvme_error_status(struct request *req)
+int nvme_reset_ctrl(struct nvme_ctrl *ctrl)
+{
+ if (!nvme_change_ctrl_state(ctrl, NVME_CTRL_RESETTING))
+ return -EBUSY;
+ if (!queue_work(nvme_wq, &ctrl->reset_work))
+ return -EBUSY;
+ return 0;
+}
+EXPORT_SYMBOL_GPL(nvme_reset_ctrl);
+
+static int nvme_reset_ctrl_sync(struct nvme_ctrl *ctrl)
+{
+ int ret;
+
+ ret = nvme_reset_ctrl(ctrl);
+ if (!ret)
+ flush_work(&ctrl->reset_work);
+ return ret;
+}
+
+static blk_status_t nvme_error_status(struct request *req)
{
switch (nvme_req(req)->status & 0x7ff) {
case NVME_SC_SUCCESS:
- return 0;
+ return BLK_STS_OK;
case NVME_SC_CAP_EXCEEDED:
- return -ENOSPC;
- default:
- return -EIO;
-
- /*
- * XXX: these errors are a nasty side-band protocol to
- * drivers/md/dm-mpath.c:noretry_error() that aren't documented
- * anywhere..
- */
- case NVME_SC_CMD_SEQ_ERROR:
- return -EILSEQ;
+ return BLK_STS_NOSPC;
case NVME_SC_ONCS_NOT_SUPPORTED:
- return -EOPNOTSUPP;
+ return BLK_STS_NOTSUPP;
case NVME_SC_WRITE_FAULT:
case NVME_SC_READ_ERROR:
case NVME_SC_UNWRITTEN_BLOCK:
- return -ENODATA;
+ return BLK_STS_MEDIUM;
+ default:
+ return BLK_STS_IOERR;
}
}
switch (old_state) {
case NVME_CTRL_NEW:
case NVME_CTRL_LIVE:
- case NVME_CTRL_RECONNECTING:
changed = true;
/* FALLTHRU */
default:
cmnd->common.nsid = cpu_to_le32(ns->ns_id);
}
-static inline int nvme_setup_discard(struct nvme_ns *ns, struct request *req,
+static blk_status_t nvme_setup_discard(struct nvme_ns *ns, struct request *req,
struct nvme_command *cmnd)
{
unsigned short segments = blk_rq_nr_discard_segments(req), n = 0;
range = kmalloc_array(segments, sizeof(*range), GFP_ATOMIC);
if (!range)
- return BLK_MQ_RQ_QUEUE_BUSY;
+ return BLK_STS_RESOURCE;
__rq_for_each_bio(bio, req) {
u64 slba = nvme_block_nr(ns, bio->bi_iter.bi_sector);
if (WARN_ON_ONCE(n != segments)) {
kfree(range);
- return BLK_MQ_RQ_QUEUE_ERROR;
+ return BLK_STS_IOERR;
}
memset(cmnd, 0, sizeof(*cmnd));
req->special_vec.bv_len = sizeof(*range) * segments;
req->rq_flags |= RQF_SPECIAL_PAYLOAD;
- return BLK_MQ_RQ_QUEUE_OK;
+ return BLK_STS_OK;
}
-static inline void nvme_setup_rw(struct nvme_ns *ns, struct request *req,
- struct nvme_command *cmnd)
+static inline blk_status_t nvme_setup_rw(struct nvme_ns *ns,
+ struct request *req, struct nvme_command *cmnd)
{
u16 control = 0;
u32 dsmgmt = 0;
+ /*
+ * If formated with metadata, require the block layer provide a buffer
+ * unless this namespace is formated such that the metadata can be
+ * stripped/generated by the controller with PRACT=1.
+ */
+ if (ns && ns->ms && (!ns->pi_type || ns->ms != 8) &&
+ !blk_integrity_rq(req) && !blk_rq_is_passthrough(req))
+ return BLK_STS_NOTSUPP;
+
if (req->cmd_flags & REQ_FUA)
control |= NVME_RW_FUA;
if (req->cmd_flags & (REQ_FAILFAST_DEV | REQ_RAHEAD))
cmnd->rw.control = cpu_to_le16(control);
cmnd->rw.dsmgmt = cpu_to_le32(dsmgmt);
+ return 0;
}
-int nvme_setup_cmd(struct nvme_ns *ns, struct request *req,
+blk_status_t nvme_setup_cmd(struct nvme_ns *ns, struct request *req,
struct nvme_command *cmd)
{
- int ret = BLK_MQ_RQ_QUEUE_OK;
+ blk_status_t ret = BLK_STS_OK;
if (!(req->rq_flags & RQF_DONTPREP)) {
nvme_req(req)->retries = 0;
break;
case REQ_OP_READ:
case REQ_OP_WRITE:
- nvme_setup_rw(ns, req, cmd);
+ ret = nvme_setup_rw(ns, req, cmd);
break;
default:
WARN_ON_ONCE(1);
- return BLK_MQ_RQ_QUEUE_ERROR;
+ return BLK_STS_IOERR;
}
cmd->common.command_id = req->tag;
result, timeout);
}
-static void nvme_keep_alive_end_io(struct request *rq, int error)
+static void nvme_keep_alive_end_io(struct request *rq, blk_status_t status)
{
struct nvme_ctrl *ctrl = rq->end_io_data;
blk_mq_free_request(rq);
- if (error) {
+ if (status) {
dev_err(ctrl->device,
- "failed nvme_keep_alive_end_io error=%d\n", error);
+ "failed nvme_keep_alive_end_io error=%d\n",
+ status);
return;
}
if (nvme_keep_alive(ctrl)) {
/* allocation failure, reset the controller */
dev_err(ctrl->device, "keep-alive failed\n");
- ctrl->ops->reset_ctrl(ctrl);
+ nvme_reset_ctrl_sync(ctrl);
return;
}
}
return error;
}
+static int nvme_identify_ns_descs(struct nvme_ns *ns, unsigned nsid)
+{
+ struct nvme_command c = { };
+ int status;
+ void *data;
+ int pos;
+ int len;
+
+ c.identify.opcode = nvme_admin_identify;
+ c.identify.nsid = cpu_to_le32(nsid);
+ c.identify.cns = NVME_ID_CNS_NS_DESC_LIST;
+
+ data = kzalloc(NVME_IDENTIFY_DATA_SIZE, GFP_KERNEL);
+ if (!data)
+ return -ENOMEM;
+
+ status = nvme_submit_sync_cmd(ns->ctrl->admin_q, &c, data,
+ NVME_IDENTIFY_DATA_SIZE);
+ if (status)
+ goto free_data;
+
+ for (pos = 0; pos < NVME_IDENTIFY_DATA_SIZE; pos += len) {
+ struct nvme_ns_id_desc *cur = data + pos;
+
+ if (cur->nidl == 0)
+ break;
+
+ switch (cur->nidt) {
+ case NVME_NIDT_EUI64:
+ if (cur->nidl != NVME_NIDT_EUI64_LEN) {
+ dev_warn(ns->ctrl->device,
+ "ctrl returned bogus length: %d for NVME_NIDT_EUI64\n",
+ cur->nidl);
+ goto free_data;
+ }
+ len = NVME_NIDT_EUI64_LEN;
+ memcpy(ns->eui, data + pos + sizeof(*cur), len);
+ break;
+ case NVME_NIDT_NGUID:
+ if (cur->nidl != NVME_NIDT_NGUID_LEN) {
+ dev_warn(ns->ctrl->device,
+ "ctrl returned bogus length: %d for NVME_NIDT_NGUID\n",
+ cur->nidl);
+ goto free_data;
+ }
+ len = NVME_NIDT_NGUID_LEN;
+ memcpy(ns->nguid, data + pos + sizeof(*cur), len);
+ break;
+ case NVME_NIDT_UUID:
+ if (cur->nidl != NVME_NIDT_UUID_LEN) {
+ dev_warn(ns->ctrl->device,
+ "ctrl returned bogus length: %d for NVME_NIDT_UUID\n",
+ cur->nidl);
+ goto free_data;
+ }
+ len = NVME_NIDT_UUID_LEN;
+ uuid_copy(&ns->uuid, data + pos + sizeof(*cur));
+ break;
+ default:
+ /* Skip unnkown types */
+ len = cur->nidl;
+ break;
+ }
+
+ len += sizeof(*cur);
+ }
+free_data:
+ kfree(data);
+ return status;
+}
+
static int nvme_identify_ns_list(struct nvme_ctrl *dev, unsigned nsid, __le32 *ns_list)
{
struct nvme_command c = { };
* access to the admin queue, as that might be only way to fix them up.
*/
if (status > 0) {
- dev_err(ctrl->dev, "Could not set queue count (%d)\n", status);
+ dev_err(ctrl->device, "Could not set queue count (%d)\n", status);
*count = 0;
} else {
nr_io_queues = min(result & 0xffff, result >> 16) + 1;
if (ns->ctrl->vs >= NVME_VS(1, 1, 0))
memcpy(ns->eui, (*id)->eui64, sizeof(ns->eui));
if (ns->ctrl->vs >= NVME_VS(1, 2, 0))
- memcpy(ns->uuid, (*id)->nguid, sizeof(ns->uuid));
+ memcpy(ns->nguid, (*id)->nguid, sizeof(ns->nguid));
+ if (ns->ctrl->vs >= NVME_VS(1, 3, 0)) {
+ /* Don't treat error as fatal we potentially
+ * already have a NGUID or EUI-64
+ */
+ if (nvme_identify_ns_descs(ns, ns->ns_id))
+ dev_warn(ns->ctrl->device,
+ "%s: Identify Descriptors failed\n", __func__);
+ }
return 0;
}
int nvme_shutdown_ctrl(struct nvme_ctrl *ctrl)
{
- unsigned long timeout = SHUTDOWN_TIMEOUT + jiffies;
+ unsigned long timeout = jiffies + (shutdown_timeout * HZ);
u32 csts;
int ret;
* transitioning between power states. Therefore, when running
* in any given state, we will enter the next lower-power
* non-operational state after waiting 50 * (enlat + exlat)
- * microseconds, as long as that state's total latency is under
+ * microseconds, as long as that state's exit latency is under
* the requested maximum latency.
*
* We will not autonomously enter any non-operational state for
* lowest-power state, not the number of states.
*/
for (state = (int)ctrl->npss; state >= 0; state--) {
- u64 total_latency_us, transition_ms;
+ u64 total_latency_us, exit_latency_us, transition_ms;
if (target)
table->entries[state] = target;
NVME_PS_FLAGS_NON_OP_STATE))
continue;
- total_latency_us =
- (u64)le32_to_cpu(ctrl->psd[state].entry_lat) +
- + le32_to_cpu(ctrl->psd[state].exit_lat);
- if (total_latency_us > ctrl->ps_max_latency_us)
+ exit_latency_us =
+ (u64)le32_to_cpu(ctrl->psd[state].exit_lat);
+ if (exit_latency_us > ctrl->ps_max_latency_us)
continue;
+ total_latency_us =
+ exit_latency_us +
+ le32_to_cpu(ctrl->psd[state].entry_lat);
+
/*
* This state is good. Use it as the APST idle
* target for higher power states.
}
if (force_apst && (ctrl->quirks & NVME_QUIRK_NO_DEEPEST_PS)) {
- dev_warn(ctrl->dev, "forcibly allowing all power states due to nvme_core.force_apst -- use at your own risk\n");
+ dev_warn(ctrl->device, "forcibly allowing all power states due to nvme_core.force_apst -- use at your own risk\n");
ctrl->quirks &= ~NVME_QUIRK_NO_DEEPEST_PS;
}
prev_apsta = ctrl->apsta;
if (ctrl->quirks & NVME_QUIRK_NO_APST) {
if (force_apst && id->apsta) {
- dev_warn(ctrl->dev, "forcibly allowing APST due to nvme_core.force_apst -- use at your own risk\n");
+ dev_warn(ctrl->device, "forcibly allowing APST due to nvme_core.force_apst -- use at your own risk\n");
ctrl->apsta = 1;
} else {
ctrl->apsta = 0;
ret = -EINVAL;
if (!ctrl->opts->discovery_nqn && !ctrl->kas) {
- dev_err(ctrl->dev,
+ dev_err(ctrl->device,
"keep-alive support is mandatory for fabrics\n");
ret = -EINVAL;
}
} else {
ctrl->cntlid = le16_to_cpu(id->cntlid);
+ ctrl->hmpre = le32_to_cpu(id->hmpre);
+ ctrl->hmmin = le32_to_cpu(id->hmmin);
}
kfree(id);
return nvme_dev_user_cmd(ctrl, argp);
case NVME_IOCTL_RESET:
dev_warn(ctrl->device, "resetting controller\n");
- return ctrl->ops->reset_ctrl(ctrl);
+ return nvme_reset_ctrl_sync(ctrl);
case NVME_IOCTL_SUBSYS_RESET:
return nvme_reset_subsystem(ctrl);
case NVME_IOCTL_RESCAN:
struct nvme_ctrl *ctrl = dev_get_drvdata(dev);
int ret;
- ret = ctrl->ops->reset_ctrl(ctrl);
+ ret = nvme_reset_ctrl_sync(ctrl);
if (ret < 0)
return ret;
return count;
int serial_len = sizeof(ctrl->serial);
int model_len = sizeof(ctrl->model);
- if (memchr_inv(ns->uuid, 0, sizeof(ns->uuid)))
- return sprintf(buf, "eui.%16phN\n", ns->uuid);
+ if (memchr_inv(ns->nguid, 0, sizeof(ns->nguid)))
+ return sprintf(buf, "eui.%16phN\n", ns->nguid);
if (memchr_inv(ns->eui, 0, sizeof(ns->eui)))
return sprintf(buf, "eui.%8phN\n", ns->eui);
}
static DEVICE_ATTR(wwid, S_IRUGO, wwid_show, NULL);
+static ssize_t nguid_show(struct device *dev, struct device_attribute *attr,
+ char *buf)
+{
+ struct nvme_ns *ns = nvme_get_ns_from_dev(dev);
+ return sprintf(buf, "%pU\n", ns->nguid);
+}
+static DEVICE_ATTR(nguid, S_IRUGO, nguid_show, NULL);
+
static ssize_t uuid_show(struct device *dev, struct device_attribute *attr,
char *buf)
{
struct nvme_ns *ns = nvme_get_ns_from_dev(dev);
- return sprintf(buf, "%pU\n", ns->uuid);
+
+ /* For backward compatibility expose the NGUID to userspace if
+ * we have no UUID set
+ */
+ if (uuid_is_null(&ns->uuid)) {
+ printk_ratelimited(KERN_WARNING
+ "No UUID available providing old NGUID\n");
+ return sprintf(buf, "%pU\n", ns->nguid);
+ }
+ return sprintf(buf, "%pU\n", &ns->uuid);
}
static DEVICE_ATTR(uuid, S_IRUGO, uuid_show, NULL);
static struct attribute *nvme_ns_attrs[] = {
&dev_attr_wwid.attr,
&dev_attr_uuid.attr,
+ &dev_attr_nguid.attr,
&dev_attr_eui.attr,
&dev_attr_nsid.attr,
NULL,
struct nvme_ns *ns = nvme_get_ns_from_dev(dev);
if (a == &dev_attr_uuid.attr) {
- if (!memchr_inv(ns->uuid, 0, sizeof(ns->uuid)))
+ if (uuid_is_null(&ns->uuid) ||
+ !memchr_inv(ns->nguid, 0, sizeof(ns->nguid)))
+ return 0;
+ }
+ if (a == &dev_attr_nguid.attr) {
+ if (!memchr_inv(ns->nguid, 0, sizeof(ns->nguid)))
return 0;
}
if (a == &dev_attr_eui.attr) {
if (nvme_nvm_ns_supported(ns, id) &&
nvme_nvm_register(ns, disk_name, node)) {
- dev_warn(ctrl->dev, "%s: LightNVM init failure\n", __func__);
+ dev_warn(ctrl->device, "%s: LightNVM init failure\n", __func__);
goto out_free_id;
}
* removal.
*/
if (ctrl->state == NVME_CTRL_LIVE)
- schedule_work(&ctrl->scan_work);
+ queue_work(nvme_wq, &ctrl->scan_work);
}
EXPORT_SYMBOL_GPL(nvme_queue_scan);
/*FALLTHRU*/
case NVME_SC_ABORT_REQ:
++ctrl->event_limit;
- schedule_work(&ctrl->async_event_work);
+ queue_work(nvme_wq, &ctrl->async_event_work);
break;
default:
break;
void nvme_queue_async_events(struct nvme_ctrl *ctrl)
{
ctrl->event_limit = NVME_NR_AERS;
- schedule_work(&ctrl->async_event_work);
+ queue_work(nvme_wq, &ctrl->async_event_work);
}
EXPORT_SYMBOL_GPL(nvme_queue_async_events);
struct nvme_ns *ns;
mutex_lock(&ctrl->namespaces_mutex);
+
+ /* Forcibly start all queues to avoid having stuck requests */
+ blk_mq_start_hw_queues(ctrl->admin_q);
+
list_for_each_entry(ns, &ctrl->namespaces, list) {
/*
* Revalidating a dead namespace sets capacity to 0. This will
{
int result;
+ nvme_wq = alloc_workqueue("nvme-wq",
+ WQ_UNBOUND | WQ_MEM_RECLAIM | WQ_SYSFS, 0);
+ if (!nvme_wq)
+ return -ENOMEM;
+
result = __register_chrdev(nvme_char_major, 0, NVME_MINORS, "nvme",
&nvme_dev_fops);
if (result < 0)
- return result;
+ goto destroy_wq;
else if (result > 0)
nvme_char_major = result;
return 0;
- unregister_chrdev:
+unregister_chrdev:
__unregister_chrdev(nvme_char_major, 0, NVME_MINORS, "nvme");
+destroy_wq:
+ destroy_workqueue(nvme_wq);
return result;
}
{
class_destroy(nvme_class);
__unregister_chrdev(nvme_char_major, 0, NVME_MINORS, "nvme");
+ destroy_workqueue(nvme_wq);
}
MODULE_LICENSE("GPL");