if (req->q->queuedata) {
struct nvme_ns *ns = req->q->disk->private_data;
- logging_enabled = ns->passthru_err_log_enabled;
+ logging_enabled = ns->head->passthru_err_log_enabled;
req->timeout = NVME_IO_TIMEOUT;
} else { /* no queuedata implies admin queue */
logging_enabled = nr->ctrl->passthru_err_log_enabled;
effects &= ~NVME_CMD_EFFECTS_CSE_MASK;
} else {
effects = le32_to_cpu(ctrl->effects->acs[opcode]);
+
+ /* Ignore execution restrictions if any relaxation bits are set */
+ if (effects & NVME_CMD_EFFECTS_CSER_MASK)
+ effects &= ~NVME_CMD_EFFECTS_CSE_MASK;
}
return effects;
{
struct nvme_ctrl *ctrl = ns->ctrl;
- BUILD_BUG_ON(PAGE_SIZE / sizeof(struct nvme_dsm_range) <
- NVME_DSM_MAX_RANGES);
-
if (ctrl->dmrsl && ctrl->dmrsl <= nvme_sect_to_lba(ns->head, UINT_MAX))
lim->max_hw_discard_sectors =
nvme_lba_to_sect(ns->head, ctrl->dmrsl);
if (ctrl->shutdown_timeout != shutdown_timeout)
dev_info(ctrl->device,
- "Shutdown timeout set to %u seconds\n",
+ "D3 entry latency set to %u seconds\n",
ctrl->shutdown_timeout);
} else
ctrl->shutdown_timeout = shutdown_timeout;
ns->disk = disk;
ns->queue = disk->queue;
- ns->passthru_err_log_enabled = false;
if (ctrl->opts && ctrl->opts->data_digest)
blk_queue_flag_set(QUEUE_FLAG_STABLE_WRITES, ns->queue);
/*
* Set ns->disk->device->driver_data to ns so we can access
- * ns->logging_enabled in nvme_passthru_err_log_enabled_store() and
- * nvme_passthru_err_log_enabled_show().
+ * ns->head->passthru_err_log_enabled in
+ * nvme_io_passthru_err_log_enabled_[store | show]().
*/
dev_set_drvdata(disk_to_dev(ns->disk), ns);
static void nvme_get_fw_slot_info(struct nvme_ctrl *ctrl)
{
struct nvme_fw_slot_info_log *log;
+ u8 next_fw_slot, cur_fw_slot;
log = kmalloc(sizeof(*log), GFP_KERNEL);
if (!log)
goto out_free_log;
}
- if (log->afi & 0x70 || !(log->afi & 0x7)) {
+ cur_fw_slot = log->afi & 0x7;
+ next_fw_slot = (log->afi & 0x70) >> 4;
+ if (!cur_fw_slot || (next_fw_slot && (cur_fw_slot != next_fw_slot))) {
dev_info(ctrl->device,
"Firmware is activated after next Controller Level Reset\n");
goto out_free_log;
}
- memcpy(ctrl->subsys->firmware_rev, &log->frs[(log->afi & 0x7) - 1],
+ memcpy(ctrl->subsys->firmware_rev, &log->frs[cur_fw_slot - 1],
sizeof(ctrl->subsys->firmware_rev));
out_free_log:
set->ops = ops;
set->queue_depth = NVME_AQ_MQ_TAG_DEPTH;
if (ctrl->ops->flags & NVME_F_FABRICS)
- set->reserved_tags = NVMF_RESERVED_TAGS;
+ /* Reserved for fabric connect and keep alive */
+ set->reserved_tags = 2;
set->numa_node = ctrl->numa_node;
set->flags = BLK_MQ_F_NO_SCHED;
if (ctrl->ops->flags & NVME_F_BLOCKING)
if (ctrl->quirks & NVME_QUIRK_SHARED_TAGS)
set->reserved_tags = NVME_AQ_DEPTH;
else if (ctrl->ops->flags & NVME_F_FABRICS)
- set->reserved_tags = NVMF_RESERVED_TAGS;
+ /* Reserved for fabric connect */
+ set->reserved_tags = 1;
set->numa_node = ctrl->numa_node;
set->flags = BLK_MQ_F_SHOULD_MERGE;
if (ctrl->ops->flags & NVME_F_BLOCKING)
struct device_attribute *attr, const char *buf, size_t count)
{
struct nvme_ctrl *ctrl = dev_get_drvdata(dev);
- int err;
bool passthru_err_log_enabled;
+ int err;
err = kstrtobool(buf, &passthru_err_log_enabled);
if (err)
return count;
}
+static inline struct nvme_ns_head *dev_to_ns_head(struct device *dev)
+{
+ struct gendisk *disk = dev_to_disk(dev);
+
+ if (nvme_disk_is_ns_head(disk))
+ return disk->private_data;
+ return nvme_get_ns_from_dev(dev)->head;
+}
+
static ssize_t nvme_io_passthru_err_log_enabled_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
- struct nvme_ns *n = dev_get_drvdata(dev);
+ struct nvme_ns_head *head = dev_to_ns_head(dev);
- return sysfs_emit(buf, n->passthru_err_log_enabled ? "on\n" : "off\n");
+ return sysfs_emit(buf, head->passthru_err_log_enabled ? "on\n" : "off\n");
}
static ssize_t nvme_io_passthru_err_log_enabled_store(struct device *dev,
struct device_attribute *attr, const char *buf, size_t count)
{
- struct nvme_ns *ns = dev_get_drvdata(dev);
- int err;
+ struct nvme_ns_head *head = dev_to_ns_head(dev);
bool passthru_err_log_enabled;
+ int err;
err = kstrtobool(buf, &passthru_err_log_enabled);
if (err)
return -EINVAL;
- ns->passthru_err_log_enabled = passthru_err_log_enabled;
+ head->passthru_err_log_enabled = passthru_err_log_enabled;
return count;
}
__ATTR(passthru_err_log_enabled, S_IRUGO | S_IWUSR, \
nvme_io_passthru_err_log_enabled_show, nvme_io_passthru_err_log_enabled_store);
-static inline struct nvme_ns_head *dev_to_ns_head(struct device *dev)
-{
- struct gendisk *disk = dev_to_disk(dev);
-
- if (nvme_disk_is_ns_head(disk))
- return disk->private_data;
- return nvme_get_ns_from_dev(dev)->head;
-}
-
static ssize_t wwid_show(struct device *dev, struct device_attribute *attr,
char *buf)
{
struct block_device *bdev = disk->part0;
int ret;
- if (IS_ENABLED(CONFIG_NVME_MULTIPATH) &&
- bdev->bd_disk->fops == &nvme_ns_head_ops)
+ if (nvme_disk_is_ns_head(bdev->bd_disk))
ret = ns_head_update_nuse(head);
else
ret = ns_update_nuse(bdev->bd_disk->private_data);
module_param(so_priority, int, 0644);
MODULE_PARM_DESC(so_priority, "nvme tcp socket optimize priority");
+ /*
+ * Use the unbound workqueue for nvme_tcp_wq, then we can set the cpu affinity
+ * from sysfs.
+ */
+ static bool wq_unbound;
+ module_param(wq_unbound, bool, 0644);
+ MODULE_PARM_DESC(wq_unbound, "Use unbound workqueue for nvme-tcp IO context (default false)");
+
/*
* TLS handshake timeout
*/
static void nvme_tcp_free_queue(struct nvme_ctrl *nctrl, int qid)
{
- struct page *page;
struct nvme_tcp_ctrl *ctrl = to_tcp_ctrl(nctrl);
struct nvme_tcp_queue *queue = &ctrl->queues[qid];
unsigned int noreclaim_flag;
if (queue->hdr_digest || queue->data_digest)
nvme_tcp_free_crypto(queue);
- if (queue->pf_cache.va) {
- page = virt_to_head_page(queue->pf_cache.va);
- __page_frag_cache_drain(page, queue->pf_cache.pagecnt_bias);
- queue->pf_cache.va = NULL;
- }
+ page_frag_cache_drain(&queue->pf_cache);
noreclaim_flag = memalloc_noreclaim_save();
/* ->sock will be released by fput() */
else if (nvme_tcp_poll_queue(queue))
n = qid - ctrl->io_queues[HCTX_TYPE_DEFAULT] -
ctrl->io_queues[HCTX_TYPE_READ] - 1;
- queue->io_cpu = cpumask_next_wrap(n - 1, cpu_online_mask, -1, false);
+ if (wq_unbound)
+ queue->io_cpu = WORK_CPU_UNBOUND;
+ else
+ queue->io_cpu = cpumask_next_wrap(n - 1, cpu_online_mask, -1, false);
}
static void nvme_tcp_tls_done(void *data, int status, key_serial_t pskid)
static int __init nvme_tcp_init_module(void)
{
+ unsigned int wq_flags = WQ_MEM_RECLAIM | WQ_HIGHPRI | WQ_SYSFS;
+
BUILD_BUG_ON(sizeof(struct nvme_tcp_hdr) != 8);
BUILD_BUG_ON(sizeof(struct nvme_tcp_cmd_pdu) != 72);
BUILD_BUG_ON(sizeof(struct nvme_tcp_data_pdu) != 24);
BUILD_BUG_ON(sizeof(struct nvme_tcp_icresp_pdu) != 128);
BUILD_BUG_ON(sizeof(struct nvme_tcp_term_pdu) != 24);
- nvme_tcp_wq = alloc_workqueue("nvme_tcp_wq",
- WQ_MEM_RECLAIM | WQ_HIGHPRI, 0);
+ if (wq_unbound)
+ wq_flags |= WQ_UNBOUND;
+
+ nvme_tcp_wq = alloc_workqueue("nvme_tcp_wq", wq_flags, 0);
if (!nvme_tcp_wq)
return -ENOMEM;
pr_err("bad nvme-tcp pdu length (%d)\n",
le32_to_cpu(icreq->hdr.plen));
nvmet_tcp_fatal_error(queue);
+ return -EPROTO;
}
if (icreq->pfv != NVME_TCP_PFV_1_0) {
static void nvmet_tcp_release_queue_work(struct work_struct *w)
{
- struct page *page;
struct nvmet_tcp_queue *queue =
container_of(w, struct nvmet_tcp_queue, release_work);
if (queue->hdr_digest || queue->data_digest)
nvmet_tcp_free_crypto(queue);
ida_free(&nvmet_tcp_queue_ida, queue->idx);
- page = virt_to_head_page(queue->pf_cache.va);
- __page_frag_cache_drain(page, queue->pf_cache.pagecnt_bias);
+ page_frag_cache_drain(&queue->pf_cache);
kfree(queue);
}