diff options
Diffstat (limited to 'drivers/nvme')
-rw-r--r-- | drivers/nvme/host/Kconfig | 4 | ||||
-rw-r--r-- | drivers/nvme/host/core.c | 166 | ||||
-rw-r--r-- | drivers/nvme/host/fabrics.c | 48 | ||||
-rw-r--r-- | drivers/nvme/host/fabrics.h | 13 | ||||
-rw-r--r-- | drivers/nvme/host/lightnvm.c | 33 | ||||
-rw-r--r-- | drivers/nvme/host/nvme.h | 30 | ||||
-rw-r--r-- | drivers/nvme/host/pci.c | 9 | ||||
-rw-r--r-- | drivers/nvme/host/rdma.c | 188 | ||||
-rw-r--r-- | drivers/nvme/host/scsi.c | 80 | ||||
-rw-r--r-- | drivers/nvme/target/Kconfig | 2 | ||||
-rw-r--r-- | drivers/nvme/target/admin-cmd.c | 88 | ||||
-rw-r--r-- | drivers/nvme/target/io-cmd.c | 3 | ||||
-rw-r--r-- | drivers/nvme/target/loop.c | 4 | ||||
-rw-r--r-- | drivers/nvme/target/rdma.c | 7 |
14 files changed, 407 insertions, 268 deletions
diff --git a/drivers/nvme/host/Kconfig b/drivers/nvme/host/Kconfig index db39d53cdfb9..f7d37a62f874 100644 --- a/drivers/nvme/host/Kconfig +++ b/drivers/nvme/host/Kconfig @@ -30,8 +30,8 @@ config NVME_FABRICS config NVME_RDMA tristate "NVM Express over Fabrics RDMA host driver" - depends on INFINIBAND - depends on BLK_DEV_NVME + depends on INFINIBAND && BLOCK + select NVME_CORE select NVME_FABRICS select SG_POOL help diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 7ff2e820bbf4..4669c052239e 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -81,10 +81,12 @@ EXPORT_SYMBOL_GPL(nvme_cancel_request); bool nvme_change_ctrl_state(struct nvme_ctrl *ctrl, enum nvme_ctrl_state new_state) { - enum nvme_ctrl_state old_state = ctrl->state; + enum nvme_ctrl_state old_state; bool changed = false; spin_lock_irq(&ctrl->lock); + + old_state = ctrl->state; switch (new_state) { case NVME_CTRL_LIVE: switch (old_state) { @@ -140,11 +142,12 @@ bool nvme_change_ctrl_state(struct nvme_ctrl *ctrl, default: break; } - spin_unlock_irq(&ctrl->lock); if (changed) ctrl->state = new_state; + spin_unlock_irq(&ctrl->lock); + return changed; } EXPORT_SYMBOL_GPL(nvme_change_ctrl_state); @@ -153,12 +156,14 @@ static void nvme_free_ns(struct kref *kref) { struct nvme_ns *ns = container_of(kref, struct nvme_ns, kref); - if (ns->type == NVME_NS_LIGHTNVM) - nvme_nvm_unregister(ns->queue, ns->disk->disk_name); + if (ns->ndev) + nvme_nvm_unregister(ns); - spin_lock(&dev_list_lock); - ns->disk->private_data = NULL; - spin_unlock(&dev_list_lock); + if (ns->disk) { + spin_lock(&dev_list_lock); + ns->disk->private_data = NULL; + spin_unlock(&dev_list_lock); + } put_disk(ns->disk); ida_simple_remove(&ns->ctrl->ns_ida, ns->instance); @@ -594,7 +599,7 @@ int nvme_identify_ns(struct nvme_ctrl *dev, unsigned nsid, } int nvme_get_features(struct nvme_ctrl *dev, unsigned fid, unsigned nsid, - dma_addr_t dma_addr, u32 *result) + void *buffer, size_t buflen, u32 *result) { struct nvme_command c; struct nvme_completion cqe; @@ -603,18 +608,17 @@ int nvme_get_features(struct nvme_ctrl *dev, unsigned fid, unsigned nsid, memset(&c, 0, sizeof(c)); c.features.opcode = nvme_admin_get_features; c.features.nsid = cpu_to_le32(nsid); - c.features.dptr.prp1 = cpu_to_le64(dma_addr); c.features.fid = cpu_to_le32(fid); - ret = __nvme_submit_sync_cmd(dev->admin_q, &c, &cqe, NULL, 0, 0, + ret = __nvme_submit_sync_cmd(dev->admin_q, &c, &cqe, buffer, buflen, 0, NVME_QID_ANY, 0, 0); - if (ret >= 0) + if (ret >= 0 && result) *result = le32_to_cpu(cqe.result); return ret; } int nvme_set_features(struct nvme_ctrl *dev, unsigned fid, unsigned dword11, - dma_addr_t dma_addr, u32 *result) + void *buffer, size_t buflen, u32 *result) { struct nvme_command c; struct nvme_completion cqe; @@ -622,13 +626,12 @@ int nvme_set_features(struct nvme_ctrl *dev, unsigned fid, unsigned dword11, memset(&c, 0, sizeof(c)); c.features.opcode = nvme_admin_set_features; - c.features.dptr.prp1 = cpu_to_le64(dma_addr); c.features.fid = cpu_to_le32(fid); c.features.dword11 = cpu_to_le32(dword11); - ret = __nvme_submit_sync_cmd(dev->admin_q, &c, &cqe, NULL, 0, 0, - NVME_QID_ANY, 0, 0); - if (ret >= 0) + ret = __nvme_submit_sync_cmd(dev->admin_q, &c, &cqe, + buffer, buflen, 0, NVME_QID_ANY, 0, 0); + if (ret >= 0 && result) *result = le32_to_cpu(cqe.result); return ret; } @@ -661,7 +664,7 @@ int nvme_set_queue_count(struct nvme_ctrl *ctrl, int *count) u32 result; int status, nr_io_queues; - status = nvme_set_features(ctrl, NVME_FEAT_NUM_QUEUES, q_count, 0, + status = nvme_set_features(ctrl, NVME_FEAT_NUM_QUEUES, q_count, NULL, 0, &result); if (status < 0) return status; @@ -885,42 +888,32 @@ static void nvme_config_discard(struct nvme_ns *ns) queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, ns->queue); } -static int nvme_revalidate_disk(struct gendisk *disk) +static int nvme_revalidate_ns(struct nvme_ns *ns, struct nvme_id_ns **id) { - struct nvme_ns *ns = disk->private_data; - struct nvme_id_ns *id; - u8 lbaf, pi_type; - u16 old_ms; - unsigned short bs; - - if (test_bit(NVME_NS_DEAD, &ns->flags)) { - set_capacity(disk, 0); - return -ENODEV; - } - if (nvme_identify_ns(ns->ctrl, ns->ns_id, &id)) { - dev_warn(disk_to_dev(ns->disk), "%s: Identify failure\n", - __func__); - return -ENODEV; - } - if (id->ncap == 0) { - kfree(id); + if (nvme_identify_ns(ns->ctrl, ns->ns_id, id)) { + dev_warn(ns->ctrl->dev, "%s: Identify failure\n", __func__); return -ENODEV; } - if (nvme_nvm_ns_supported(ns, id) && ns->type != NVME_NS_LIGHTNVM) { - if (nvme_nvm_register(ns->queue, disk->disk_name)) { - dev_warn(disk_to_dev(ns->disk), - "%s: LightNVM init failure\n", __func__); - kfree(id); - return -ENODEV; - } - ns->type = NVME_NS_LIGHTNVM; + if ((*id)->ncap == 0) { + kfree(*id); + return -ENODEV; } if (ns->ctrl->vs >= NVME_VS(1, 1)) - memcpy(ns->eui, id->eui64, sizeof(ns->eui)); + memcpy(ns->eui, (*id)->eui64, sizeof(ns->eui)); if (ns->ctrl->vs >= NVME_VS(1, 2)) - memcpy(ns->uuid, id->nguid, sizeof(ns->uuid)); + memcpy(ns->uuid, (*id)->nguid, sizeof(ns->uuid)); + + return 0; +} + +static void __nvme_revalidate_disk(struct gendisk *disk, struct nvme_id_ns *id) +{ + struct nvme_ns *ns = disk->private_data; + u8 lbaf, pi_type; + u16 old_ms; + unsigned short bs; old_ms = ns->ms; lbaf = id->flbas & NVME_NS_FLBAS_LBA_MASK; @@ -959,8 +952,26 @@ static int nvme_revalidate_disk(struct gendisk *disk) if (ns->ctrl->oncs & NVME_CTRL_ONCS_DSM) nvme_config_discard(ns); blk_mq_unfreeze_queue(disk->queue); +} +static int nvme_revalidate_disk(struct gendisk *disk) +{ + struct nvme_ns *ns = disk->private_data; + struct nvme_id_ns *id = NULL; + int ret; + + if (test_bit(NVME_NS_DEAD, &ns->flags)) { + set_capacity(disk, 0); + return -ENODEV; + } + + ret = nvme_revalidate_ns(ns, &id); + if (ret) + return ret; + + __nvme_revalidate_disk(disk, id); kfree(id); + return 0; } @@ -1422,7 +1433,7 @@ static DEVICE_ATTR(rescan_controller, S_IWUSR, NULL, nvme_sysfs_rescan); static ssize_t wwid_show(struct device *dev, struct device_attribute *attr, char *buf) { - struct nvme_ns *ns = dev_to_disk(dev)->private_data; + struct nvme_ns *ns = nvme_get_ns_from_dev(dev); struct nvme_ctrl *ctrl = ns->ctrl; int serial_len = sizeof(ctrl->serial); int model_len = sizeof(ctrl->model); @@ -1446,7 +1457,7 @@ static DEVICE_ATTR(wwid, S_IRUGO, wwid_show, NULL); static ssize_t uuid_show(struct device *dev, struct device_attribute *attr, char *buf) { - struct nvme_ns *ns = dev_to_disk(dev)->private_data; + struct nvme_ns *ns = nvme_get_ns_from_dev(dev); return sprintf(buf, "%pU\n", ns->uuid); } static DEVICE_ATTR(uuid, S_IRUGO, uuid_show, NULL); @@ -1454,7 +1465,7 @@ static DEVICE_ATTR(uuid, S_IRUGO, uuid_show, NULL); static ssize_t eui_show(struct device *dev, struct device_attribute *attr, char *buf) { - struct nvme_ns *ns = dev_to_disk(dev)->private_data; + struct nvme_ns *ns = nvme_get_ns_from_dev(dev); return sprintf(buf, "%8phd\n", ns->eui); } static DEVICE_ATTR(eui, S_IRUGO, eui_show, NULL); @@ -1462,7 +1473,7 @@ static DEVICE_ATTR(eui, S_IRUGO, eui_show, NULL); static ssize_t nsid_show(struct device *dev, struct device_attribute *attr, char *buf) { - struct nvme_ns *ns = dev_to_disk(dev)->private_data; + struct nvme_ns *ns = nvme_get_ns_from_dev(dev); return sprintf(buf, "%d\n", ns->ns_id); } static DEVICE_ATTR(nsid, S_IRUGO, nsid_show, NULL); @@ -1479,7 +1490,7 @@ static umode_t nvme_ns_attrs_are_visible(struct kobject *kobj, struct attribute *a, int n) { struct device *dev = container_of(kobj, struct device, kobj); - struct nvme_ns *ns = dev_to_disk(dev)->private_data; + 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))) @@ -1639,6 +1650,8 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid) { struct nvme_ns *ns; struct gendisk *disk; + struct nvme_id_ns *id; + char disk_name[DISK_NAME_LEN]; int node = dev_to_node(ctrl->dev); ns = kzalloc_node(sizeof(*ns), GFP_KERNEL, node); @@ -1656,34 +1669,49 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid) ns->queue->queuedata = ns; ns->ctrl = ctrl; - disk = alloc_disk_node(0, node); - if (!disk) - goto out_free_queue; - kref_init(&ns->kref); ns->ns_id = nsid; - ns->disk = disk; ns->lba_shift = 9; /* set to a default value for 512 until disk is validated */ - blk_queue_logical_block_size(ns->queue, 1 << ns->lba_shift); nvme_set_queue_limits(ctrl, ns->queue); - disk->fops = &nvme_fops; - disk->private_data = ns; - disk->queue = ns->queue; - disk->flags = GENHD_FL_EXT_DEVT; - sprintf(disk->disk_name, "nvme%dn%d", ctrl->instance, ns->instance); + sprintf(disk_name, "nvme%dn%d", ctrl->instance, ns->instance); + + if (nvme_revalidate_ns(ns, &id)) + goto out_free_queue; + + if (nvme_nvm_ns_supported(ns, id)) { + if (nvme_nvm_register(ns, disk_name, node, + &nvme_ns_attr_group)) { + dev_warn(ctrl->dev, "%s: LightNVM init failure\n", + __func__); + goto out_free_id; + } + } else { + disk = alloc_disk_node(0, node); + if (!disk) + goto out_free_id; + + disk->fops = &nvme_fops; + disk->private_data = ns; + disk->queue = ns->queue; + disk->flags = GENHD_FL_EXT_DEVT; + memcpy(disk->disk_name, disk_name, DISK_NAME_LEN); + ns->disk = disk; - if (nvme_revalidate_disk(ns->disk)) - goto out_free_disk; + __nvme_revalidate_disk(disk, id); + } mutex_lock(&ctrl->namespaces_mutex); list_add_tail(&ns->list, &ctrl->namespaces); mutex_unlock(&ctrl->namespaces_mutex); kref_get(&ctrl->kref); - if (ns->type == NVME_NS_LIGHTNVM) + + kfree(id); + + if (ns->ndev) return; device_add_disk(ctrl->device, ns->disk); @@ -1692,8 +1720,8 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid) pr_warn("%s: failed to create sysfs group for identification\n", ns->disk->disk_name); return; - out_free_disk: - kfree(disk); + out_free_id: + kfree(id); out_free_queue: blk_cleanup_queue(ns->queue); out_release_instance: @@ -1707,7 +1735,7 @@ static void nvme_ns_remove(struct nvme_ns *ns) if (test_and_set_bit(NVME_NS_REMOVING, &ns->flags)) return; - if (ns->disk->flags & GENHD_FL_UP) { + if (ns->disk && ns->disk->flags & GENHD_FL_UP) { if (blk_get_integrity(ns->disk)) blk_integrity_unregister(ns->disk); sysfs_remove_group(&disk_to_dev(ns->disk)->kobj, @@ -1730,7 +1758,7 @@ static void nvme_validate_ns(struct nvme_ctrl *ctrl, unsigned nsid) ns = nvme_find_get_ns(ctrl, nsid); if (ns) { - if (revalidate_disk(ns->disk)) + if (ns->disk && revalidate_disk(ns->disk)) nvme_ns_remove(ns); nvme_put_ns(ns); } else @@ -2035,7 +2063,7 @@ void nvme_kill_queues(struct nvme_ctrl *ctrl) * Revalidating a dead namespace sets capacity to 0. This will * end buffered writers dirtying pages that can't be synced. */ - if (!test_and_set_bit(NVME_NS_DEAD, &ns->flags)) + if (ns->disk && !test_and_set_bit(NVME_NS_DEAD, &ns->flags)) revalidate_disk(ns->disk); blk_set_queue_dying(ns->queue); diff --git a/drivers/nvme/host/fabrics.c b/drivers/nvme/host/fabrics.c index dc996761042f..5a3f008d3480 100644 --- a/drivers/nvme/host/fabrics.c +++ b/drivers/nvme/host/fabrics.c @@ -47,8 +47,10 @@ static struct nvmf_host *nvmf_host_add(const char *hostnqn) mutex_lock(&nvmf_hosts_mutex); host = __nvmf_host_find(hostnqn); - if (host) + if (host) { + kref_get(&host->ref); goto out_unlock; + } host = kmalloc(sizeof(*host), GFP_KERNEL); if (!host) @@ -56,7 +58,7 @@ static struct nvmf_host *nvmf_host_add(const char *hostnqn) kref_init(&host->ref); memcpy(host->nqn, hostnqn, NVMF_NQN_SIZE); - uuid_le_gen(&host->id); + uuid_be_gen(&host->id); list_add_tail(&host->list, &nvmf_hosts); out_unlock: @@ -73,9 +75,9 @@ static struct nvmf_host *nvmf_host_default(void) return NULL; kref_init(&host->ref); - uuid_le_gen(&host->id); + uuid_be_gen(&host->id); snprintf(host->nqn, NVMF_NQN_SIZE, - "nqn.2014-08.org.nvmexpress:NVMf:uuid:%pUl", &host->id); + "nqn.2014-08.org.nvmexpress:NVMf:uuid:%pUb", &host->id); mutex_lock(&nvmf_hosts_mutex); list_add_tail(&host->list, &nvmf_hosts); @@ -109,8 +111,19 @@ static void nvmf_host_put(struct nvmf_host *host) */ int nvmf_get_address(struct nvme_ctrl *ctrl, char *buf, int size) { - return snprintf(buf, size, "traddr=%s,trsvcid=%s\n", - ctrl->opts->traddr, ctrl->opts->trsvcid); + int len = 0; + + if (ctrl->opts->mask & NVMF_OPT_TRADDR) + len += snprintf(buf, size, "traddr=%s", ctrl->opts->traddr); + if (ctrl->opts->mask & NVMF_OPT_TRSVCID) + len += snprintf(buf + len, size - len, "%strsvcid=%s", + (len) ? "," : "", ctrl->opts->trsvcid); + if (ctrl->opts->mask & NVMF_OPT_HOST_TRADDR) + len += snprintf(buf + len, size - len, "%shost_traddr=%s", + (len) ? "," : "", ctrl->opts->host_traddr); + len += snprintf(buf + len, size - len, "\n"); + + return len; } EXPORT_SYMBOL_GPL(nvmf_get_address); @@ -363,7 +376,14 @@ int nvmf_connect_admin_queue(struct nvme_ctrl *ctrl) cmd.connect.opcode = nvme_fabrics_command; cmd.connect.fctype = nvme_fabrics_type_connect; cmd.connect.qid = 0; - cmd.connect.sqsize = cpu_to_le16(ctrl->sqsize); + + /* + * fabrics spec sets a minimum of depth 32 for admin queue, + * so set the queue with this depth always until + * justification otherwise. + */ + cmd.connect.sqsize = cpu_to_le16(NVMF_AQ_DEPTH - 1); + /* * Set keep-alive timeout in seconds granularity (ms * 1000) * and add a grace period for controller kato enforcement @@ -375,7 +395,7 @@ int nvmf_connect_admin_queue(struct nvme_ctrl *ctrl) if (!data) return -ENOMEM; - memcpy(&data->hostid, &ctrl->opts->host->id, sizeof(uuid_le)); + memcpy(&data->hostid, &ctrl->opts->host->id, sizeof(uuid_be)); data->cntlid = cpu_to_le16(0xffff); strncpy(data->subsysnqn, ctrl->opts->subsysnqn, NVMF_NQN_SIZE); strncpy(data->hostnqn, ctrl->opts->host->nqn, NVMF_NQN_SIZE); @@ -434,7 +454,7 @@ int nvmf_connect_io_queue(struct nvme_ctrl *ctrl, u16 qid) if (!data) return -ENOMEM; - memcpy(&data->hostid, &ctrl->opts->host->id, sizeof(uuid_le)); + memcpy(&data->hostid, &ctrl->opts->host->id, sizeof(uuid_be)); data->cntlid = cpu_to_le16(ctrl->cntlid); strncpy(data->subsysnqn, ctrl->opts->subsysnqn, NVMF_NQN_SIZE); strncpy(data->hostnqn, ctrl->opts->host->nqn, NVMF_NQN_SIZE); @@ -510,6 +530,7 @@ static const match_table_t opt_tokens = { { NVMF_OPT_RECONNECT_DELAY, "reconnect_delay=%d" }, { NVMF_OPT_KATO, "keep_alive_tmo=%d" }, { NVMF_OPT_HOSTNQN, "hostnqn=%s" }, + { NVMF_OPT_HOST_TRADDR, "host_traddr=%s" }, { NVMF_OPT_ERR, NULL } }; @@ -666,6 +687,14 @@ static int nvmf_parse_options(struct nvmf_ctrl_options *opts, } opts->reconnect_delay = token; break; + case NVMF_OPT_HOST_TRADDR: + p = match_strdup(args); + if (!p) { + ret = -ENOMEM; + goto out; + } + opts->host_traddr = p; + break; default: pr_warn("unknown parameter or missing value '%s' in ctrl creation request\n", p); @@ -732,6 +761,7 @@ void nvmf_free_options(struct nvmf_ctrl_options *opts) kfree(opts->traddr); kfree(opts->trsvcid); kfree(opts->subsysnqn); + kfree(opts->host_traddr); kfree(opts); } EXPORT_SYMBOL_GPL(nvmf_free_options); diff --git a/drivers/nvme/host/fabrics.h b/drivers/nvme/host/fabrics.h index 89df52c8be97..924145c979f1 100644 --- a/drivers/nvme/host/fabrics.h +++ b/drivers/nvme/host/fabrics.h @@ -34,7 +34,7 @@ struct nvmf_host { struct kref ref; struct list_head list; char nqn[NVMF_NQN_SIZE]; - uuid_le id; + uuid_be id; }; /** @@ -52,6 +52,7 @@ enum { NVMF_OPT_KATO = 1 << 7, NVMF_OPT_HOSTNQN = 1 << 8, NVMF_OPT_RECONNECT_DELAY = 1 << 9, + NVMF_OPT_HOST_TRADDR = 1 << 10, }; /** @@ -64,9 +65,12 @@ enum { * being added. * @subsysnqn: Hold the fully qualified NQN subystem name (format defined * in the NVMe specification, "NVMe Qualified Names"). - * @traddr: network address that will be used by the host to communicate - * to the added NVMe controller. - * @trsvcid: network port used for host-controller communication. + * @traddr: The transport-specific TRADDR field for a port on the + * subsystem which is adding a controller. + * @trsvcid: The transport-specific TRSVCID field for a port on the + * subsystem which is adding a controller. + * @host_traddr: A transport-specific field identifying the NVME host port + * to use for the connection to the controller. * @queue_size: Number of IO queue elements. * @nr_io_queues: Number of controller IO queues that will be established. * @reconnect_delay: Time between two consecutive reconnect attempts. @@ -80,6 +84,7 @@ struct nvmf_ctrl_options { char *subsysnqn; char *traddr; char *trsvcid; + char *host_traddr; size_t queue_size; unsigned int nr_io_queues; unsigned int reconnect_delay; diff --git a/drivers/nvme/host/lightnvm.c b/drivers/nvme/host/lightnvm.c index 63f483daf930..f5e3011e31fc 100644 --- a/drivers/nvme/host/lightnvm.c +++ b/drivers/nvme/host/lightnvm.c @@ -475,7 +475,7 @@ static inline void nvme_nvm_rqtocmd(struct request *rq, struct nvm_rq *rqd, if (rqd->opcode == NVM_OP_HBWRITE || rqd->opcode == NVM_OP_HBREAD) c->hb_rw.slba = cpu_to_le64(nvme_block_nr(ns, - rqd->bio->bi_iter.bi_sector)); + rqd->bio->bi_iter.bi_sector)); } static void nvme_nvm_end_io(struct request *rq, int error) @@ -592,14 +592,37 @@ static struct nvm_dev_ops nvme_nvm_dev_ops = { .max_phys_sect = 64, }; -int nvme_nvm_register(struct request_queue *q, char *disk_name) +int nvme_nvm_register(struct nvme_ns *ns, char *disk_name, int node, + const struct attribute_group *attrs) { - return nvm_register(q, disk_name, &nvme_nvm_dev_ops); + struct request_queue *q = ns->queue; + struct nvm_dev *dev; + int ret; + + dev = nvm_alloc_dev(node); + if (!dev) + return -ENOMEM; + + dev->q = q; + memcpy(dev->name, disk_name, DISK_NAME_LEN); + dev->ops = &nvme_nvm_dev_ops; + dev->parent_dev = ns->ctrl->device; + dev->private_data = ns; + ns->ndev = dev; + + ret = nvm_register(dev); + + ns->lba_shift = ilog2(dev->sec_size) - 9; + + if (sysfs_create_group(&dev->dev.kobj, attrs)) + pr_warn("%s: failed to create sysfs group for identification\n", + disk_name); + return ret; } -void nvme_nvm_unregister(struct request_queue *q, char *disk_name) +void nvme_nvm_unregister(struct nvme_ns *ns) { - nvm_unregister(disk_name); + nvm_unregister(ns->ndev); } /* move to shared place when used in multiple places. */ diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h index ab18b78102bf..b0a9ec681685 100644 --- a/drivers/nvme/host/nvme.h +++ b/drivers/nvme/host/nvme.h @@ -18,6 +18,7 @@ #include <linux/pci.h> #include <linux/kref.h> #include <linux/blk-mq.h> +#include <linux/lightnvm.h> enum { /* @@ -154,6 +155,7 @@ struct nvme_ns { struct nvme_ctrl *ctrl; struct request_queue *queue; struct gendisk *disk; + struct nvm_dev *ndev; struct kref kref; int instance; @@ -165,7 +167,6 @@ struct nvme_ns { u16 ms; bool ext; u8 pi_type; - int type; unsigned long flags; #define NVME_NS_REMOVING 0 @@ -292,9 +293,9 @@ int nvme_identify_ns(struct nvme_ctrl *dev, unsigned nsid, struct nvme_id_ns **id); int nvme_get_log_page(struct nvme_ctrl *dev, struct nvme_smart_log **log); int nvme_get_features(struct nvme_ctrl *dev, unsigned fid, unsigned nsid, - dma_addr_t dma_addr, u32 *result); + void *buffer, size_t buflen, u32 *result); int nvme_set_features(struct nvme_ctrl *dev, unsigned fid, unsigned dword11, - dma_addr_t dma_addr, u32 *result); + void *buffer, size_t buflen, u32 *result); int nvme_set_queue_count(struct nvme_ctrl *ctrl, int *count); void nvme_start_keep_alive(struct nvme_ctrl *ctrl); void nvme_stop_keep_alive(struct nvme_ctrl *ctrl); @@ -307,20 +308,35 @@ int nvme_sg_get_version_num(int __user *ip); #ifdef CONFIG_NVM int nvme_nvm_ns_supported(struct nvme_ns *ns, struct nvme_id_ns *id); -int nvme_nvm_register(struct request_queue *q, char *disk_name); -void nvme_nvm_unregister(struct request_queue *q, char *disk_name); +int nvme_nvm_register(struct nvme_ns *ns, char *disk_name, int node, + const struct attribute_group *attrs); +void nvme_nvm_unregister(struct nvme_ns *ns); + +static inline struct nvme_ns *nvme_get_ns_from_dev(struct device *dev) +{ + if (dev->type->devnode) + return dev_to_disk(dev)->private_data; + + return (container_of(dev, struct nvm_dev, dev))->private_data; +} #else -static inline int nvme_nvm_register(struct request_queue *q, char *disk_name) +static inline int nvme_nvm_register(struct nvme_ns *ns, char *disk_name, + int node, + const struct attribute_group *attrs) { return 0; } -static inline void nvme_nvm_unregister(struct request_queue *q, char *disk_name) {}; +static inline void nvme_nvm_unregister(struct nvme_ns *ns) {}; static inline int nvme_nvm_ns_supported(struct nvme_ns *ns, struct nvme_id_ns *id) { return 0; } +static inline struct nvme_ns *nvme_get_ns_from_dev(struct device *dev) +{ + return dev_to_disk(dev)->private_data; +} #endif /* CONFIG_NVM */ int __init nvme_core_init(void); diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 8dcf5a960951..60f7eab11865 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -1693,7 +1693,12 @@ static void nvme_dev_disable(struct nvme_dev *dev, bool shutdown) nvme_suspend_queue(dev->queues[i]); if (csts & NVME_CSTS_CFS || !(csts & NVME_CSTS_RDY)) { - nvme_suspend_queue(dev->queues[0]); + /* A device might become IO incapable very soon during + * probe, before the admin queue is configured. Thus, + * queue_count can be 0 here. + */ + if (dev->queue_count) + nvme_suspend_queue(dev->queues[0]); } else { nvme_disable_io_queues(dev); nvme_disable_admin_queue(dev, shutdown); @@ -2112,6 +2117,8 @@ 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(0x1c5f, 0x0540), /* Memblaze Pblaze4 adapter */ + .driver_data = NVME_QUIRK_DELAY_BEFORE_CHK_RDY, }, { PCI_DEVICE_CLASS(PCI_CLASS_STORAGE_EXPRESS, 0xffffff) }, { PCI_DEVICE(PCI_VENDOR_ID_APPLE, 0x2001) }, { 0, } diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c index 1a1854796797..28632292e85e 100644 --- a/drivers/nvme/host/rdma.c +++ b/drivers/nvme/host/rdma.c @@ -43,10 +43,6 @@ #define NVME_RDMA_MAX_INLINE_SEGMENTS 1 -#define NVME_RDMA_MAX_PAGES_PER_MR 512 - -#define NVME_RDMA_DEF_RECONNECT_DELAY 20 - /* * We handle AEN commands ourselves and don't even let the * block layer know about them. @@ -76,7 +72,6 @@ struct nvme_rdma_request { u32 num_sge; int nents; bool inline_data; - bool need_inval; struct ib_reg_wr reg_wr; struct ib_cqe reg_cqe; struct nvme_rdma_queue *queue; @@ -86,6 +81,8 @@ struct nvme_rdma_request { enum nvme_rdma_queue_flags { NVME_RDMA_Q_CONNECTED = (1 << 0), + NVME_RDMA_IB_QUEUE_ALLOCATED = (1 << 1), + NVME_RDMA_Q_DELETING = (1 << 2), }; struct nvme_rdma_queue { @@ -285,7 +282,7 @@ static int nvme_rdma_reinit_request(void *data, struct request *rq) struct nvme_rdma_request *req = blk_mq_rq_to_pdu(rq); int ret = 0; - if (!req->need_inval) + if (!req->mr->need_inval) goto out; ib_dereg_mr(req->mr); @@ -295,9 +292,10 @@ static int nvme_rdma_reinit_request(void *data, struct request *rq) if (IS_ERR(req->mr)) { ret = PTR_ERR(req->mr); req->mr = NULL; + goto out; } - req->need_inval = false; + req->mr->need_inval = false; out: return ret; @@ -470,9 +468,14 @@ 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; + + if (!test_and_clear_bit(NVME_RDMA_IB_QUEUE_ALLOCATED, &queue->flags)) + return; + dev = queue->device; + ibdev = dev->dev; rdma_destroy_qp(queue->cm_id); ib_free_cq(queue->ib_cq); @@ -523,6 +526,7 @@ static int nvme_rdma_create_queue_ib(struct nvme_rdma_queue *queue, ret = -ENOMEM; goto out_destroy_qp; } + set_bit(NVME_RDMA_IB_QUEUE_ALLOCATED, &queue->flags); return 0; @@ -575,11 +579,13 @@ static int nvme_rdma_init_queue(struct nvme_rdma_ctrl *ctrl, goto out_destroy_cm_id; } + clear_bit(NVME_RDMA_Q_DELETING, &queue->flags); set_bit(NVME_RDMA_Q_CONNECTED, &queue->flags); return 0; out_destroy_cm_id: + nvme_rdma_destroy_queue_ib(queue); rdma_destroy_id(queue->cm_id); return ret; } @@ -598,7 +604,7 @@ static void nvme_rdma_free_queue(struct nvme_rdma_queue *queue) static void nvme_rdma_stop_and_free_queue(struct nvme_rdma_queue *queue) { - if (!test_and_clear_bit(NVME_RDMA_Q_CONNECTED, &queue->flags)) + if (test_and_set_bit(NVME_RDMA_Q_DELETING, &queue->flags)) return; nvme_rdma_stop_queue(queue); nvme_rdma_free_queue(queue); @@ -630,7 +636,8 @@ static int nvme_rdma_init_io_queues(struct nvme_rdma_ctrl *ctrl) int i, ret; for (i = 1; i < ctrl->queue_count; i++) { - ret = nvme_rdma_init_queue(ctrl, i, ctrl->ctrl.sqsize); + ret = nvme_rdma_init_queue(ctrl, i, + ctrl->ctrl.opts->queue_size); if (ret) { dev_info(ctrl->ctrl.device, "failed to initialize i/o queue: %d\n", ret); @@ -641,7 +648,7 @@ static int nvme_rdma_init_io_queues(struct nvme_rdma_ctrl *ctrl) return 0; out_free_queues: - for (; i >= 1; i--) + for (i--; i >= 1; i--) nvme_rdma_stop_and_free_queue(&ctrl->queues[i]); return ret; @@ -750,8 +757,13 @@ static void nvme_rdma_error_recovery_work(struct work_struct *work) { struct nvme_rdma_ctrl *ctrl = container_of(work, struct nvme_rdma_ctrl, err_work); + int i; nvme_stop_keep_alive(&ctrl->ctrl); + + for (i = 0; i < ctrl->queue_count; i++) + clear_bit(NVME_RDMA_Q_CONNECTED, &ctrl->queues[i].flags); + if (ctrl->queue_count > 1) nvme_stop_queues(&ctrl->ctrl); blk_mq_stop_hw_queues(ctrl->ctrl.admin_q); @@ -834,7 +846,7 @@ static void nvme_rdma_unmap_data(struct nvme_rdma_queue *queue, if (!blk_rq_bytes(rq)) return; - if (req->need_inval) { + if (req->mr->need_inval) { res = nvme_rdma_inv_rkey(queue, req); if (res < 0) { dev_err(ctrl->ctrl.device, @@ -920,7 +932,7 @@ static int nvme_rdma_map_sg_fr(struct nvme_rdma_queue *queue, IB_ACCESS_REMOTE_READ | IB_ACCESS_REMOTE_WRITE; - req->need_inval = true; + req->mr->need_inval = true; sg->addr = cpu_to_le64(req->mr->iova); put_unaligned_le24(req->mr->length, sg->length); @@ -943,7 +955,7 @@ static int nvme_rdma_map_data(struct nvme_rdma_queue *queue, req->num_sge = 1; req->inline_data = false; - req->need_inval = false; + req->mr->need_inval = false; c->common.flags |= NVME_CMD_SGL_METABUF; @@ -1130,7 +1142,7 @@ static int nvme_rdma_process_nvme_rsp(struct nvme_rdma_queue *queue, if ((wc->wc_flags & IB_WC_WITH_INVALIDATE) && wc->ex.invalidate_rkey == req->mr->rkey) - req->need_inval = false; + req->mr->need_inval = false; blk_mq_complete_request(rq, status); @@ -1263,8 +1275,22 @@ static int nvme_rdma_route_resolved(struct nvme_rdma_queue *queue) priv.recfmt = cpu_to_le16(NVME_RDMA_CM_FMT_1_0); priv.qid = cpu_to_le16(nvme_rdma_queue_idx(queue)); - priv.hrqsize = cpu_to_le16(queue->queue_size); - priv.hsqsize = cpu_to_le16(queue->queue_size); + /* + * set the admin queue depth to the minimum size + * specified by the Fabrics standard. + */ + if (priv.qid == 0) { + priv.hrqsize = cpu_to_le16(NVMF_AQ_DEPTH); + priv.hsqsize = cpu_to_le16(NVMF_AQ_DEPTH - 1); + } else { + /* + * current interpretation of the fabrics spec + * is at minimum you make hrqsize sqsize+1, or a + * 1's based representation of sqsize. + */ + priv.hrqsize = cpu_to_le16(queue->queue_size); + priv.hsqsize = cpu_to_le16(queue->ctrl->ctrl.sqsize); + } ret = rdma_connect(queue->cm_id, ¶m); if (ret) { @@ -1280,58 +1306,6 @@ out_destroy_queue_ib: return ret; } -/** - * nvme_rdma_device_unplug() - Handle RDMA device unplug - * @queue: Queue that owns the cm_id that caught the event - * - * DEVICE_REMOVAL event notifies us that the RDMA device is about - * to unplug so we should take care of destroying our RDMA resources. - * This event will be generated for each allocated cm_id. - * - * In our case, the RDMA resources are managed per controller and not - * only per queue. So the way we handle this is we trigger an implicit - * controller deletion upon the first DEVICE_REMOVAL event we see, and - * hold the event inflight until the controller deletion is completed. - * - * One exception that we need to handle is the destruction of the cm_id - * that caught the event. Since we hold the callout until the controller - * deletion is completed, we'll deadlock if the controller deletion will - * call rdma_destroy_id on this queue's cm_id. Thus, we claim ownership - * of destroying this queue before-hand, destroy the queue resources, - * then queue the controller deletion which won't destroy this queue and - * we destroy the cm_id implicitely by returning a non-zero rc to the callout. - */ -static int nvme_rdma_device_unplug(struct nvme_rdma_queue *queue) -{ - struct nvme_rdma_ctrl *ctrl = queue->ctrl; - int ret; - - /* Own the controller deletion */ - if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_DELETING)) - return 0; - - dev_warn(ctrl->ctrl.device, - "Got rdma device removal event, deleting ctrl\n"); - - /* Get rid of reconnect work if its running */ - cancel_delayed_work_sync(&ctrl->reconnect_work); - - /* Disable the queue so ctrl delete won't free it */ - if (test_and_clear_bit(NVME_RDMA_Q_CONNECTED, &queue->flags)) { - /* Free this queue ourselves */ - nvme_rdma_stop_queue(queue); - nvme_rdma_destroy_queue_ib(queue); - - /* Return non-zero so the cm_id will destroy implicitly */ - ret = 1; - } - - /* Queue controller deletion */ - queue_work(nvme_rdma_wq, &ctrl->delete_work); - flush_work(&ctrl->delete_work); - return ret; -} - static int nvme_rdma_cm_handler(struct rdma_cm_id *cm_id, struct rdma_cm_event *ev) { @@ -1373,8 +1347,8 @@ static int nvme_rdma_cm_handler(struct rdma_cm_id *cm_id, nvme_rdma_error_recovery(queue->ctrl); break; case RDMA_CM_EVENT_DEVICE_REMOVAL: - /* return 1 means impliciy CM ID destroy */ - return nvme_rdma_device_unplug(queue); + /* device removal is handled via the ib_client API */ + break; default: dev_err(queue->ctrl->ctrl.device, "Unexpected RDMA CM event (%d)\n", ev->event); @@ -1446,7 +1420,7 @@ static int nvme_rdma_queue_rq(struct blk_mq_hw_ctx *hctx, if (rq->cmd_type == REQ_TYPE_FS && req_op(rq) == REQ_OP_FLUSH) flush = true; ret = nvme_rdma_post_send(queue, sqe, req->sge, req->num_sge, - req->need_inval ? &req->reg_wr.wr : NULL, flush); + req->mr->need_inval ? &req->reg_wr.wr : NULL, flush); if (ret) { nvme_rdma_unmap_data(queue, rq); goto err; @@ -1675,15 +1649,19 @@ static int __nvme_rdma_del_ctrl(struct nvme_rdma_ctrl *ctrl) static int nvme_rdma_del_ctrl(struct nvme_ctrl *nctrl) { struct nvme_rdma_ctrl *ctrl = to_rdma_ctrl(nctrl); - int ret; + int ret = 0; + /* + * Keep a reference until all work is flushed since + * __nvme_rdma_del_ctrl can free the ctrl mem + */ + if (!kref_get_unless_zero(&ctrl->ctrl.kref)) + return -EBUSY; ret = __nvme_rdma_del_ctrl(ctrl); - if (ret) - return ret; - - flush_work(&ctrl->delete_work); - - return 0; + if (!ret) + flush_work(&ctrl->delete_work); + nvme_put_ctrl(&ctrl->ctrl); + return ret; } static void nvme_rdma_remove_ctrl_work(struct work_struct *work) @@ -1801,7 +1779,7 @@ static int nvme_rdma_create_io_queues(struct nvme_rdma_ctrl *ctrl) memset(&ctrl->tag_set, 0, sizeof(ctrl->tag_set)); ctrl->tag_set.ops = &nvme_rdma_mq_ops; - ctrl->tag_set.queue_depth = ctrl->ctrl.sqsize; + ctrl->tag_set.queue_depth = ctrl->ctrl.opts->queue_size; ctrl->tag_set.reserved_tags = 1; /* fabric connect */ ctrl->tag_set.numa_node = NUMA_NO_NODE; ctrl->tag_set.flags = BLK_MQ_F_SHOULD_MERGE; @@ -1899,7 +1877,7 @@ static struct nvme_ctrl *nvme_rdma_create_ctrl(struct device *dev, spin_lock_init(&ctrl->lock); ctrl->queue_count = opts->nr_io_queues + 1; /* +1 for admin queue */ - ctrl->ctrl.sqsize = opts->queue_size; + ctrl->ctrl.sqsize = opts->queue_size - 1; ctrl->ctrl.kato = opts->kato; ret = -ENOMEM; @@ -1980,27 +1958,57 @@ static struct nvmf_transport_ops nvme_rdma_transport = { .create_ctrl = nvme_rdma_create_ctrl, }; +static void nvme_rdma_add_one(struct ib_device *ib_device) +{ +} + +static void nvme_rdma_remove_one(struct ib_device *ib_device, void *client_data) +{ + struct nvme_rdma_ctrl *ctrl; + + /* Delete all controllers using this device */ + mutex_lock(&nvme_rdma_ctrl_mutex); + list_for_each_entry(ctrl, &nvme_rdma_ctrl_list, list) { + if (ctrl->device->dev != ib_device) + continue; + dev_info(ctrl->ctrl.device, + "Removing ctrl: NQN \"%s\", addr %pISp\n", + ctrl->ctrl.opts->subsysnqn, &ctrl->addr); + __nvme_rdma_del_ctrl(ctrl); + } + mutex_unlock(&nvme_rdma_ctrl_mutex); + + flush_workqueue(nvme_rdma_wq); +} + +static struct ib_client nvme_rdma_ib_client = { + .name = "nvme_rdma", + .add = nvme_rdma_add_one, + .remove = nvme_rdma_remove_one +}; + static int __init nvme_rdma_init_module(void) { + int ret; + nvme_rdma_wq = create_workqueue("nvme_rdma_wq"); if (!nvme_rdma_wq) return -ENOMEM; + ret = ib_register_client(&nvme_rdma_ib_client); + if (ret) { + destroy_workqueue(nvme_rdma_wq); + return ret; + } + nvmf_register_transport(&nvme_rdma_transport); return 0; } static void __exit nvme_rdma_cleanup_module(void) { - struct nvme_rdma_ctrl *ctrl; - nvmf_unregister_transport(&nvme_rdma_transport); - - mutex_lock(&nvme_rdma_ctrl_mutex); - list_for_each_entry(ctrl, &nvme_rdma_ctrl_list, list) - __nvme_rdma_del_ctrl(ctrl); - mutex_unlock(&nvme_rdma_ctrl_mutex); - + ib_unregister_client(&nvme_rdma_ib_client); destroy_workqueue(nvme_rdma_wq); } diff --git a/drivers/nvme/host/scsi.c b/drivers/nvme/host/scsi.c index e947e298a737..c2a0a1c7d05d 100644 --- a/drivers/nvme/host/scsi.c +++ b/drivers/nvme/host/scsi.c @@ -72,15 +72,6 @@ static int sg_version_num = 30534; /* 2 digits for each component */ #define ALL_LUNS_RETURNED 0x02 #define ALL_WELL_KNOWN_LUNS_RETURNED 0x01 #define RESTRICTED_LUNS_RETURNED 0x00 -#define NVME_POWER_STATE_START_VALID 0x00 -#define NVME_POWER_STATE_ACTIVE 0x01 -#define NVME_POWER_STATE_IDLE 0x02 -#define NVME_POWER_STATE_STANDBY 0x03 -#define NVME_POWER_STATE_LU_CONTROL 0x07 -#define POWER_STATE_0 0 -#define POWER_STATE_1 1 -#define POWER_STATE_2 2 -#define POWER_STATE_3 3 #define DOWNLOAD_SAVE_ACTIVATE 0x05 #define DOWNLOAD_SAVE_DEFER_ACTIVATE 0x0E #define ACTIVATE_DEFERRED_MICROCODE 0x0F @@ -915,7 +906,7 @@ static int nvme_trans_log_temperature(struct nvme_ns *ns, struct sg_io_hdr *hdr, kfree(smart_log); /* Get Features for Temp Threshold */ - res = nvme_get_features(ns->ctrl, NVME_FEAT_TEMP_THRESH, 0, 0, + res = nvme_get_features(ns->ctrl, NVME_FEAT_TEMP_THRESH, 0, NULL, 0, &feature_resp); if (res != NVME_SC_SUCCESS) temp_c_thresh = LOG_TEMP_UNKNOWN; @@ -1048,7 +1039,7 @@ static int nvme_trans_fill_caching_page(struct nvme_ns *ns, if (len < MODE_PAGE_CACHING_LEN) return -EINVAL; - nvme_sc = nvme_get_features(ns->ctrl, NVME_FEAT_VOLATILE_WC, 0, 0, + nvme_sc = nvme_get_features(ns->ctrl, NVME_FEAT_VOLATILE_WC, 0, NULL, 0, &feature_resp); res = nvme_trans_status_code(hdr, nvme_sc); if (res) @@ -1229,64 +1220,6 @@ static void nvme_trans_fill_read_cap(u8 *response, struct nvme_id_ns *id_ns, /* Start Stop Unit Helper Functions */ -static int nvme_trans_power_state(struct nvme_ns *ns, struct sg_io_hdr *hdr, - u8 pc, u8 pcmod, u8 start) -{ - int res; - int nvme_sc; - struct nvme_id_ctrl *id_ctrl; - int lowest_pow_st; /* max npss = lowest power consumption */ - unsigned ps_desired = 0; - - nvme_sc = nvme_identify_ctrl(ns->ctrl, &id_ctrl); - res = nvme_trans_status_code(hdr, nvme_sc); - if (res) - return res; - - lowest_pow_st = max(POWER_STATE_0, (int)(id_ctrl->npss - 1)); - kfree(id_ctrl); - - switch (pc) { - case NVME_POWER_STATE_START_VALID: - /* Action unspecified if POWER CONDITION MODIFIER != 0 */ - if (pcmod == 0 && start == 0x1) - ps_desired = POWER_STATE_0; - if (pcmod == 0 && start == 0x0) - ps_desired = lowest_pow_st; - break; - case NVME_POWER_STATE_ACTIVE: - /* Action unspecified if POWER CONDITION MODIFIER != 0 */ - if (pcmod == 0) - ps_desired = POWER_STATE_0; - break; - case NVME_POWER_STATE_IDLE: - /* Action unspecified if POWER CONDITION MODIFIER != [0,1,2] */ - if (pcmod == 0x0) - ps_desired = POWER_STATE_1; - else if (pcmod == 0x1) - ps_desired = POWER_STATE_2; - else if (pcmod == 0x2) - ps_desired = POWER_STATE_3; - break; - case NVME_POWER_STATE_STANDBY: - /* Action unspecified if POWER CONDITION MODIFIER != [0,1] */ - if (pcmod == 0x0) - ps_desired = max(POWER_STATE_0, (lowest_pow_st - 2)); - else if (pcmod == 0x1) - ps_desired = max(POWER_STATE_0, (lowest_pow_st - 1)); - break; - case NVME_POWER_STATE_LU_CONTROL: - default: - res = nvme_trans_completion(hdr, SAM_STAT_CHECK_CONDITION, - ILLEGAL_REQUEST, SCSI_ASC_INVALID_CDB, - SCSI_ASCQ_CAUSE_NOT_REPORTABLE); - break; - } - nvme_sc = nvme_set_features(ns->ctrl, NVME_FEAT_POWER_MGMT, ps_desired, 0, - NULL); - return nvme_trans_status_code(hdr, nvme_sc); -} - static int nvme_trans_send_activate_fw_cmd(struct nvme_ns *ns, struct sg_io_hdr *hdr, u8 buffer_id) { @@ -1395,7 +1328,7 @@ static int nvme_trans_modesel_get_mp(struct nvme_ns *ns, struct sg_io_hdr *hdr, case MODE_PAGE_CACHING: dword11 = ((mode_page[2] & CACHING_MODE_PAGE_WCE_MASK) ? 1 : 0); nvme_sc = nvme_set_features(ns->ctrl, NVME_FEAT_VOLATILE_WC, - dword11, 0, NULL); + dword11, NULL, 0, NULL); res = nvme_trans_status_code(hdr, nvme_sc); break; case MODE_PAGE_CONTROL: @@ -2235,11 +2168,10 @@ static int nvme_trans_synchronize_cache(struct nvme_ns *ns, static int nvme_trans_start_stop(struct nvme_ns *ns, struct sg_io_hdr *hdr, u8 *cmd) { - u8 immed, pcmod, pc, no_flush, start; + u8 immed, pcmod, no_flush, start; immed = cmd[1] & 0x01; pcmod = cmd[3] & 0x0f; - pc = (cmd[4] & 0xf0) >> 4; no_flush = cmd[4] & 0x04; start = cmd[4] & 0x01; @@ -2254,8 +2186,8 @@ static int nvme_trans_start_stop(struct nvme_ns *ns, struct sg_io_hdr *hdr, if (res) return res; } - /* Setup the expected power state transition */ - return nvme_trans_power_state(ns, hdr, pc, pcmod, start); + + return 0; } } diff --git a/drivers/nvme/target/Kconfig b/drivers/nvme/target/Kconfig index a5c31cbeb481..3a5b9d0576cb 100644 --- a/drivers/nvme/target/Kconfig +++ b/drivers/nvme/target/Kconfig @@ -15,8 +15,8 @@ config NVME_TARGET config NVME_TARGET_LOOP tristate "NVMe loopback device support" - depends on BLK_DEV_NVME depends on NVME_TARGET + select NVME_CORE select NVME_FABRICS select SG_POOL help diff --git a/drivers/nvme/target/admin-cmd.c b/drivers/nvme/target/admin-cmd.c index 47c564b5a289..7ab9c9381b98 100644 --- a/drivers/nvme/target/admin-cmd.c +++ b/drivers/nvme/target/admin-cmd.c @@ -14,6 +14,7 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/module.h> #include <generated/utsrelease.h> +#include <asm/unaligned.h> #include "nvmet.h" u32 nvmet_get_log_page_len(struct nvme_command *cmd) @@ -29,8 +30,84 @@ u32 nvmet_get_log_page_len(struct nvme_command *cmd) return len; } +static u16 nvmet_get_smart_log_nsid(struct nvmet_req *req, + struct nvme_smart_log *slog) +{ + u16 status; + struct nvmet_ns *ns; + u64 host_reads, host_writes, data_units_read, data_units_written; + + status = NVME_SC_SUCCESS; + ns = nvmet_find_namespace(req->sq->ctrl, req->cmd->get_log_page.nsid); + if (!ns) { + status = NVME_SC_INVALID_NS; + pr_err("nvmet : Counld not find namespace id : %d\n", + le32_to_cpu(req->cmd->get_log_page.nsid)); + goto out; + } + + host_reads = part_stat_read(ns->bdev->bd_part, ios[READ]); + data_units_read = part_stat_read(ns->bdev->bd_part, sectors[READ]); + host_writes = part_stat_read(ns->bdev->bd_part, ios[WRITE]); + data_units_written = part_stat_read(ns->bdev->bd_part, sectors[WRITE]); + + put_unaligned_le64(host_reads, &slog->host_reads[0]); + put_unaligned_le64(data_units_read, &slog->data_units_read[0]); + put_unaligned_le64(host_writes, &slog->host_writes[0]); + put_unaligned_le64(data_units_written, &slog->data_units_written[0]); + nvmet_put_namespace(ns); +out: + return status; +} + +static u16 nvmet_get_smart_log_all(struct nvmet_req *req, + struct nvme_smart_log *slog) +{ + u16 status; + u64 host_reads = 0, host_writes = 0; + u64 data_units_read = 0, data_units_written = 0; + struct nvmet_ns *ns; + struct nvmet_ctrl *ctrl; + + status = NVME_SC_SUCCESS; + ctrl = req->sq->ctrl; + + rcu_read_lock(); + list_for_each_entry_rcu(ns, &ctrl->subsys->namespaces, dev_link) { + host_reads += part_stat_read(ns->bdev->bd_part, ios[READ]); + data_units_read += + part_stat_read(ns->bdev->bd_part, sectors[READ]); + host_writes += part_stat_read(ns->bdev->bd_part, ios[WRITE]); + data_units_written += + part_stat_read(ns->bdev->bd_part, sectors[WRITE]); + + } + rcu_read_unlock(); + + put_unaligned_le64(host_reads, &slog->host_reads[0]); + put_unaligned_le64(data_units_read, &slog->data_units_read[0]); + put_unaligned_le64(host_writes, &slog->host_writes[0]); + put_unaligned_le64(data_units_written, &slog->data_units_written[0]); + + return status; +} + +static u16 nvmet_get_smart_log(struct nvmet_req *req, + struct nvme_smart_log *slog) +{ + u16 status; + + WARN_ON(req == NULL || slog == NULL); + if (req->cmd->get_log_page.nsid == 0xFFFFFFFF) + status = nvmet_get_smart_log_all(req, slog); + else + status = nvmet_get_smart_log_nsid(req, slog); + return status; +} + static void nvmet_execute_get_log_page(struct nvmet_req *req) { + struct nvme_smart_log *smart_log; size_t data_len = nvmet_get_log_page_len(req->cmd); void *buf; u16 status = 0; @@ -59,6 +136,16 @@ static void nvmet_execute_get_log_page(struct nvmet_req *req) * available (e.g. units or commands read/written) those aren't * persistent over power loss. */ + if (data_len != sizeof(*smart_log)) { + status = NVME_SC_INTERNAL; + goto err; + } + smart_log = buf; + status = nvmet_get_smart_log(req, smart_log); + if (status) { + memset(buf, '\0', data_len); + goto err; + } break; case 0x03: /* @@ -73,6 +160,7 @@ static void nvmet_execute_get_log_page(struct nvmet_req *req) status = nvmet_copy_to_sgl(req, 0, buf, data_len); +err: kfree(buf); out: nvmet_req_complete(req, status); diff --git a/drivers/nvme/target/io-cmd.c b/drivers/nvme/target/io-cmd.c index 2cd069b691ae..4a96c2049b7b 100644 --- a/drivers/nvme/target/io-cmd.c +++ b/drivers/nvme/target/io-cmd.c @@ -58,6 +58,7 @@ static void nvmet_execute_rw(struct nvmet_req *req) if (req->cmd->rw.opcode == nvme_cmd_write) { op = REQ_OP_WRITE; + op_flags = WRITE_ODIRECT; if (req->cmd->rw.control & cpu_to_le16(NVME_RW_FUA)) op_flags |= REQ_FUA; } else { @@ -205,7 +206,7 @@ int nvmet_parse_io_cmd(struct nvmet_req *req) return 0; case nvme_cmd_dsm: req->execute = nvmet_execute_dsm; - req->data_len = le32_to_cpu(cmd->dsm.nr) * + req->data_len = le32_to_cpu(cmd->dsm.nr + 1) * sizeof(struct nvme_dsm_range); return 0; default: diff --git a/drivers/nvme/target/loop.c b/drivers/nvme/target/loop.c index 7affd40a6b33..395e60dad835 100644 --- a/drivers/nvme/target/loop.c +++ b/drivers/nvme/target/loop.c @@ -556,7 +556,7 @@ static int nvme_loop_create_io_queues(struct nvme_loop_ctrl *ctrl) memset(&ctrl->tag_set, 0, sizeof(ctrl->tag_set)); ctrl->tag_set.ops = &nvme_loop_mq_ops; - ctrl->tag_set.queue_depth = ctrl->ctrl.sqsize; + ctrl->tag_set.queue_depth = ctrl->ctrl.opts->queue_size; ctrl->tag_set.reserved_tags = 1; /* fabric connect */ ctrl->tag_set.numa_node = NUMA_NO_NODE; ctrl->tag_set.flags = BLK_MQ_F_SHOULD_MERGE; @@ -620,7 +620,7 @@ static struct nvme_ctrl *nvme_loop_create_ctrl(struct device *dev, ret = -ENOMEM; - ctrl->ctrl.sqsize = opts->queue_size; + ctrl->ctrl.sqsize = opts->queue_size - 1; ctrl->ctrl.kato = opts->kato; ctrl->queues = kcalloc(opts->nr_io_queues + 1, sizeof(*ctrl->queues), diff --git a/drivers/nvme/target/rdma.c b/drivers/nvme/target/rdma.c index 187763a77355..f8d23999e0f2 100644 --- a/drivers/nvme/target/rdma.c +++ b/drivers/nvme/target/rdma.c @@ -978,10 +978,11 @@ static void nvmet_rdma_release_queue_work(struct work_struct *w) container_of(w, struct nvmet_rdma_queue, release_work); struct rdma_cm_id *cm_id = queue->cm_id; struct nvmet_rdma_device *dev = queue->dev; + enum nvmet_rdma_queue_state state = queue->state; nvmet_rdma_free_queue(queue); - if (queue->state != NVMET_RDMA_IN_DEVICE_REMOVAL) + if (state != NVMET_RDMA_IN_DEVICE_REMOVAL) rdma_destroy_id(cm_id); kref_put(&dev->ref, nvmet_rdma_free_dev); @@ -1003,10 +1004,10 @@ nvmet_rdma_parse_cm_connect_req(struct rdma_conn_param *conn, queue->host_qid = le16_to_cpu(req->qid); /* - * req->hsqsize corresponds to our recv queue size + * req->hsqsize corresponds to our recv queue size plus 1 * req->hrqsize corresponds to our send queue size */ - queue->recv_queue_size = le16_to_cpu(req->hsqsize); + queue->recv_queue_size = le16_to_cpu(req->hsqsize) + 1; queue->send_queue_size = le16_to_cpu(req->hrqsize); if (!queue->host_qid && queue->recv_queue_size > NVMF_AQ_DEPTH) |