diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index c596dd3c58b1..b0dd58db110e 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -76,6 +76,11 @@ static DEFINE_SPINLOCK(dev_list_lock); static struct class *nvme_class; +static __le32 nvme_get_log_dw10(u8 lid, size_t size) +{ + return cpu_to_le32((((size / 4) - 1) << 16) | lid); +} + int nvme_reset_ctrl(struct nvme_ctrl *ctrl) { if (!nvme_change_ctrl_state(ctrl, NVME_CTRL_RESETTING)) @@ -108,7 +113,16 @@ static blk_status_t nvme_error_status(struct request *req) case NVME_SC_WRITE_FAULT: case NVME_SC_READ_ERROR: case NVME_SC_UNWRITTEN_BLOCK: + case NVME_SC_ACCESS_DENIED: + case NVME_SC_READ_ONLY: return BLK_STS_MEDIUM; + case NVME_SC_GUARD_CHECK: + case NVME_SC_APPTAG_CHECK: + case NVME_SC_REFTAG_CHECK: + case NVME_SC_INVALID_PI: + return BLK_STS_PROTECTION; + case NVME_SC_RESERVATION_CONFLICT: + return BLK_STS_NEXUS; default: return BLK_STS_IOERR; } @@ -162,9 +176,10 @@ bool nvme_change_ctrl_state(struct nvme_ctrl *ctrl, enum nvme_ctrl_state new_state) { enum nvme_ctrl_state old_state; + unsigned long flags; bool changed = false; - spin_lock_irq(&ctrl->lock); + spin_lock_irqsave(&ctrl->lock, flags); old_state = ctrl->state; switch (new_state) { @@ -225,7 +240,7 @@ bool nvme_change_ctrl_state(struct nvme_ctrl *ctrl, if (changed) ctrl->state = new_state; - spin_unlock_irq(&ctrl->lock); + spin_unlock_irqrestore(&ctrl->lock, flags); return changed; } @@ -307,7 +322,7 @@ static int nvme_toggle_streams(struct nvme_ctrl *ctrl, bool enable) memset(&c, 0, sizeof(c)); c.directive.opcode = nvme_admin_directive_send; - c.directive.nsid = cpu_to_le32(0xffffffff); + c.directive.nsid = cpu_to_le32(NVME_NSID_ALL); c.directive.doper = NVME_DIR_SND_ID_OP_ENABLE; c.directive.dtype = NVME_DIR_IDENTIFY; c.directive.tdtype = NVME_DIR_STREAMS; @@ -357,7 +372,7 @@ static int nvme_configure_directives(struct nvme_ctrl *ctrl) if (ret) return ret; - ret = nvme_get_stream_params(ctrl, &s, 0xffffffff); + ret = nvme_get_stream_params(ctrl, &s, NVME_NSID_ALL); if (ret) return ret; @@ -768,7 +783,8 @@ static int nvme_identify_ctrl(struct nvme_ctrl *dev, struct nvme_id_ctrl **id) return error; } -static int nvme_identify_ns_descs(struct nvme_ns *ns, unsigned nsid) +static int nvme_identify_ns_descs(struct nvme_ctrl *ctrl, unsigned nsid, + u8 *eui64, u8 *nguid, uuid_t *uuid) { struct nvme_command c = { }; int status; @@ -784,7 +800,7 @@ static int nvme_identify_ns_descs(struct nvme_ns *ns, unsigned nsid) if (!data) return -ENOMEM; - status = nvme_submit_sync_cmd(ns->ctrl->admin_q, &c, data, + status = nvme_submit_sync_cmd(ctrl->admin_q, &c, data, NVME_IDENTIFY_DATA_SIZE); if (status) goto free_data; @@ -798,33 +814,33 @@ static int nvme_identify_ns_descs(struct nvme_ns *ns, unsigned nsid) switch (cur->nidt) { case NVME_NIDT_EUI64: if (cur->nidl != NVME_NIDT_EUI64_LEN) { - dev_warn(ns->ctrl->device, + dev_warn(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); + memcpy(eui64, data + pos + sizeof(*cur), len); break; case NVME_NIDT_NGUID: if (cur->nidl != NVME_NIDT_NGUID_LEN) { - dev_warn(ns->ctrl->device, + dev_warn(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); + memcpy(nguid, data + pos + sizeof(*cur), len); break; case NVME_NIDT_UUID: if (cur->nidl != NVME_NIDT_UUID_LEN) { - dev_warn(ns->ctrl->device, + dev_warn(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)); + uuid_copy(uuid, data + pos + sizeof(*cur)); break; default: /* Skip unnkown types */ @@ -849,9 +865,10 @@ static int nvme_identify_ns_list(struct nvme_ctrl *dev, unsigned nsid, __le32 *n return nvme_submit_sync_cmd(dev->admin_q, &c, ns_list, 0x1000); } -static int nvme_identify_ns(struct nvme_ctrl *dev, unsigned nsid, - struct nvme_id_ns **id) +static struct nvme_id_ns *nvme_identify_ns(struct nvme_ctrl *ctrl, + unsigned nsid) { + struct nvme_id_ns *id; struct nvme_command c = { }; int error; @@ -860,15 +877,18 @@ static int nvme_identify_ns(struct nvme_ctrl *dev, unsigned nsid, c.identify.nsid = cpu_to_le32(nsid); c.identify.cns = NVME_ID_CNS_NS; - *id = kmalloc(sizeof(struct nvme_id_ns), GFP_KERNEL); - if (!*id) - return -ENOMEM; + id = kmalloc(sizeof(*id), GFP_KERNEL); + if (!id) + return NULL; - error = nvme_submit_sync_cmd(dev->admin_q, &c, *id, - sizeof(struct nvme_id_ns)); - if (error) - kfree(*id); - return error; + error = nvme_submit_sync_cmd(ctrl->admin_q, &c, id, sizeof(*id)); + if (error) { + dev_warn(ctrl->device, "Identify namespace failed\n"); + kfree(id); + return NULL; + } + + return id; } static int nvme_set_features(struct nvme_ctrl *dev, unsigned fid, unsigned dword11, @@ -1159,32 +1179,21 @@ static void nvme_config_discard(struct nvme_ns *ns) blk_queue_max_write_zeroes_sectors(ns->queue, UINT_MAX); } -static int nvme_revalidate_ns(struct nvme_ns *ns, struct nvme_id_ns **id) +static void nvme_report_ns_ids(struct nvme_ctrl *ctrl, unsigned int nsid, + struct nvme_id_ns *id, u8 *eui64, u8 *nguid, uuid_t *uuid) { - if (nvme_identify_ns(ns->ctrl, ns->ns_id, id)) { - dev_warn(ns->ctrl->dev, "%s: Identify failure\n", __func__); - return -ENODEV; - } - - if ((*id)->ncap == 0) { - kfree(*id); - return -ENODEV; - } - - 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->nguid, (*id)->nguid, sizeof(ns->nguid)); - if (ns->ctrl->vs >= NVME_VS(1, 3, 0)) { + if (ctrl->vs >= NVME_VS(1, 1, 0)) + memcpy(eui64, id->eui64, sizeof(id->eui64)); + if (ctrl->vs >= NVME_VS(1, 2, 0)) + memcpy(nguid, id->nguid, sizeof(id->nguid)); + if (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, + if (nvme_identify_ns_descs(ctrl, nsid, eui64, nguid, uuid)) + dev_warn(ctrl->device, "%s: Identify Descriptors failed\n", __func__); } - - return 0; } static void __nvme_revalidate_disk(struct gendisk *disk, struct nvme_id_ns *id) @@ -1225,22 +1234,38 @@ static void __nvme_revalidate_disk(struct gendisk *disk, struct nvme_id_ns *id) static int nvme_revalidate_disk(struct gendisk *disk) { struct nvme_ns *ns = disk->private_data; - struct nvme_id_ns *id = NULL; - int ret; + struct nvme_ctrl *ctrl = ns->ctrl; + struct nvme_id_ns *id; + u8 eui64[8] = { 0 }, nguid[16] = { 0 }; + uuid_t uuid = uuid_null; + int ret = 0; if (test_bit(NVME_NS_DEAD, &ns->flags)) { set_capacity(disk, 0); return -ENODEV; } - ret = nvme_revalidate_ns(ns, &id); - if (ret) - return ret; + id = nvme_identify_ns(ctrl, ns->ns_id); + if (!id) + return -ENODEV; - __nvme_revalidate_disk(disk, id); + if (id->ncap == 0) { + ret = -ENODEV; + goto out; + } + + nvme_report_ns_ids(ctrl, ns->ns_id, id, eui64, nguid, &uuid); + if (!uuid_equal(&ns->uuid, &uuid) || + memcmp(&ns->nguid, &nguid, sizeof(ns->nguid)) || + memcmp(&ns->eui, &eui64, sizeof(ns->eui))) { + dev_err(ctrl->device, + "identifiers changed for nsid %d\n", ns->ns_id); + ret = -ENODEV; + } + +out: kfree(id); - - return 0; + return ret; } static char nvme_pr_type(enum pr_type type) @@ -1440,7 +1465,7 @@ int nvme_enable_ctrl(struct nvme_ctrl *ctrl, u64 cap) ctrl->ctrl_config = NVME_CC_CSS_NVM; ctrl->ctrl_config |= (page_shift - 12) << NVME_CC_MPS_SHIFT; - ctrl->ctrl_config |= NVME_CC_ARB_RR | NVME_CC_SHN_NONE; + ctrl->ctrl_config |= NVME_CC_AMS_RR | NVME_CC_SHN_NONE; ctrl->ctrl_config |= NVME_CC_IOSQES | NVME_CC_IOCQES; ctrl->ctrl_config |= NVME_CC_ENABLE; @@ -1453,7 +1478,7 @@ EXPORT_SYMBOL_GPL(nvme_enable_ctrl); int nvme_shutdown_ctrl(struct nvme_ctrl *ctrl) { - unsigned long timeout = jiffies + (shutdown_timeout * HZ); + unsigned long timeout = jiffies + (ctrl->shutdown_timeout * HZ); u32 csts; int ret; @@ -1502,6 +1527,23 @@ static void nvme_set_queue_limits(struct nvme_ctrl *ctrl, blk_queue_write_cache(q, vwc, vwc); } +static int nvme_configure_timestamp(struct nvme_ctrl *ctrl) +{ + __le64 ts; + int ret; + + if (!(ctrl->oncs & NVME_CTRL_ONCS_TIMESTAMP)) + return 0; + + ts = cpu_to_le64(ktime_to_ms(ktime_get_real())); + ret = nvme_set_features(ctrl, NVME_FEAT_TIMESTAMP, 0, &ts, sizeof(ts), + NULL); + if (ret) + dev_warn_once(ctrl->device, + "could not set timestamp (%d)\n", ret); + return ret; +} + static int nvme_configure_apst(struct nvme_ctrl *ctrl) { /* @@ -1804,6 +1846,20 @@ int nvme_init_identify(struct nvme_ctrl *ctrl) ctrl->sgls = le32_to_cpu(id->sgls); ctrl->kas = le16_to_cpu(id->kas); + if (id->rtd3e) { + /* us -> s */ + u32 transition_time = le32_to_cpu(id->rtd3e) / 1000000; + + ctrl->shutdown_timeout = clamp_t(unsigned int, transition_time, + shutdown_timeout, 60); + + if (ctrl->shutdown_timeout != shutdown_timeout) + dev_warn(ctrl->device, + "Shutdown timeout set to %u seconds\n", + ctrl->shutdown_timeout); + } else + ctrl->shutdown_timeout = shutdown_timeout; + ctrl->npss = id->npss; ctrl->apsta = id->apsta; prev_apst_enabled = ctrl->apst_enabled; @@ -1856,6 +1912,10 @@ int nvme_init_identify(struct nvme_ctrl *ctrl) ret = nvme_configure_apst(ctrl); if (ret < 0) return ret; + + ret = nvme_configure_timestamp(ctrl); + if (ret < 0) + return ret; ret = nvme_configure_directives(ctrl); if (ret < 0) @@ -2311,9 +2371,15 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid) sprintf(disk_name, "nvme%dn%d", ctrl->instance, ns->instance); - if (nvme_revalidate_ns(ns, &id)) + id = nvme_identify_ns(ctrl, nsid); + if (!id) goto out_free_queue; + if (id->ncap == 0) + goto out_free_id; + + nvme_report_ns_ids(ctrl, ns->ns_id, id, ns->eui, ns->nguid, &ns->uuid); + if (nvme_nvm_ns_supported(ns, id) && nvme_nvm_register(ns, disk_name, node)) { dev_warn(ctrl->device, "%s: LightNVM init failure\n", __func__); @@ -2534,6 +2600,71 @@ static void nvme_async_event_work(struct work_struct *work) spin_unlock_irq(&ctrl->lock); } +static bool nvme_ctrl_pp_status(struct nvme_ctrl *ctrl) +{ + + u32 csts; + + if (ctrl->ops->reg_read32(ctrl, NVME_REG_CSTS, &csts)) + return false; + + if (csts == ~0) + return false; + + return ((ctrl->ctrl_config & NVME_CC_ENABLE) && (csts & NVME_CSTS_PP)); +} + +static void nvme_get_fw_slot_info(struct nvme_ctrl *ctrl) +{ + struct nvme_command c = { }; + struct nvme_fw_slot_info_log *log; + + log = kmalloc(sizeof(*log), GFP_KERNEL); + if (!log) + return; + + c.common.opcode = nvme_admin_get_log_page; + c.common.nsid = cpu_to_le32(NVME_NSID_ALL); + c.common.cdw10[0] = nvme_get_log_dw10(NVME_LOG_FW_SLOT, sizeof(*log)); + + if (!nvme_submit_sync_cmd(ctrl->admin_q, &c, log, sizeof(*log))) + dev_warn(ctrl->device, + "Get FW SLOT INFO log error\n"); + kfree(log); +} + +static void nvme_fw_act_work(struct work_struct *work) +{ + struct nvme_ctrl *ctrl = container_of(work, + struct nvme_ctrl, fw_act_work); + unsigned long fw_act_timeout; + + if (ctrl->mtfa) + fw_act_timeout = jiffies + + msecs_to_jiffies(ctrl->mtfa * 100); + else + fw_act_timeout = jiffies + + msecs_to_jiffies(admin_timeout * 1000); + + nvme_stop_queues(ctrl); + while (nvme_ctrl_pp_status(ctrl)) { + if (time_after(jiffies, fw_act_timeout)) { + dev_warn(ctrl->device, + "Fw activation timeout, reset controller\n"); + nvme_reset_ctrl(ctrl); + break; + } + msleep(100); + } + + if (ctrl->state != NVME_CTRL_LIVE) + return; + + nvme_start_queues(ctrl); + /* read FW slot informationi to clear the AER*/ + nvme_get_fw_slot_info(ctrl); +} + void nvme_complete_async_event(struct nvme_ctrl *ctrl, __le16 status, union nvme_result *res) { @@ -2560,6 +2691,9 @@ void nvme_complete_async_event(struct nvme_ctrl *ctrl, __le16 status, dev_info(ctrl->device, "rescanning\n"); nvme_queue_scan(ctrl); break; + case NVME_AER_NOTICE_FW_ACT_STARTING: + schedule_work(&ctrl->fw_act_work); + break; default: dev_warn(ctrl->device, "async event result %08x\n", result); } @@ -2607,6 +2741,7 @@ void nvme_stop_ctrl(struct nvme_ctrl *ctrl) nvme_stop_keep_alive(ctrl); flush_work(&ctrl->async_event_work); flush_work(&ctrl->scan_work); + cancel_work_sync(&ctrl->fw_act_work); } EXPORT_SYMBOL_GPL(nvme_stop_ctrl); @@ -2670,6 +2805,7 @@ int nvme_init_ctrl(struct nvme_ctrl *ctrl, struct device *dev, ctrl->quirks = quirks; INIT_WORK(&ctrl->scan_work, nvme_scan_work); INIT_WORK(&ctrl->async_event_work, nvme_async_event_work); + INIT_WORK(&ctrl->fw_act_work, nvme_fw_act_work); ret = nvme_set_instance(ctrl); if (ret) diff --git a/drivers/nvme/host/fabrics.c b/drivers/nvme/host/fabrics.c index 5f5cd306f76d..fc3b6552f467 100644 --- a/drivers/nvme/host/fabrics.c +++ b/drivers/nvme/host/fabrics.c @@ -735,6 +735,7 @@ static int nvmf_parse_options(struct nvmf_ctrl_options *opts, goto out; } if (uuid_parse(p, &hostid)) { + pr_err("Invalid hostid %s\n", p); ret = -EINVAL; goto out; } diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c index 1438be649866..d2e882c0f496 100644 --- a/drivers/nvme/host/fc.c +++ b/drivers/nvme/host/fc.c @@ -220,6 +220,90 @@ static int __nvme_fc_del_ctrl(struct nvme_fc_ctrl *); static void __nvme_fc_delete_hw_queue(struct nvme_fc_ctrl *, struct nvme_fc_queue *, unsigned int); +static void +nvme_fc_free_lport(struct kref *ref) +{ + struct nvme_fc_lport *lport = + container_of(ref, struct nvme_fc_lport, ref); + unsigned long flags; + + WARN_ON(lport->localport.port_state != FC_OBJSTATE_DELETED); + WARN_ON(!list_empty(&lport->endp_list)); + + /* remove from transport list */ + spin_lock_irqsave(&nvme_fc_lock, flags); + list_del(&lport->port_list); + spin_unlock_irqrestore(&nvme_fc_lock, flags); + + /* let the LLDD know we've finished tearing it down */ + lport->ops->localport_delete(&lport->localport); + + ida_simple_remove(&nvme_fc_local_port_cnt, lport->localport.port_num); + ida_destroy(&lport->endp_cnt); + + put_device(lport->dev); + + kfree(lport); +} + +static void +nvme_fc_lport_put(struct nvme_fc_lport *lport) +{ + kref_put(&lport->ref, nvme_fc_free_lport); +} + +static int +nvme_fc_lport_get(struct nvme_fc_lport *lport) +{ + return kref_get_unless_zero(&lport->ref); +} + + +static struct nvme_fc_lport * +nvme_fc_attach_to_unreg_lport(struct nvme_fc_port_info *pinfo) +{ + struct nvme_fc_lport *lport; + unsigned long flags; + + spin_lock_irqsave(&nvme_fc_lock, flags); + + list_for_each_entry(lport, &nvme_fc_lport_list, port_list) { + if (lport->localport.node_name != pinfo->node_name || + lport->localport.port_name != pinfo->port_name) + continue; + + if (lport->localport.port_state != FC_OBJSTATE_DELETED) { + lport = ERR_PTR(-EEXIST); + goto out_done; + } + + if (!nvme_fc_lport_get(lport)) { + /* + * fails if ref cnt already 0. If so, + * act as if lport already deleted + */ + lport = NULL; + goto out_done; + } + + /* resume the lport */ + + lport->localport.port_role = pinfo->port_role; + lport->localport.port_id = pinfo->port_id; + lport->localport.port_state = FC_OBJSTATE_ONLINE; + + spin_unlock_irqrestore(&nvme_fc_lock, flags); + + return lport; + } + + lport = NULL; + +out_done: + spin_unlock_irqrestore(&nvme_fc_lock, flags); + + return lport; +} /** * nvme_fc_register_localport - transport entry point called by an @@ -257,6 +341,28 @@ nvme_fc_register_localport(struct nvme_fc_port_info *pinfo, goto out_reghost_failed; } + /* + * look to see if there is already a localport that had been + * deregistered and in the process of waiting for all the + * references to fully be removed. If the references haven't + * expired, we can simply re-enable the localport. Remoteports + * and controller reconnections should resume naturally. + */ + newrec = nvme_fc_attach_to_unreg_lport(pinfo); + + /* found an lport, but something about its state is bad */ + if (IS_ERR(newrec)) { + ret = PTR_ERR(newrec); + goto out_reghost_failed; + + /* found existing lport, which was resumed */ + } else if (newrec) { + *portptr = &newrec->localport; + return 0; + } + + /* nothing found - allocate a new localport struct */ + newrec = kmalloc((sizeof(*newrec) + template->local_priv_sz), GFP_KERNEL); if (!newrec) { @@ -310,44 +416,6 @@ out_reghost_failed: } EXPORT_SYMBOL_GPL(nvme_fc_register_localport); -static void -nvme_fc_free_lport(struct kref *ref) -{ - struct nvme_fc_lport *lport = - container_of(ref, struct nvme_fc_lport, ref); - unsigned long flags; - - WARN_ON(lport->localport.port_state != FC_OBJSTATE_DELETED); - WARN_ON(!list_empty(&lport->endp_list)); - - /* remove from transport list */ - spin_lock_irqsave(&nvme_fc_lock, flags); - list_del(&lport->port_list); - spin_unlock_irqrestore(&nvme_fc_lock, flags); - - /* let the LLDD know we've finished tearing it down */ - lport->ops->localport_delete(&lport->localport); - - ida_simple_remove(&nvme_fc_local_port_cnt, lport->localport.port_num); - ida_destroy(&lport->endp_cnt); - - put_device(lport->dev); - - kfree(lport); -} - -static void -nvme_fc_lport_put(struct nvme_fc_lport *lport) -{ - kref_put(&lport->ref, nvme_fc_free_lport); -} - -static int -nvme_fc_lport_get(struct nvme_fc_lport *lport) -{ - return kref_get_unless_zero(&lport->ref); -} - /** * nvme_fc_unregister_localport - transport entry point called by an * LLDD to deregister/remove a previously @@ -2731,6 +2799,7 @@ nvme_fc_init_ctrl(struct device *dev, struct nvmf_ctrl_options *opts, ret = blk_mq_alloc_tag_set(&ctrl->admin_tag_set); if (ret) goto out_free_queues; + ctrl->ctrl.admin_tagset = &ctrl->admin_tag_set; ctrl->ctrl.admin_q = blk_mq_init_queue(&ctrl->admin_tag_set); if (IS_ERR(ctrl->ctrl.admin_q)) { diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h index 8f2a168ddc01..936c4056d98e 100644 --- a/drivers/nvme/host/nvme.h +++ b/drivers/nvme/host/nvme.h @@ -125,6 +125,7 @@ struct nvme_ctrl { struct kref kref; int instance; struct blk_mq_tag_set *tagset; + struct blk_mq_tag_set *admin_tagset; struct list_head namespaces; struct mutex namespaces_mutex; struct device *device; /* char device */ @@ -142,6 +143,7 @@ struct nvme_ctrl { u16 cntlid; u32 ctrl_config; + u16 mtfa; u32 queue_count; u64 cap; @@ -160,6 +162,7 @@ struct nvme_ctrl { u16 kas; u8 npss; u8 apsta; + unsigned int shutdown_timeout; unsigned int kato; bool subsystem; unsigned long quirks; @@ -167,6 +170,7 @@ struct nvme_ctrl { struct work_struct scan_work; struct work_struct async_event_work; struct delayed_work ka_work; + struct work_struct fw_act_work; /* Power saving configuration */ u64 ps_max_latency_us; @@ -207,13 +211,9 @@ struct nvme_ns { bool ext; u8 pi_type; unsigned long flags; - u16 noiob; - #define NVME_NS_REMOVING 0 #define NVME_NS_DEAD 1 - - u64 mode_select_num_blocks; - u32 mode_select_block_len; + u16 noiob; }; struct nvme_ctrl_ops { diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 925467b31a33..544805a2421b 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -555,8 +555,10 @@ static blk_status_t nvme_setup_prps(struct nvme_dev *dev, struct request *req) int nprps, i; length -= (page_size - offset); - if (length <= 0) + if (length <= 0) { + iod->first_dma = 0; return BLK_STS_OK; + } dma_len -= (page_size - offset); if (dma_len) { @@ -1376,6 +1378,7 @@ static int nvme_alloc_admin_tags(struct nvme_dev *dev) if (blk_mq_alloc_tag_set(&dev->admin_tagset)) return -ENOMEM; + dev->ctrl.admin_tagset = &dev->admin_tagset; dev->ctrl.admin_q = blk_mq_init_queue(&dev->admin_tagset); if (IS_ERR(dev->ctrl.admin_q)) { diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c index 9ff0eb3a625e..6a7682620d87 100644 --- a/drivers/nvme/host/rdma.c +++ b/drivers/nvme/host/rdma.c @@ -36,8 +36,6 @@ #define NVME_RDMA_CONNECT_TIMEOUT_MS 3000 /* 3 second */ -#define NVME_RDMA_MAX_SEGMENT_SIZE 0xffffff /* 24-bit SGL field */ - #define NVME_RDMA_MAX_SEGMENTS 256 #define NVME_RDMA_MAX_INLINE_SEGMENTS 1 @@ -151,6 +149,9 @@ static int nvme_rdma_cm_handler(struct rdma_cm_id *cm_id, struct rdma_cm_event *event); static void nvme_rdma_recv_done(struct ib_cq *cq, struct ib_wc *wc); +static const struct blk_mq_ops nvme_rdma_mq_ops; +static const struct blk_mq_ops nvme_rdma_admin_mq_ops; + /* XXX: really should move to a generic header sooner or later.. */ static inline void put_unaligned_le24(u32 val, u8 *p) { @@ -503,7 +504,7 @@ out_put_dev: return ret; } -static int nvme_rdma_init_queue(struct nvme_rdma_ctrl *ctrl, +static int nvme_rdma_alloc_queue(struct nvme_rdma_ctrl *ctrl, int idx, size_t queue_size) { struct nvme_rdma_queue *queue; @@ -561,22 +562,20 @@ out_destroy_cm_id: static void nvme_rdma_stop_queue(struct nvme_rdma_queue *queue) { + if (!test_and_clear_bit(NVME_RDMA_Q_LIVE, &queue->flags)) + return; + rdma_disconnect(queue->cm_id); ib_drain_qp(queue->qp); } static void nvme_rdma_free_queue(struct nvme_rdma_queue *queue) -{ - nvme_rdma_destroy_queue_ib(queue); - rdma_destroy_id(queue->cm_id); -} - -static void nvme_rdma_stop_and_free_queue(struct nvme_rdma_queue *queue) { if (test_and_set_bit(NVME_RDMA_Q_DELETING, &queue->flags)) return; - nvme_rdma_stop_queue(queue); - nvme_rdma_free_queue(queue); + + nvme_rdma_destroy_queue_ib(queue); + rdma_destroy_id(queue->cm_id); } static void nvme_rdma_free_io_queues(struct nvme_rdma_ctrl *ctrl) @@ -584,31 +583,53 @@ static void nvme_rdma_free_io_queues(struct nvme_rdma_ctrl *ctrl) int i; for (i = 1; i < ctrl->ctrl.queue_count; i++) - nvme_rdma_stop_and_free_queue(&ctrl->queues[i]); + nvme_rdma_free_queue(&ctrl->queues[i]); } -static int nvme_rdma_connect_io_queues(struct nvme_rdma_ctrl *ctrl) +static void nvme_rdma_stop_io_queues(struct nvme_rdma_ctrl *ctrl) +{ + int i; + + for (i = 1; i < ctrl->ctrl.queue_count; i++) + nvme_rdma_stop_queue(&ctrl->queues[i]); +} + +static int nvme_rdma_start_queue(struct nvme_rdma_ctrl *ctrl, int idx) +{ + int ret; + + if (idx) + ret = nvmf_connect_io_queue(&ctrl->ctrl, idx); + else + ret = nvmf_connect_admin_queue(&ctrl->ctrl); + + if (!ret) + set_bit(NVME_RDMA_Q_LIVE, &ctrl->queues[idx].flags); + else + dev_info(ctrl->ctrl.device, + "failed to connect queue: %d ret=%d\n", idx, ret); + return ret; +} + +static int nvme_rdma_start_io_queues(struct nvme_rdma_ctrl *ctrl) { int i, ret = 0; for (i = 1; i < ctrl->ctrl.queue_count; i++) { - ret = nvmf_connect_io_queue(&ctrl->ctrl, i); - if (ret) { - dev_info(ctrl->ctrl.device, - "failed to connect i/o queue: %d\n", ret); - goto out_free_queues; - } - set_bit(NVME_RDMA_Q_LIVE, &ctrl->queues[i].flags); + ret = nvme_rdma_start_queue(ctrl, i); + if (ret) + goto out_stop_queues; } return 0; -out_free_queues: - nvme_rdma_free_io_queues(ctrl); +out_stop_queues: + for (i--; i >= 1; i--) + nvme_rdma_stop_queue(&ctrl->queues[i]); return ret; } -static int nvme_rdma_init_io_queues(struct nvme_rdma_ctrl *ctrl) +static int nvme_rdma_alloc_io_queues(struct nvme_rdma_ctrl *ctrl) { struct nvmf_ctrl_options *opts = ctrl->ctrl.opts; unsigned int nr_io_queues; @@ -627,32 +648,230 @@ static int nvme_rdma_init_io_queues(struct nvme_rdma_ctrl *ctrl) "creating %d I/O queues.\n", nr_io_queues); for (i = 1; i < ctrl->ctrl.queue_count; i++) { - 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); + ret = nvme_rdma_alloc_queue(ctrl, i, + ctrl->ctrl.sqsize + 1); + if (ret) goto out_free_queues; - } } return 0; out_free_queues: for (i--; i >= 1; i--) - nvme_rdma_stop_and_free_queue(&ctrl->queues[i]); + nvme_rdma_free_queue(&ctrl->queues[i]); return ret; } -static void nvme_rdma_destroy_admin_queue(struct nvme_rdma_ctrl *ctrl) +static void nvme_rdma_free_tagset(struct nvme_ctrl *nctrl, bool admin) +{ + struct nvme_rdma_ctrl *ctrl = to_rdma_ctrl(nctrl); + struct blk_mq_tag_set *set = admin ? + &ctrl->admin_tag_set : &ctrl->tag_set; + + blk_mq_free_tag_set(set); + nvme_rdma_dev_put(ctrl->device); +} + +static struct blk_mq_tag_set *nvme_rdma_alloc_tagset(struct nvme_ctrl *nctrl, + bool admin) +{ + struct nvme_rdma_ctrl *ctrl = to_rdma_ctrl(nctrl); + struct blk_mq_tag_set *set; + int ret; + + if (admin) { + set = &ctrl->admin_tag_set; + memset(set, 0, sizeof(*set)); + set->ops = &nvme_rdma_admin_mq_ops; + set->queue_depth = NVME_RDMA_AQ_BLKMQ_DEPTH; + set->reserved_tags = 2; /* connect + keep-alive */ + set->numa_node = NUMA_NO_NODE; + set->cmd_size = sizeof(struct nvme_rdma_request) + + SG_CHUNK_SIZE * sizeof(struct scatterlist); + set->driver_data = ctrl; + set->nr_hw_queues = 1; + set->timeout = ADMIN_TIMEOUT; + } else { + set = &ctrl->tag_set; + memset(set, 0, sizeof(*set)); + set->ops = &nvme_rdma_mq_ops; + set->queue_depth = nctrl->opts->queue_size; + set->reserved_tags = 1; /* fabric connect */ + set->numa_node = NUMA_NO_NODE; + set->flags = BLK_MQ_F_SHOULD_MERGE; + set->cmd_size = sizeof(struct nvme_rdma_request) + + SG_CHUNK_SIZE * sizeof(struct scatterlist); + set->driver_data = ctrl; + set->nr_hw_queues = nctrl->queue_count - 1; + set->timeout = NVME_IO_TIMEOUT; + } + + ret = blk_mq_alloc_tag_set(set); + if (ret) + goto out; + + /* + * We need a reference on the device as long as the tag_set is alive, + * as the MRs in the request structures need a valid ib_device. + */ + ret = nvme_rdma_dev_get(ctrl->device); + if (!ret) { + ret = -EINVAL; + goto out_free_tagset; + } + + return set; + +out_free_tagset: + blk_mq_free_tag_set(set); +out: + return ERR_PTR(ret); +} + +static void nvme_rdma_destroy_admin_queue(struct nvme_rdma_ctrl *ctrl, + bool remove) { nvme_rdma_free_qe(ctrl->queues[0].device->dev, &ctrl->async_event_sqe, sizeof(struct nvme_command), DMA_TO_DEVICE); - nvme_rdma_stop_and_free_queue(&ctrl->queues[0]); - blk_cleanup_queue(ctrl->ctrl.admin_q); - blk_mq_free_tag_set(&ctrl->admin_tag_set); - nvme_rdma_dev_put(ctrl->device); + nvme_rdma_stop_queue(&ctrl->queues[0]); + if (remove) { + blk_cleanup_queue(ctrl->ctrl.admin_q); + nvme_rdma_free_tagset(&ctrl->ctrl, true); + } + nvme_rdma_free_queue(&ctrl->queues[0]); +} + +static int nvme_rdma_configure_admin_queue(struct nvme_rdma_ctrl *ctrl, + bool new) +{ + int error; + + error = nvme_rdma_alloc_queue(ctrl, 0, NVME_AQ_DEPTH); + if (error) + return error; + + ctrl->device = ctrl->queues[0].device; + + ctrl->max_fr_pages = min_t(u32, NVME_RDMA_MAX_SEGMENTS, + ctrl->device->dev->attrs.max_fast_reg_page_list_len); + + if (new) { + ctrl->ctrl.admin_tagset = nvme_rdma_alloc_tagset(&ctrl->ctrl, true); + if (IS_ERR(ctrl->ctrl.admin_tagset)) + goto out_free_queue; + + ctrl->ctrl.admin_q = blk_mq_init_queue(&ctrl->admin_tag_set); + if (IS_ERR(ctrl->ctrl.admin_q)) { + error = PTR_ERR(ctrl->ctrl.admin_q); + goto out_free_tagset; + } + } else { + error = blk_mq_reinit_tagset(&ctrl->admin_tag_set, + nvme_rdma_reinit_request); + if (error) + goto out_free_queue; + } + + error = nvme_rdma_start_queue(ctrl, 0); + if (error) + goto out_cleanup_queue; + + error = ctrl->ctrl.ops->reg_read64(&ctrl->ctrl, NVME_REG_CAP, + &ctrl->ctrl.cap); + if (error) { + dev_err(ctrl->ctrl.device, + "prop_get NVME_REG_CAP failed\n"); + goto out_cleanup_queue; + } + + ctrl->ctrl.sqsize = + min_t(int, NVME_CAP_MQES(ctrl->ctrl.cap), ctrl->ctrl.sqsize); + + error = nvme_enable_ctrl(&ctrl->ctrl, ctrl->ctrl.cap); + if (error) + goto out_cleanup_queue; + + ctrl->ctrl.max_hw_sectors = + (ctrl->max_fr_pages - 1) << (PAGE_SHIFT - 9); + + error = nvme_init_identify(&ctrl->ctrl); + if (error) + goto out_cleanup_queue; + + error = nvme_rdma_alloc_qe(ctrl->queues[0].device->dev, + &ctrl->async_event_sqe, sizeof(struct nvme_command), + DMA_TO_DEVICE); + if (error) + goto out_cleanup_queue; + + return 0; + +out_cleanup_queue: + if (new) + blk_cleanup_queue(ctrl->ctrl.admin_q); +out_free_tagset: + if (new) + nvme_rdma_free_tagset(&ctrl->ctrl, true); +out_free_queue: + nvme_rdma_free_queue(&ctrl->queues[0]); + return error; +} + +static void nvme_rdma_destroy_io_queues(struct nvme_rdma_ctrl *ctrl, + bool remove) +{ + nvme_rdma_stop_io_queues(ctrl); + if (remove) { + blk_cleanup_queue(ctrl->ctrl.connect_q); + nvme_rdma_free_tagset(&ctrl->ctrl, false); + } + nvme_rdma_free_io_queues(ctrl); +} + +static int nvme_rdma_configure_io_queues(struct nvme_rdma_ctrl *ctrl, bool new) +{ + int ret; + + ret = nvme_rdma_alloc_io_queues(ctrl); + if (ret) + return ret; + + if (new) { + ctrl->ctrl.tagset = nvme_rdma_alloc_tagset(&ctrl->ctrl, false); + if (IS_ERR(ctrl->ctrl.tagset)) + goto out_free_io_queues; + + ctrl->ctrl.connect_q = blk_mq_init_queue(&ctrl->tag_set); + if (IS_ERR(ctrl->ctrl.connect_q)) { + ret = PTR_ERR(ctrl->ctrl.connect_q); + goto out_free_tag_set; + } + } else { + ret = blk_mq_reinit_tagset(&ctrl->tag_set, + nvme_rdma_reinit_request); + if (ret) + goto out_free_io_queues; + + blk_mq_update_nr_hw_queues(&ctrl->tag_set, + ctrl->ctrl.queue_count - 1); + } + + ret = nvme_rdma_start_io_queues(ctrl); + if (ret) + goto out_cleanup_connect_q; + + return 0; + +out_cleanup_connect_q: + if (new) + blk_cleanup_queue(ctrl->ctrl.connect_q); +out_free_tag_set: + if (new) + nvme_rdma_free_tagset(&ctrl->ctrl, false); +out_free_io_queues: + nvme_rdma_free_io_queues(ctrl); + return ret; } static void nvme_rdma_free_ctrl(struct nvme_ctrl *nctrl) @@ -701,47 +920,18 @@ static void nvme_rdma_reconnect_ctrl_work(struct work_struct *work) ++ctrl->ctrl.nr_reconnects; - if (ctrl->ctrl.queue_count > 1) { - nvme_rdma_free_io_queues(ctrl); + if (ctrl->ctrl.queue_count > 1) + nvme_rdma_destroy_io_queues(ctrl, false); - ret = blk_mq_reinit_tagset(&ctrl->tag_set, - nvme_rdma_reinit_request); - if (ret) - goto requeue; - } - - nvme_rdma_stop_and_free_queue(&ctrl->queues[0]); - - ret = blk_mq_reinit_tagset(&ctrl->admin_tag_set, - nvme_rdma_reinit_request); - if (ret) - goto requeue; - - ret = nvme_rdma_init_queue(ctrl, 0, NVME_AQ_DEPTH); - if (ret) - goto requeue; - - ret = nvmf_connect_admin_queue(&ctrl->ctrl); - if (ret) - goto requeue; - - set_bit(NVME_RDMA_Q_LIVE, &ctrl->queues[0].flags); - - ret = nvme_enable_ctrl(&ctrl->ctrl, ctrl->ctrl.cap); + nvme_rdma_destroy_admin_queue(ctrl, false); + ret = nvme_rdma_configure_admin_queue(ctrl, false); if (ret) goto requeue; if (ctrl->ctrl.queue_count > 1) { - ret = nvme_rdma_init_io_queues(ctrl); + ret = nvme_rdma_configure_io_queues(ctrl, false); if (ret) goto requeue; - - ret = nvme_rdma_connect_io_queues(ctrl); - if (ret) - goto requeue; - - blk_mq_update_nr_hw_queues(&ctrl->tag_set, - ctrl->ctrl.queue_count - 1); } changed = nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_LIVE); @@ -764,16 +954,15 @@ 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_ctrl(&ctrl->ctrl); - for (i = 0; i < ctrl->ctrl.queue_count; i++) - clear_bit(NVME_RDMA_Q_LIVE, &ctrl->queues[i].flags); - - if (ctrl->ctrl.queue_count > 1) + if (ctrl->ctrl.queue_count > 1) { nvme_stop_queues(&ctrl->ctrl); + nvme_rdma_stop_io_queues(ctrl); + } blk_mq_quiesce_queue(ctrl->ctrl.admin_q); + nvme_rdma_stop_queue(&ctrl->queues[0]); /* We must take care of fastfail/requeue all our inflight requests */ if (ctrl->ctrl.queue_count > 1) @@ -858,7 +1047,7 @@ static void nvme_rdma_unmap_data(struct nvme_rdma_queue *queue, if (req->mr->need_inval) { res = nvme_rdma_inv_rkey(queue, req); - if (res < 0) { + if (unlikely(res < 0)) { dev_err(ctrl->ctrl.device, "Queueing INV WR for rkey %#x failed (%d)\n", req->mr->rkey, res); @@ -923,7 +1112,7 @@ static int nvme_rdma_map_sg_fr(struct nvme_rdma_queue *queue, int nr; nr = ib_map_mr_sg(req->mr, req->sg_table.sgl, count, NULL, PAGE_SIZE); - if (nr < count) { + if (unlikely(nr < count)) { if (nr < 0) return nr; return -EINVAL; @@ -1059,7 +1248,7 @@ static int nvme_rdma_post_send(struct nvme_rdma_queue *queue, first = ≀ ret = ib_post_send(queue->qp, first, &bad_wr); - if (ret) { + if (unlikely(ret)) { dev_err(queue->ctrl->ctrl.device, "%s failed with error code %d\n", __func__, ret); } @@ -1085,7 +1274,7 @@ static int nvme_rdma_post_recv(struct nvme_rdma_queue *queue, wr.num_sge = 1; ret = ib_post_recv(queue->qp, &wr, &bad_wr); - if (ret) { + if (unlikely(ret)) { dev_err(queue->ctrl->ctrl.device, "%s failed with error code %d\n", __func__, ret); } @@ -1445,7 +1634,7 @@ static blk_status_t nvme_rdma_queue_rq(struct blk_mq_hw_ctx *hctx, blk_mq_start_request(rq); err = nvme_rdma_map_data(queue, rq, c); - if (err < 0) { + if (unlikely(err < 0)) { dev_err(queue->ctrl->ctrl.device, "Failed to map data (%d)\n", err); nvme_cleanup_cmd(rq); @@ -1459,7 +1648,7 @@ static blk_status_t nvme_rdma_queue_rq(struct blk_mq_hw_ctx *hctx, flush = true; err = nvme_rdma_post_send(queue, sqe, req->sge, req->num_sge, req->mr->need_inval ? &req->reg_wr.wr : NULL, flush); - if (err) { + if (unlikely(err)) { nvme_rdma_unmap_data(queue, rq); goto err; } @@ -1519,98 +1708,7 @@ static const struct blk_mq_ops nvme_rdma_admin_mq_ops = { .timeout = nvme_rdma_timeout, }; -static int nvme_rdma_configure_admin_queue(struct nvme_rdma_ctrl *ctrl) -{ - int error; - - error = nvme_rdma_init_queue(ctrl, 0, NVME_AQ_DEPTH); - if (error) - return error; - - ctrl->device = ctrl->queues[0].device; - - /* - * We need a reference on the device as long as the tag_set is alive, - * as the MRs in the request structures need a valid ib_device. - */ - error = -EINVAL; - if (!nvme_rdma_dev_get(ctrl->device)) - goto out_free_queue; - - ctrl->max_fr_pages = min_t(u32, NVME_RDMA_MAX_SEGMENTS, - ctrl->device->dev->attrs.max_fast_reg_page_list_len); - - memset(&ctrl->admin_tag_set, 0, sizeof(ctrl->admin_tag_set)); - ctrl->admin_tag_set.ops = &nvme_rdma_admin_mq_ops; - ctrl->admin_tag_set.queue_depth = NVME_RDMA_AQ_BLKMQ_DEPTH; - ctrl->admin_tag_set.reserved_tags = 2; /* connect + keep-alive */ - ctrl->admin_tag_set.numa_node = NUMA_NO_NODE; - ctrl->admin_tag_set.cmd_size = sizeof(struct nvme_rdma_request) + - SG_CHUNK_SIZE * 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; - - error = blk_mq_alloc_tag_set(&ctrl->admin_tag_set); - if (error) - goto out_put_dev; - - ctrl->ctrl.admin_q = blk_mq_init_queue(&ctrl->admin_tag_set); - if (IS_ERR(ctrl->ctrl.admin_q)) { - error = PTR_ERR(ctrl->ctrl.admin_q); - goto out_free_tagset; - } - - error = nvmf_connect_admin_queue(&ctrl->ctrl); - if (error) - goto out_cleanup_queue; - - set_bit(NVME_RDMA_Q_LIVE, &ctrl->queues[0].flags); - - error = nvmf_reg_read64(&ctrl->ctrl, NVME_REG_CAP, - &ctrl->ctrl.cap); - if (error) { - dev_err(ctrl->ctrl.device, - "prop_get NVME_REG_CAP failed\n"); - goto out_cleanup_queue; - } - - ctrl->ctrl.sqsize = - min_t(int, NVME_CAP_MQES(ctrl->ctrl.cap), ctrl->ctrl.sqsize); - - error = nvme_enable_ctrl(&ctrl->ctrl, ctrl->ctrl.cap); - if (error) - goto out_cleanup_queue; - - ctrl->ctrl.max_hw_sectors = - (ctrl->max_fr_pages - 1) << (PAGE_SHIFT - 9); - - error = nvme_init_identify(&ctrl->ctrl); - if (error) - goto out_cleanup_queue; - - error = nvme_rdma_alloc_qe(ctrl->queues[0].device->dev, - &ctrl->async_event_sqe, sizeof(struct nvme_command), - DMA_TO_DEVICE); - if (error) - goto out_cleanup_queue; - - return 0; - -out_cleanup_queue: - blk_cleanup_queue(ctrl->ctrl.admin_q); -out_free_tagset: - /* disconnect and drain the queue before freeing the tagset */ - nvme_rdma_stop_queue(&ctrl->queues[0]); - blk_mq_free_tag_set(&ctrl->admin_tag_set); -out_put_dev: - nvme_rdma_dev_put(ctrl->device); -out_free_queue: - nvme_rdma_free_queue(&ctrl->queues[0]); - return error; -} - -static void nvme_rdma_shutdown_ctrl(struct nvme_rdma_ctrl *ctrl) +static void nvme_rdma_shutdown_ctrl(struct nvme_rdma_ctrl *ctrl, bool shutdown) { cancel_work_sync(&ctrl->err_work); cancel_delayed_work_sync(&ctrl->reconnect_work); @@ -1619,33 +1717,26 @@ static void nvme_rdma_shutdown_ctrl(struct nvme_rdma_ctrl *ctrl) nvme_stop_queues(&ctrl->ctrl); blk_mq_tagset_busy_iter(&ctrl->tag_set, nvme_cancel_request, &ctrl->ctrl); - nvme_rdma_free_io_queues(ctrl); + nvme_rdma_destroy_io_queues(ctrl, shutdown); } - if (test_bit(NVME_RDMA_Q_LIVE, &ctrl->queues[0].flags)) + if (shutdown) nvme_shutdown_ctrl(&ctrl->ctrl); + else + nvme_disable_ctrl(&ctrl->ctrl, ctrl->ctrl.cap); blk_mq_quiesce_queue(ctrl->ctrl.admin_q); blk_mq_tagset_busy_iter(&ctrl->admin_tag_set, nvme_cancel_request, &ctrl->ctrl); blk_mq_unquiesce_queue(ctrl->ctrl.admin_q); - nvme_rdma_destroy_admin_queue(ctrl); + nvme_rdma_destroy_admin_queue(ctrl, shutdown); } -static void __nvme_rdma_remove_ctrl(struct nvme_rdma_ctrl *ctrl, bool shutdown) +static void nvme_rdma_remove_ctrl(struct nvme_rdma_ctrl *ctrl) { - nvme_stop_ctrl(&ctrl->ctrl); nvme_remove_namespaces(&ctrl->ctrl); - if (shutdown) - nvme_rdma_shutdown_ctrl(ctrl); - + nvme_rdma_shutdown_ctrl(ctrl, true); nvme_uninit_ctrl(&ctrl->ctrl); - if (ctrl->ctrl.tagset) { - blk_cleanup_queue(ctrl->ctrl.connect_q); - blk_mq_free_tag_set(&ctrl->tag_set); - nvme_rdma_dev_put(ctrl->device); - } - nvme_put_ctrl(&ctrl->ctrl); } @@ -1654,7 +1745,8 @@ static void nvme_rdma_del_ctrl_work(struct work_struct *work) struct nvme_rdma_ctrl *ctrl = container_of(work, struct nvme_rdma_ctrl, delete_work); - __nvme_rdma_remove_ctrl(ctrl, true); + nvme_stop_ctrl(&ctrl->ctrl); + nvme_rdma_remove_ctrl(ctrl); } static int __nvme_rdma_del_ctrl(struct nvme_rdma_ctrl *ctrl) @@ -1686,14 +1778,6 @@ static int nvme_rdma_del_ctrl(struct nvme_ctrl *nctrl) return ret; } -static void nvme_rdma_remove_ctrl_work(struct work_struct *work) -{ - struct nvme_rdma_ctrl *ctrl = container_of(work, - struct nvme_rdma_ctrl, delete_work); - - __nvme_rdma_remove_ctrl(ctrl, false); -} - static void nvme_rdma_reset_ctrl_work(struct work_struct *work) { struct nvme_rdma_ctrl *ctrl = @@ -1702,31 +1786,16 @@ static void nvme_rdma_reset_ctrl_work(struct work_struct *work) bool changed; nvme_stop_ctrl(&ctrl->ctrl); - nvme_rdma_shutdown_ctrl(ctrl); + nvme_rdma_shutdown_ctrl(ctrl, false); - ret = nvme_rdma_configure_admin_queue(ctrl); - if (ret) { - /* ctrl is already shutdown, just remove the ctrl */ - INIT_WORK(&ctrl->delete_work, nvme_rdma_remove_ctrl_work); - goto del_dead_ctrl; - } + ret = nvme_rdma_configure_admin_queue(ctrl, false); + if (ret) + goto out_fail; if (ctrl->ctrl.queue_count > 1) { - ret = blk_mq_reinit_tagset(&ctrl->tag_set, - nvme_rdma_reinit_request); + ret = nvme_rdma_configure_io_queues(ctrl, false); if (ret) - goto del_dead_ctrl; - - ret = nvme_rdma_init_io_queues(ctrl); - if (ret) - goto del_dead_ctrl; - - ret = nvme_rdma_connect_io_queues(ctrl); - if (ret) - goto del_dead_ctrl; - - blk_mq_update_nr_hw_queues(&ctrl->tag_set, - ctrl->ctrl.queue_count - 1); + goto out_fail; } changed = nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_LIVE); @@ -1736,10 +1805,9 @@ static void nvme_rdma_reset_ctrl_work(struct work_struct *work) return; -del_dead_ctrl: - /* Deleting this dead controller... */ +out_fail: dev_warn(ctrl->ctrl.device, "Removing after reset failure\n"); - WARN_ON(!queue_work(nvme_wq, &ctrl->delete_work)); + nvme_rdma_remove_ctrl(ctrl); } static const struct nvme_ctrl_ops nvme_rdma_ctrl_ops = { @@ -1755,62 +1823,6 @@ static const struct nvme_ctrl_ops nvme_rdma_ctrl_ops = { .get_address = nvmf_get_address, }; -static int nvme_rdma_create_io_queues(struct nvme_rdma_ctrl *ctrl) -{ - int ret; - - ret = nvme_rdma_init_io_queues(ctrl); - if (ret) - return ret; - - /* - * We need a reference on the device as long as the tag_set is alive, - * as the MRs in the request structures need a valid ib_device. - */ - ret = -EINVAL; - if (!nvme_rdma_dev_get(ctrl->device)) - goto out_free_io_queues; - - memset(&ctrl->tag_set, 0, sizeof(ctrl->tag_set)); - ctrl->tag_set.ops = &nvme_rdma_mq_ops; - 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; - ctrl->tag_set.cmd_size = sizeof(struct nvme_rdma_request) + - SG_CHUNK_SIZE * sizeof(struct scatterlist); - ctrl->tag_set.driver_data = ctrl; - ctrl->tag_set.nr_hw_queues = ctrl->ctrl.queue_count - 1; - ctrl->tag_set.timeout = NVME_IO_TIMEOUT; - - ret = blk_mq_alloc_tag_set(&ctrl->tag_set); - if (ret) - goto out_put_dev; - ctrl->ctrl.tagset = &ctrl->tag_set; - - ctrl->ctrl.connect_q = blk_mq_init_queue(&ctrl->tag_set); - if (IS_ERR(ctrl->ctrl.connect_q)) { - ret = PTR_ERR(ctrl->ctrl.connect_q); - goto out_free_tag_set; - } - - ret = nvme_rdma_connect_io_queues(ctrl); - if (ret) - goto out_cleanup_connect_q; - - return 0; - -out_cleanup_connect_q: - blk_cleanup_queue(ctrl->ctrl.connect_q); -out_free_tag_set: - blk_mq_free_tag_set(&ctrl->tag_set); -out_put_dev: - nvme_rdma_dev_put(ctrl->device); -out_free_io_queues: - nvme_rdma_free_io_queues(ctrl); - return ret; -} - static struct nvme_ctrl *nvme_rdma_create_ctrl(struct device *dev, struct nvmf_ctrl_options *opts) { @@ -1868,7 +1880,7 @@ static struct nvme_ctrl *nvme_rdma_create_ctrl(struct device *dev, if (!ctrl->queues) goto out_uninit_ctrl; - ret = nvme_rdma_configure_admin_queue(ctrl); + ret = nvme_rdma_configure_admin_queue(ctrl, true); if (ret) goto out_kfree_queues; @@ -1903,7 +1915,7 @@ static struct nvme_ctrl *nvme_rdma_create_ctrl(struct device *dev, } if (opts->nr_io_queues) { - ret = nvme_rdma_create_io_queues(ctrl); + ret = nvme_rdma_configure_io_queues(ctrl, true); if (ret) goto out_remove_admin_queue; } @@ -1925,7 +1937,7 @@ static struct nvme_ctrl *nvme_rdma_create_ctrl(struct device *dev, return &ctrl->ctrl; out_remove_admin_queue: - nvme_rdma_destroy_admin_queue(ctrl); + nvme_rdma_destroy_admin_queue(ctrl, true); out_kfree_queues: kfree(ctrl->queues); out_uninit_ctrl: diff --git a/drivers/nvme/target/admin-cmd.c b/drivers/nvme/target/admin-cmd.c index a53bb6635b83..9496c71d2257 100644 --- a/drivers/nvme/target/admin-cmd.c +++ b/drivers/nvme/target/admin-cmd.c @@ -100,7 +100,7 @@ static u16 nvmet_get_smart_log(struct nvmet_req *req, u16 status; WARN_ON(req == NULL || slog == NULL); - if (req->cmd->get_log_page.nsid == cpu_to_le32(0xFFFFFFFF)) + if (req->cmd->get_log_page.nsid == cpu_to_le32(NVME_NSID_ALL)) status = nvmet_get_smart_log_all(req, slog); else status = nvmet_get_smart_log_nsid(req, slog); @@ -168,15 +168,6 @@ out: nvmet_req_complete(req, status); } -static void copy_and_pad(char *dst, int dst_len, const char *src, int src_len) -{ - int len = min(src_len, dst_len); - - memcpy(dst, src, len); - if (dst_len > len) - memset(dst + len, ' ', dst_len - len); -} - static void nvmet_execute_identify_ctrl(struct nvmet_req *req) { struct nvmet_ctrl *ctrl = req->sq->ctrl; @@ -196,8 +187,9 @@ static void nvmet_execute_identify_ctrl(struct nvmet_req *req) bin2hex(id->sn, &ctrl->subsys->serial, min(sizeof(ctrl->subsys->serial), sizeof(id->sn) / 2)); - copy_and_pad(id->mn, sizeof(id->mn), model, sizeof(model) - 1); - copy_and_pad(id->fr, sizeof(id->fr), UTS_RELEASE, strlen(UTS_RELEASE)); + memcpy_and_pad(id->mn, sizeof(id->mn), model, sizeof(model) - 1, ' '); + memcpy_and_pad(id->fr, sizeof(id->fr), + UTS_RELEASE, strlen(UTS_RELEASE), ' '); id->rab = 6; diff --git a/drivers/nvme/target/configfs.c b/drivers/nvme/target/configfs.c index 0a0067e771f5..b6aeb1d70951 100644 --- a/drivers/nvme/target/configfs.c +++ b/drivers/nvme/target/configfs.c @@ -444,7 +444,7 @@ static struct config_group *nvmet_ns_make(struct config_group *group, goto out; ret = -EINVAL; - if (nsid == 0 || nsid == 0xffffffff) + if (nsid == 0 || nsid == NVME_NSID_ALL) goto out; ret = -ENOMEM; diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c index f4b02bb4a1a8..7c23eaf8e563 100644 --- a/drivers/nvme/target/core.c +++ b/drivers/nvme/target/core.c @@ -538,37 +538,37 @@ EXPORT_SYMBOL_GPL(nvmet_req_uninit); static inline bool nvmet_cc_en(u32 cc) { - return cc & 0x1; + return (cc >> NVME_CC_EN_SHIFT) & 0x1; } static inline u8 nvmet_cc_css(u32 cc) { - return (cc >> 4) & 0x7; + return (cc >> NVME_CC_CSS_SHIFT) & 0x7; } static inline u8 nvmet_cc_mps(u32 cc) { - return (cc >> 7) & 0xf; + return (cc >> NVME_CC_MPS_SHIFT) & 0xf; } static inline u8 nvmet_cc_ams(u32 cc) { - return (cc >> 11) & 0x7; + return (cc >> NVME_CC_AMS_SHIFT) & 0x7; } static inline u8 nvmet_cc_shn(u32 cc) { - return (cc >> 14) & 0x3; + return (cc >> NVME_CC_SHN_SHIFT) & 0x3; } static inline u8 nvmet_cc_iosqes(u32 cc) { - return (cc >> 16) & 0xf; + return (cc >> NVME_CC_IOSQES_SHIFT) & 0xf; } static inline u8 nvmet_cc_iocqes(u32 cc) { - return (cc >> 20) & 0xf; + return (cc >> NVME_CC_IOCQES_SHIFT) & 0xf; } static void nvmet_start_ctrl(struct nvmet_ctrl *ctrl) @@ -749,6 +749,7 @@ u16 nvmet_alloc_ctrl(const char *subsysnqn, const char *hostnqn, hostnqn, subsysnqn); req->rsp->result.u32 = IPO_IATTR_CONNECT_DATA(hostnqn); up_read(&nvmet_config_sem); + status = NVME_SC_CONNECT_INVALID_HOST | NVME_SC_DNR; goto out_put_subsystem; } up_read(&nvmet_config_sem); diff --git a/drivers/nvme/target/fc.c b/drivers/nvme/target/fc.c index 309c84aa7595..421e43bf1dd7 100644 --- a/drivers/nvme/target/fc.c +++ b/drivers/nvme/target/fc.c @@ -58,7 +58,8 @@ struct nvmet_fc_ls_iod { struct work_struct work; } __aligned(sizeof(unsigned long long)); -#define NVMET_FC_MAX_KB_PER_XFR 256 +#define NVMET_FC_MAX_SEQ_LENGTH (256 * 1024) +#define NVMET_FC_MAX_XFR_SGENTS (NVMET_FC_MAX_SEQ_LENGTH / PAGE_SIZE) enum nvmet_fcp_datadir { NVMET_FCP_NODATA, @@ -74,9 +75,7 @@ struct nvmet_fc_fcp_iod { struct nvme_fc_ersp_iu rspiubuf; dma_addr_t rspdma; struct scatterlist *data_sg; - struct scatterlist *next_sg; int data_sg_cnt; - u32 next_sg_offset; u32 total_length; u32 offset; enum nvmet_fcp_datadir io_dir; @@ -112,6 +111,7 @@ struct nvmet_fc_tgtport { struct ida assoc_cnt; struct nvmet_port *port; struct kref ref; + u32 max_sg_cnt; }; struct nvmet_fc_defer_fcp_req { @@ -994,6 +994,8 @@ nvmet_fc_register_targetport(struct nvmet_fc_port_info *pinfo, INIT_LIST_HEAD(&newrec->assoc_list); kref_init(&newrec->ref); ida_init(&newrec->assoc_cnt); + newrec->max_sg_cnt = min_t(u32, NVMET_FC_MAX_XFR_SGENTS, + template->max_sgl_segments); ret = nvmet_fc_alloc_ls_iodlist(newrec); if (ret) { @@ -1866,51 +1868,23 @@ nvmet_fc_transfer_fcp_data(struct nvmet_fc_tgtport *tgtport, struct nvmet_fc_fcp_iod *fod, u8 op) { struct nvmefc_tgt_fcp_req *fcpreq = fod->fcpreq; - struct scatterlist *sg, *datasg; unsigned long flags; - u32 tlen, sg_off; + u32 tlen; int ret; fcpreq->op = op; fcpreq->offset = fod->offset; fcpreq->timeout = NVME_FC_TGTOP_TIMEOUT_SEC; - tlen = min_t(u32, (NVMET_FC_MAX_KB_PER_XFR * 1024), + + tlen = min_t(u32, tgtport->max_sg_cnt * PAGE_SIZE, (fod->total_length - fod->offset)); - tlen = min_t(u32, tlen, NVME_FC_MAX_SEGMENTS * PAGE_SIZE); - tlen = min_t(u32, tlen, fod->tgtport->ops->max_sgl_segments - * PAGE_SIZE); fcpreq->transfer_length = tlen; fcpreq->transferred_length = 0; fcpreq->fcp_error = 0; fcpreq->rsplen = 0; - fcpreq->sg_cnt = 0; - - datasg = fod->next_sg; - sg_off = fod->next_sg_offset; - - for (sg = fcpreq->sg ; tlen; sg++) { - *sg = *datasg; - if (sg_off) { - sg->offset += sg_off; - sg->length -= sg_off; - sg->dma_address += sg_off; - sg_off = 0; - } - if (tlen < sg->length) { - sg->length = tlen; - fod->next_sg = datasg; - fod->next_sg_offset += tlen; - } else if (tlen == sg->length) { - fod->next_sg_offset = 0; - fod->next_sg = sg_next(datasg); - } else { - fod->next_sg_offset = 0; - datasg = sg_next(datasg); - } - tlen -= sg->length; - fcpreq->sg_cnt++; - } + fcpreq->sg = &fod->data_sg[fod->offset / PAGE_SIZE]; + fcpreq->sg_cnt = DIV_ROUND_UP(tlen, PAGE_SIZE); /* * If the last READDATA request: check if LLDD supports @@ -2225,8 +2199,6 @@ nvmet_fc_handle_fcp_rqst(struct nvmet_fc_tgtport *tgtport, fod->req.sg = fod->data_sg; fod->req.sg_cnt = fod->data_sg_cnt; fod->offset = 0; - fod->next_sg = fod->data_sg; - fod->next_sg_offset = 0; if (fod->io_dir == NVMET_FCP_WRITE) { /* pull the data over before invoking nvmet layer */ diff --git a/drivers/nvme/target/fcloop.c b/drivers/nvme/target/fcloop.c index 1bb9d5b311b1..1cb9847ec261 100644 --- a/drivers/nvme/target/fcloop.c +++ b/drivers/nvme/target/fcloop.c @@ -193,9 +193,6 @@ out_free_options: #define TGTPORT_OPTS (NVMF_OPT_WWNN | NVMF_OPT_WWPN) -#define ALL_OPTS (NVMF_OPT_WWNN | NVMF_OPT_WWPN | NVMF_OPT_ROLES | \ - NVMF_OPT_FCADDR | NVMF_OPT_LPWWNN | NVMF_OPT_LPWWPN) - static DEFINE_SPINLOCK(fcloop_lock); static LIST_HEAD(fcloop_lports); diff --git a/drivers/nvme/target/loop.c b/drivers/nvme/target/loop.c index 717ed7ddb2f6..92628c432926 100644 --- a/drivers/nvme/target/loop.c +++ b/drivers/nvme/target/loop.c @@ -375,6 +375,7 @@ static int nvme_loop_configure_admin_queue(struct nvme_loop_ctrl *ctrl) error = blk_mq_alloc_tag_set(&ctrl->admin_tag_set); if (error) goto out_free_sq; + ctrl->ctrl.admin_tagset = &ctrl->admin_tag_set; ctrl->ctrl.admin_q = blk_mq_init_queue(&ctrl->admin_tag_set); if (IS_ERR(ctrl->ctrl.admin_q)) { diff --git a/include/linux/nvme-fc-driver.h b/include/linux/nvme-fc-driver.h index 2591878c1d48..9c5cb4480806 100644 --- a/include/linux/nvme-fc-driver.h +++ b/include/linux/nvme-fc-driver.h @@ -624,7 +624,7 @@ struct nvmefc_tgt_fcp_req { u32 timeout; u32 transfer_length; struct fc_ba_rjt ba_rjt; - struct scatterlist sg[NVME_FC_MAX_SEGMENTS]; + struct scatterlist *sg; int sg_cnt; void *rspaddr; dma_addr_t rspdma; diff --git a/include/linux/nvme.h b/include/linux/nvme.h index 25d8225dbd04..05560c2ecc83 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -32,6 +32,8 @@ #define NVME_RDMA_IP_PORT 4420 +#define NVME_NSID_ALL 0xffffffff + enum nvme_subsys_type { NVME_NQN_DISC = 1, /* Discovery type target subsystem */ NVME_NQN_NVME = 2, /* NVME type target subsystem */ @@ -133,19 +135,26 @@ enum { enum { NVME_CC_ENABLE = 1 << 0, NVME_CC_CSS_NVM = 0 << 4, + NVME_CC_EN_SHIFT = 0, + NVME_CC_CSS_SHIFT = 4, NVME_CC_MPS_SHIFT = 7, - NVME_CC_ARB_RR = 0 << 11, - NVME_CC_ARB_WRRU = 1 << 11, - NVME_CC_ARB_VS = 7 << 11, - NVME_CC_SHN_NONE = 0 << 14, - NVME_CC_SHN_NORMAL = 1 << 14, - NVME_CC_SHN_ABRUPT = 2 << 14, - NVME_CC_SHN_MASK = 3 << 14, - NVME_CC_IOSQES = NVME_NVM_IOSQES << 16, - NVME_CC_IOCQES = NVME_NVM_IOCQES << 20, + NVME_CC_AMS_SHIFT = 11, + NVME_CC_SHN_SHIFT = 14, + NVME_CC_IOSQES_SHIFT = 16, + NVME_CC_IOCQES_SHIFT = 20, + NVME_CC_AMS_RR = 0 << NVME_CC_AMS_SHIFT, + NVME_CC_AMS_WRRU = 1 << NVME_CC_AMS_SHIFT, + NVME_CC_AMS_VS = 7 << NVME_CC_AMS_SHIFT, + NVME_CC_SHN_NONE = 0 << NVME_CC_SHN_SHIFT, + NVME_CC_SHN_NORMAL = 1 << NVME_CC_SHN_SHIFT, + NVME_CC_SHN_ABRUPT = 2 << NVME_CC_SHN_SHIFT, + NVME_CC_SHN_MASK = 3 << NVME_CC_SHN_SHIFT, + NVME_CC_IOSQES = NVME_NVM_IOSQES << NVME_CC_IOSQES_SHIFT, + NVME_CC_IOCQES = NVME_NVM_IOCQES << NVME_CC_IOCQES_SHIFT, NVME_CSTS_RDY = 1 << 0, NVME_CSTS_CFS = 1 << 1, NVME_CSTS_NSSRO = 1 << 4, + NVME_CSTS_PP = 1 << 5, NVME_CSTS_SHST_NORMAL = 0 << 2, NVME_CSTS_SHST_OCCUR = 1 << 2, NVME_CSTS_SHST_CMPLT = 2 << 2, @@ -251,6 +260,7 @@ enum { NVME_CTRL_ONCS_WRITE_UNCORRECTABLE = 1 << 1, NVME_CTRL_ONCS_DSM = 1 << 2, NVME_CTRL_ONCS_WRITE_ZEROES = 1 << 3, + NVME_CTRL_ONCS_TIMESTAMP = 1 << 6, NVME_CTRL_VWC_PRESENT = 1 << 0, NVME_CTRL_OACS_SEC_SUPP = 1 << 0, NVME_CTRL_OACS_DIRECTIVES = 1 << 5, @@ -376,6 +386,13 @@ struct nvme_smart_log { __u8 rsvd216[296]; }; +struct nvme_fw_slot_info_log { + __u8 afi; + __u8 rsvd1[7]; + __le64 frs[7]; + __u8 rsvd64[448]; +}; + enum { NVME_SMART_CRIT_SPARE = 1 << 0, NVME_SMART_CRIT_TEMPERATURE = 1 << 1, @@ -386,6 +403,7 @@ enum { enum { NVME_AER_NOTICE_NS_CHANGED = 0x0002, + NVME_AER_NOTICE_FW_ACT_STARTING = 0x0102, }; struct nvme_lba_range_type { @@ -677,6 +695,7 @@ enum { NVME_FEAT_ASYNC_EVENT = 0x0b, NVME_FEAT_AUTO_PST = 0x0c, NVME_FEAT_HOST_MEM_BUF = 0x0d, + NVME_FEAT_TIMESTAMP = 0x0e, NVME_FEAT_KATO = 0x0f, NVME_FEAT_SW_PROGRESS = 0x80, NVME_FEAT_HOST_ID = 0x81, diff --git a/include/linux/string.h b/include/linux/string.h index a467e617eeb0..0bec4151b0eb 100644 --- a/include/linux/string.h +++ b/include/linux/string.h @@ -200,6 +200,7 @@ static inline const char *kbasename(const char *path) void fortify_panic(const char *name) __noreturn __cold; void __read_overflow(void) __compiletime_error("detected read beyond size of object passed as 1st parameter"); void __read_overflow2(void) __compiletime_error("detected read beyond size of object passed as 2nd parameter"); +void __read_overflow3(void) __compiletime_error("detected read beyond size of object passed as 3rd parameter"); void __write_overflow(void) __compiletime_error("detected write beyond size of object passed as 1st parameter"); #if !defined(__NO_FORTIFY) && defined(__OPTIMIZE__) && defined(CONFIG_FORTIFY_SOURCE) @@ -395,4 +396,33 @@ __FORTIFY_INLINE char *strcpy(char *p, const char *q) #endif +/** + * memcpy_and_pad - Copy one buffer to another with padding + * @dest: Where to copy to + * @dest_len: The destination buffer size + * @src: Where to copy from + * @count: The number of bytes to copy + * @pad: Character to use for padding if space is left in destination. + */ +__FORTIFY_INLINE void memcpy_and_pad(void *dest, size_t dest_len, + const void *src, size_t count, int pad) +{ + size_t dest_size = __builtin_object_size(dest, 0); + size_t src_size = __builtin_object_size(src, 0); + + if (__builtin_constant_p(dest_len) && __builtin_constant_p(count)) { + if (dest_size < dest_len && dest_size < count) + __write_overflow(); + else if (src_size < dest_len && src_size < count) + __read_overflow3(); + } + if (dest_size < dest_len) + fortify_panic(__func__); + if (dest_len > count) { + memcpy(dest, src, count); + memset(dest + count, pad, dest_len - count); + } else + memcpy(dest, src, dest_len); +} + #endif /* _LINUX_STRING_H_ */