diff options
29 files changed, 1110 insertions, 134 deletions
diff --git a/Documentation/fault-injection/nvme-fault-injection.txt b/Documentation/fault-injection/nvme-fault-injection.txt index 8fbf3bf60b62..efcb339a3add 100644 --- a/Documentation/fault-injection/nvme-fault-injection.txt +++ b/Documentation/fault-injection/nvme-fault-injection.txt @@ -114,3 +114,59 @@ R13: ffff88011a3c9680 R14: 0000000000000000 R15: 0000000000000000 cpu_startup_entry+0x6f/0x80 start_secondary+0x187/0x1e0 secondary_startup_64+0xa5/0xb0 + +Example 3: Inject an error into the 10th admin command +------------------------------------------------------ + +echo 100 > /sys/kernel/debug/nvme0/fault_inject/probability +echo 10 > /sys/kernel/debug/nvme0/fault_inject/space +echo 1 > /sys/kernel/debug/nvme0/fault_inject/times +nvme reset /dev/nvme0 + +Expected Result: + +After NVMe controller reset, the reinitialization may or may not succeed. +It depends on which admin command is actually forced to fail. + +Message from dmesg: + +nvme nvme0: resetting controller +FAULT_INJECTION: forcing a failure. +name fault_inject, interval 1, probability 100, space 1, times 1 +CPU: 0 PID: 0 Comm: swapper/0 Not tainted 5.2.0-rc2+ #2 +Hardware name: MSI MS-7A45/B150M MORTAR ARCTIC (MS-7A45), BIOS 1.50 04/25/2017 +Call Trace: + <IRQ> + dump_stack+0x63/0x85 + should_fail+0x14a/0x170 + nvme_should_fail+0x38/0x80 [nvme_core] + nvme_irq+0x129/0x280 [nvme] + ? blk_mq_end_request+0xb3/0x120 + __handle_irq_event_percpu+0x84/0x1a0 + handle_irq_event_percpu+0x32/0x80 + handle_irq_event+0x3b/0x60 + handle_edge_irq+0x7f/0x1a0 + handle_irq+0x20/0x30 + do_IRQ+0x4e/0xe0 + common_interrupt+0xf/0xf + </IRQ> +RIP: 0010:cpuidle_enter_state+0xc5/0x460 +Code: ff e8 8f 5f 86 ff 80 7d c7 00 74 17 9c 58 0f 1f 44 00 00 f6 c4 02 0f 85 69 03 00 00 31 ff e8 62 aa 8c ff fb 66 0f 1f 44 00 00 <45> 85 ed 0f 88 37 03 00 00 4c 8b 45 d0 4c 2b 45 b8 48 ba cf f7 53 +RSP: 0018:ffffffff88c03dd0 EFLAGS: 00000246 ORIG_RAX: ffffffffffffffdc +RAX: ffff9dac25a2ac80 RBX: ffffffff88d53760 RCX: 000000000000001f +RDX: 0000000000000000 RSI: 000000002d958403 RDI: 0000000000000000 +RBP: ffffffff88c03e18 R08: fffffff75e35ffb7 R09: 00000a49a56c0b48 +R10: ffffffff88c03da0 R11: 0000000000001b0c R12: ffff9dac25a34d00 +R13: 0000000000000006 R14: 0000000000000006 R15: ffffffff88d53760 + cpuidle_enter+0x2e/0x40 + call_cpuidle+0x23/0x40 + do_idle+0x201/0x280 + cpu_startup_entry+0x1d/0x20 + rest_init+0xaa/0xb0 + arch_call_rest_init+0xe/0x1b + start_kernel+0x51c/0x53b + x86_64_start_reservations+0x24/0x26 + x86_64_start_kernel+0x74/0x77 + secondary_startup_64+0xa4/0xb0 +nvme nvme0: Could not set queue count (16385) +nvme nvme0: IO queues not created diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 120fb593d1da..b2dd4e391f5c 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -1113,15 +1113,15 @@ static struct nvme_id_ns *nvme_identify_ns(struct nvme_ctrl *ctrl, return id; } -static int nvme_set_features(struct nvme_ctrl *dev, unsigned fid, unsigned dword11, - void *buffer, size_t buflen, u32 *result) +static int nvme_features(struct nvme_ctrl *dev, u8 op, unsigned int fid, + unsigned int dword11, void *buffer, size_t buflen, u32 *result) { struct nvme_command c; union nvme_result res; int ret; memset(&c, 0, sizeof(c)); - c.features.opcode = nvme_admin_set_features; + c.features.opcode = op; c.features.fid = cpu_to_le32(fid); c.features.dword11 = cpu_to_le32(dword11); @@ -1132,6 +1132,24 @@ static int nvme_set_features(struct nvme_ctrl *dev, unsigned fid, unsigned dword return ret; } +int nvme_set_features(struct nvme_ctrl *dev, unsigned int fid, + unsigned int dword11, void *buffer, size_t buflen, + u32 *result) +{ + return nvme_features(dev, nvme_admin_set_features, fid, dword11, buffer, + buflen, result); +} +EXPORT_SYMBOL_GPL(nvme_set_features); + +int nvme_get_features(struct nvme_ctrl *dev, unsigned int fid, + unsigned int dword11, void *buffer, size_t buflen, + u32 *result) +{ + return nvme_features(dev, nvme_admin_get_features, fid, dword11, buffer, + buflen, result); +} +EXPORT_SYMBOL_GPL(nvme_get_features); + int nvme_set_queue_count(struct nvme_ctrl *ctrl, int *count) { u32 q_count = (*count - 1) | ((*count - 1) << 16); @@ -3318,7 +3336,7 @@ static int nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid) device_add_disk(ctrl->device, ns->disk, nvme_ns_id_attr_groups); nvme_mpath_add_disk(ns, id); - nvme_fault_inject_init(ns); + nvme_fault_inject_init(&ns->fault_inject, ns->disk->disk_name); kfree(id); return 0; @@ -3343,7 +3361,15 @@ static void nvme_ns_remove(struct nvme_ns *ns) if (test_and_set_bit(NVME_NS_REMOVING, &ns->flags)) return; - nvme_fault_inject_fini(ns); + nvme_fault_inject_fini(&ns->fault_inject); + + mutex_lock(&ns->ctrl->subsys->lock); + list_del_rcu(&ns->siblings); + mutex_unlock(&ns->ctrl->subsys->lock); + synchronize_rcu(); /* guarantee not available in head->list */ + nvme_mpath_clear_current_path(ns); + synchronize_srcu(&ns->head->srcu); /* wait for concurrent submissions */ + if (ns->disk && ns->disk->flags & GENHD_FL_UP) { del_gendisk(ns->disk); blk_cleanup_queue(ns->queue); @@ -3351,16 +3377,10 @@ static void nvme_ns_remove(struct nvme_ns *ns) blk_integrity_unregister(ns->disk); } - mutex_lock(&ns->ctrl->subsys->lock); - list_del_rcu(&ns->siblings); - nvme_mpath_clear_current_path(ns); - mutex_unlock(&ns->ctrl->subsys->lock); - down_write(&ns->ctrl->namespaces_rwsem); list_del_init(&ns->list); up_write(&ns->ctrl->namespaces_rwsem); - synchronize_srcu(&ns->head->srcu); nvme_mpath_check_last_path(ns); nvme_put_ns(ns); } @@ -3702,6 +3722,7 @@ EXPORT_SYMBOL_GPL(nvme_start_ctrl); void nvme_uninit_ctrl(struct nvme_ctrl *ctrl) { + nvme_fault_inject_fini(&ctrl->fault_inject); dev_pm_qos_hide_latency_tolerance(ctrl->device); cdev_device_del(&ctrl->cdev, ctrl->device); } @@ -3797,6 +3818,8 @@ int nvme_init_ctrl(struct nvme_ctrl *ctrl, struct device *dev, dev_pm_qos_update_user_latency_tolerance(ctrl->device, min(default_ps_max_latency_us, (unsigned long)S32_MAX)); + nvme_fault_inject_init(&ctrl->fault_inject, dev_name(ctrl->device)); + return 0; out_free_name: kfree_const(ctrl->device->kobj.name); diff --git a/drivers/nvme/host/fabrics.c b/drivers/nvme/host/fabrics.c index 5838f7cd53ac..1994d5b42f94 100644 --- a/drivers/nvme/host/fabrics.c +++ b/drivers/nvme/host/fabrics.c @@ -578,7 +578,7 @@ bool __nvmf_check_ready(struct nvme_ctrl *ctrl, struct request *rq, switch (ctrl->state) { case NVME_CTRL_NEW: case NVME_CTRL_CONNECTING: - if (req->cmd->common.opcode == nvme_fabrics_command && + if (nvme_is_fabrics(req->cmd) && req->cmd->fabrics.fctype == nvme_fabrics_type_connect) return true; break; diff --git a/drivers/nvme/host/fault_inject.c b/drivers/nvme/host/fault_inject.c index 4cfd2c9222d4..1352159733b0 100644 --- a/drivers/nvme/host/fault_inject.c +++ b/drivers/nvme/host/fault_inject.c @@ -15,11 +15,10 @@ static DECLARE_FAULT_ATTR(fail_default_attr); static char *fail_request; module_param(fail_request, charp, 0000); -void nvme_fault_inject_init(struct nvme_ns *ns) +void nvme_fault_inject_init(struct nvme_fault_inject *fault_inj, + const char *dev_name) { struct dentry *dir, *parent; - char *name = ns->disk->disk_name; - struct nvme_fault_inject *fault_inj = &ns->fault_inject; struct fault_attr *attr = &fault_inj->attr; /* set default fault injection attribute */ @@ -27,20 +26,20 @@ void nvme_fault_inject_init(struct nvme_ns *ns) setup_fault_attr(&fail_default_attr, fail_request); /* create debugfs directory and attribute */ - parent = debugfs_create_dir(name, NULL); + parent = debugfs_create_dir(dev_name, NULL); if (!parent) { - pr_warn("%s: failed to create debugfs directory\n", name); + pr_warn("%s: failed to create debugfs directory\n", dev_name); return; } *attr = fail_default_attr; dir = fault_create_debugfs_attr("fault_inject", parent, attr); if (IS_ERR(dir)) { - pr_warn("%s: failed to create debugfs attr\n", name); + pr_warn("%s: failed to create debugfs attr\n", dev_name); debugfs_remove_recursive(parent); return; } - ns->fault_inject.parent = parent; + fault_inj->parent = parent; /* create debugfs for status code and dont_retry */ fault_inj->status = NVME_SC_INVALID_OPCODE; @@ -49,29 +48,33 @@ void nvme_fault_inject_init(struct nvme_ns *ns) debugfs_create_bool("dont_retry", 0600, dir, &fault_inj->dont_retry); } -void nvme_fault_inject_fini(struct nvme_ns *ns) +void nvme_fault_inject_fini(struct nvme_fault_inject *fault_inject) { /* remove debugfs directories */ - debugfs_remove_recursive(ns->fault_inject.parent); + debugfs_remove_recursive(fault_inject->parent); } void nvme_should_fail(struct request *req) { struct gendisk *disk = req->rq_disk; - struct nvme_ns *ns = NULL; + struct nvme_fault_inject *fault_inject = NULL; u16 status; - /* - * make sure this request is coming from a valid namespace - */ - if (!disk) - return; + if (disk) { + struct nvme_ns *ns = disk->private_data; + + if (ns) + fault_inject = &ns->fault_inject; + else + WARN_ONCE(1, "No namespace found for request\n"); + } else { + fault_inject = &nvme_req(req)->ctrl->fault_inject; + } - ns = disk->private_data; - if (ns && should_fail(&ns->fault_inject.attr, 1)) { + if (fault_inject && should_fail(&fault_inject->attr, 1)) { /* inject status code and DNR bit */ - status = ns->fault_inject.status; - if (ns->fault_inject.dont_retry) + status = fault_inject->status; + if (fault_inject->dont_retry) status |= NVME_SC_DNR; nvme_req(req)->status = status; } diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c index dd8169bbf0d2..9b497d785ed7 100644 --- a/drivers/nvme/host/fc.c +++ b/drivers/nvme/host/fc.c @@ -2607,6 +2607,12 @@ nvme_fc_create_association(struct nvme_fc_ctrl *ctrl) if (nvme_fc_ctlr_active_on_rport(ctrl)) return -ENOTUNIQ; + dev_info(ctrl->ctrl.device, + "NVME-FC{%d}: create association : host wwpn 0x%016llx " + " rport wwpn 0x%016llx: NQN \"%s\"\n", + ctrl->cnum, ctrl->lport->localport.port_name, + ctrl->rport->remoteport.port_name, ctrl->ctrl.opts->subsysnqn); + /* * Create the admin queue */ diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h index 55553d293a98..ea45d7d393ad 100644 --- a/drivers/nvme/host/nvme.h +++ b/drivers/nvme/host/nvme.h @@ -146,6 +146,15 @@ enum nvme_ctrl_state { NVME_CTRL_DEAD, }; +struct nvme_fault_inject { +#ifdef CONFIG_FAULT_INJECTION_DEBUG_FS + struct fault_attr attr; + struct dentry *parent; + bool dont_retry; /* DNR, do not retry */ + u16 status; /* status code */ +#endif +}; + struct nvme_ctrl { bool comp_seen; enum nvme_ctrl_state state; @@ -247,6 +256,8 @@ struct nvme_ctrl { struct page *discard_page; unsigned long discard_page_busy; + + struct nvme_fault_inject fault_inject; }; enum nvme_iopolicy { @@ -313,15 +324,6 @@ struct nvme_ns_head { #endif }; -#ifdef CONFIG_FAULT_INJECTION_DEBUG_FS -struct nvme_fault_inject { - struct fault_attr attr; - struct dentry *parent; - bool dont_retry; /* DNR, do not retry */ - u16 status; /* status code */ -}; -#endif - struct nvme_ns { struct list_head list; @@ -349,9 +351,7 @@ struct nvme_ns { #define NVME_NS_ANA_PENDING 2 u16 noiob; -#ifdef CONFIG_FAULT_INJECTION_DEBUG_FS struct nvme_fault_inject fault_inject; -#endif }; @@ -372,12 +372,18 @@ struct nvme_ctrl_ops { }; #ifdef CONFIG_FAULT_INJECTION_DEBUG_FS -void nvme_fault_inject_init(struct nvme_ns *ns); -void nvme_fault_inject_fini(struct nvme_ns *ns); +void nvme_fault_inject_init(struct nvme_fault_inject *fault_inj, + const char *dev_name); +void nvme_fault_inject_fini(struct nvme_fault_inject *fault_inject); void nvme_should_fail(struct request *req); #else -static inline void nvme_fault_inject_init(struct nvme_ns *ns) {} -static inline void nvme_fault_inject_fini(struct nvme_ns *ns) {} +static inline void nvme_fault_inject_init(struct nvme_fault_inject *fault_inj, + const char *dev_name) +{ +} +static inline void nvme_fault_inject_fini(struct nvme_fault_inject *fault_inj) +{ +} static inline void nvme_should_fail(struct request *req) {} #endif @@ -459,6 +465,12 @@ int __nvme_submit_sync_cmd(struct request_queue *q, struct nvme_command *cmd, union nvme_result *result, void *buffer, unsigned bufflen, unsigned timeout, int qid, int at_head, blk_mq_req_flags_t flags, bool poll); +int nvme_set_features(struct nvme_ctrl *dev, unsigned int fid, + unsigned int dword11, void *buffer, size_t buflen, + u32 *result); +int nvme_get_features(struct nvme_ctrl *dev, unsigned int fid, + unsigned int dword11, void *buffer, size_t buflen, + u32 *result); int nvme_set_queue_count(struct nvme_ctrl *ctrl, int *count); void nvme_stop_keep_alive(struct nvme_ctrl *ctrl); int nvme_reset_ctrl(struct nvme_ctrl *ctrl); diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 524d6bd6d095..189352081994 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -18,6 +18,7 @@ #include <linux/mutex.h> #include <linux/once.h> #include <linux/pci.h> +#include <linux/suspend.h> #include <linux/t10-pi.h> #include <linux/types.h> #include <linux/io-64-nonatomic-lo-hi.h> @@ -67,20 +68,14 @@ static int io_queue_depth = 1024; module_param_cb(io_queue_depth, &io_queue_depth_ops, &io_queue_depth, 0644); MODULE_PARM_DESC(io_queue_depth, "set io queue depth, should >= 2"); -static int queue_count_set(const char *val, const struct kernel_param *kp); -static const struct kernel_param_ops queue_count_ops = { - .set = queue_count_set, - .get = param_get_int, -}; - static int write_queues; -module_param_cb(write_queues, &queue_count_ops, &write_queues, 0644); +module_param(write_queues, int, 0644); MODULE_PARM_DESC(write_queues, "Number of queues to use for writes. If not set, reads and writes " "will share a queue set."); -static int poll_queues = 0; -module_param_cb(poll_queues, &queue_count_ops, &poll_queues, 0644); +static int poll_queues; +module_param(poll_queues, int, 0644); MODULE_PARM_DESC(poll_queues, "Number of queues to use for polled IO."); struct nvme_dev; @@ -116,6 +111,7 @@ struct nvme_dev { u32 cmbsz; u32 cmbloc; struct nvme_ctrl ctrl; + u32 last_ps; mempool_t *iod_mempool; @@ -144,19 +140,6 @@ static int io_queue_depth_set(const char *val, const struct kernel_param *kp) return param_set_int(val, kp); } -static int queue_count_set(const char *val, const struct kernel_param *kp) -{ - int n, ret; - - ret = kstrtoint(val, 10, &n); - if (ret) - return ret; - if (n > num_possible_cpus()) - n = num_possible_cpus(); - - return param_set_int(val, kp); -} - static inline unsigned int sq_idx(unsigned int qid, u32 stride) { return qid * 2 * stride; @@ -2068,6 +2051,7 @@ static int nvme_setup_irqs(struct nvme_dev *dev, unsigned int nr_io_queues) .priv = dev, }; unsigned int irq_queues, this_p_queues; + unsigned int nr_cpus = num_possible_cpus(); /* * Poll queues don't need interrupts, but we need at least one IO @@ -2078,7 +2062,10 @@ static int nvme_setup_irqs(struct nvme_dev *dev, unsigned int nr_io_queues) this_p_queues = nr_io_queues - 1; irq_queues = 1; } else { - irq_queues = nr_io_queues - this_p_queues + 1; + if (nr_cpus < nr_io_queues - this_p_queues) + irq_queues = nr_cpus + 1; + else + irq_queues = nr_io_queues - this_p_queues + 1; } dev->io_queues[HCTX_TYPE_POLL] = this_p_queues; @@ -2464,10 +2451,8 @@ static void nvme_pci_free_ctrl(struct nvme_ctrl *ctrl) kfree(dev); } -static void nvme_remove_dead_ctrl(struct nvme_dev *dev, int status) +static void nvme_remove_dead_ctrl(struct nvme_dev *dev) { - dev_warn(dev->ctrl.device, "Removing after probe failure status: %d\n", status); - nvme_get_ctrl(&dev->ctrl); nvme_dev_disable(dev, false); nvme_kill_queues(&dev->ctrl); @@ -2480,11 +2465,13 @@ static void nvme_reset_work(struct work_struct *work) struct nvme_dev *dev = container_of(work, struct nvme_dev, ctrl.reset_work); bool was_suspend = !!(dev->ctrl.ctrl_config & NVME_CC_SHN_NORMAL); - int result = -ENODEV; + int result; enum nvme_ctrl_state new_state = NVME_CTRL_LIVE; - if (WARN_ON(dev->ctrl.state != NVME_CTRL_RESETTING)) + if (WARN_ON(dev->ctrl.state != NVME_CTRL_RESETTING)) { + result = -ENODEV; goto out; + } /* * If we're called to reset a live controller first shut it down before @@ -2528,6 +2515,7 @@ static void nvme_reset_work(struct work_struct *work) if (!nvme_change_ctrl_state(&dev->ctrl, NVME_CTRL_CONNECTING)) { dev_warn(dev->ctrl.device, "failed to mark controller CONNECTING\n"); + result = -EBUSY; goto out; } @@ -2588,6 +2576,7 @@ static void nvme_reset_work(struct work_struct *work) if (!nvme_change_ctrl_state(&dev->ctrl, new_state)) { dev_warn(dev->ctrl.device, "failed to mark controller state %d\n", new_state); + result = -ENODEV; goto out; } @@ -2597,7 +2586,10 @@ static void nvme_reset_work(struct work_struct *work) out_unlock: mutex_unlock(&dev->shutdown_lock); out: - nvme_remove_dead_ctrl(dev, result); + if (result) + dev_warn(dev->ctrl.device, + "Removing after probe failure status: %d\n", result); + nvme_remove_dead_ctrl(dev); } static void nvme_remove_dead_ctrl_work(struct work_struct *work) @@ -2835,16 +2827,94 @@ static void nvme_remove(struct pci_dev *pdev) } #ifdef CONFIG_PM_SLEEP +static int nvme_get_power_state(struct nvme_ctrl *ctrl, u32 *ps) +{ + return nvme_get_features(ctrl, NVME_FEAT_POWER_MGMT, 0, NULL, 0, ps); +} + +static int nvme_set_power_state(struct nvme_ctrl *ctrl, u32 ps) +{ + return nvme_set_features(ctrl, NVME_FEAT_POWER_MGMT, ps, NULL, 0, NULL); +} + +static int nvme_resume(struct device *dev) +{ + struct nvme_dev *ndev = pci_get_drvdata(to_pci_dev(dev)); + struct nvme_ctrl *ctrl = &ndev->ctrl; + + if (pm_resume_via_firmware() || !ctrl->npss || + nvme_set_power_state(ctrl, ndev->last_ps) != 0) + nvme_reset_ctrl(ctrl); + return 0; +} + static int nvme_suspend(struct device *dev) { struct pci_dev *pdev = to_pci_dev(dev); struct nvme_dev *ndev = pci_get_drvdata(pdev); + struct nvme_ctrl *ctrl = &ndev->ctrl; + int ret = -EBUSY; + + /* + * The platform does not remove power for a kernel managed suspend so + * use host managed nvme power settings for lowest idle power if + * possible. This should have quicker resume latency than a full device + * shutdown. But if the firmware is involved after the suspend or the + * device does not support any non-default power states, shut down the + * device fully. + */ + if (pm_suspend_via_firmware() || !ctrl->npss) { + nvme_dev_disable(ndev, true); + return 0; + } + + nvme_start_freeze(ctrl); + nvme_wait_freeze(ctrl); + nvme_sync_queues(ctrl); + + if (ctrl->state != NVME_CTRL_LIVE && + ctrl->state != NVME_CTRL_ADMIN_ONLY) + goto unfreeze; + + ndev->last_ps = 0; + ret = nvme_get_power_state(ctrl, &ndev->last_ps); + if (ret < 0) + goto unfreeze; + + ret = nvme_set_power_state(ctrl, ctrl->npss); + if (ret < 0) + goto unfreeze; + + if (ret) { + /* + * Clearing npss forces a controller reset on resume. The + * correct value will be resdicovered then. + */ + nvme_dev_disable(ndev, true); + ctrl->npss = 0; + ret = 0; + goto unfreeze; + } + /* + * A saved state prevents pci pm from generically controlling the + * device's power. If we're using protocol specific settings, we don't + * want pci interfering. + */ + pci_save_state(pdev); +unfreeze: + nvme_unfreeze(ctrl); + return ret; +} + +static int nvme_simple_suspend(struct device *dev) +{ + struct nvme_dev *ndev = pci_get_drvdata(to_pci_dev(dev)); nvme_dev_disable(ndev, true); return 0; } -static int nvme_resume(struct device *dev) +static int nvme_simple_resume(struct device *dev) { struct pci_dev *pdev = to_pci_dev(dev); struct nvme_dev *ndev = pci_get_drvdata(pdev); @@ -2852,9 +2922,16 @@ static int nvme_resume(struct device *dev) nvme_reset_ctrl(&ndev->ctrl); return 0; } -#endif -static SIMPLE_DEV_PM_OPS(nvme_dev_pm_ops, nvme_suspend, nvme_resume); +const struct dev_pm_ops nvme_dev_pm_ops = { + .suspend = nvme_suspend, + .resume = nvme_resume, + .freeze = nvme_simple_suspend, + .thaw = nvme_simple_resume, + .poweroff = nvme_simple_suspend, + .restore = nvme_simple_resume, +}; +#endif /* CONFIG_PM_SLEEP */ static pci_ers_result_t nvme_error_detected(struct pci_dev *pdev, pci_channel_state_t state) @@ -2959,9 +3036,11 @@ static struct pci_driver nvme_driver = { .probe = nvme_probe, .remove = nvme_remove, .shutdown = nvme_shutdown, +#ifdef CONFIG_PM_SLEEP .driver = { .pm = &nvme_dev_pm_ops, }, +#endif .sriov_configure = pci_sriov_configure_simple, .err_handler = &nvme_err_handler, }; diff --git a/drivers/nvme/host/trace.c b/drivers/nvme/host/trace.c index 5f24ea7a28eb..f01ad0fd60bb 100644 --- a/drivers/nvme/host/trace.c +++ b/drivers/nvme/host/trace.c @@ -135,6 +135,69 @@ const char *nvme_trace_parse_nvm_cmd(struct trace_seq *p, } } +static const char *nvme_trace_fabrics_property_set(struct trace_seq *p, u8 *spc) +{ + const char *ret = trace_seq_buffer_ptr(p); + u8 attrib = spc[0]; + u32 ofst = get_unaligned_le32(spc + 4); + u64 value = get_unaligned_le64(spc + 8); + + trace_seq_printf(p, "attrib=%u, ofst=0x%x, value=0x%llx", + attrib, ofst, value); + trace_seq_putc(p, 0); + return ret; +} + +static const char *nvme_trace_fabrics_connect(struct trace_seq *p, u8 *spc) +{ + const char *ret = trace_seq_buffer_ptr(p); + u16 recfmt = get_unaligned_le16(spc); + u16 qid = get_unaligned_le16(spc + 2); + u16 sqsize = get_unaligned_le16(spc + 4); + u8 cattr = spc[6]; + u32 kato = get_unaligned_le32(spc + 8); + + trace_seq_printf(p, "recfmt=%u, qid=%u, sqsize=%u, cattr=%u, kato=%u", + recfmt, qid, sqsize, cattr, kato); + trace_seq_putc(p, 0); + return ret; +} + +static const char *nvme_trace_fabrics_property_get(struct trace_seq *p, u8 *spc) +{ + const char *ret = trace_seq_buffer_ptr(p); + u8 attrib = spc[0]; + u32 ofst = get_unaligned_le32(spc + 4); + + trace_seq_printf(p, "attrib=%u, ofst=0x%x", attrib, ofst); + trace_seq_putc(p, 0); + return ret; +} + +static const char *nvme_trace_fabrics_common(struct trace_seq *p, u8 *spc) +{ + const char *ret = trace_seq_buffer_ptr(p); + + trace_seq_printf(p, "spcecific=%*ph", 24, spc); + trace_seq_putc(p, 0); + return ret; +} + +const char *nvme_trace_parse_fabrics_cmd(struct trace_seq *p, + u8 fctype, u8 *spc) +{ + switch (fctype) { + case nvme_fabrics_type_property_set: + return nvme_trace_fabrics_property_set(p, spc); + case nvme_fabrics_type_connect: + return nvme_trace_fabrics_connect(p, spc); + case nvme_fabrics_type_property_get: + return nvme_trace_fabrics_property_get(p, spc); + default: + return nvme_trace_fabrics_common(p, spc); + } +} + const char *nvme_trace_disk_name(struct trace_seq *p, char *name) { const char *ret = trace_seq_buffer_ptr(p); @@ -145,6 +208,5 @@ const char *nvme_trace_disk_name(struct trace_seq *p, char *name) return ret; } -EXPORT_SYMBOL_GPL(nvme_trace_disk_name); EXPORT_TRACEPOINT_SYMBOL_GPL(nvme_sq); diff --git a/drivers/nvme/host/trace.h b/drivers/nvme/host/trace.h index e71502d141ed..daaf700eae79 100644 --- a/drivers/nvme/host/trace.h +++ b/drivers/nvme/host/trace.h @@ -16,59 +16,19 @@ #include "nvme.h" -#define nvme_admin_opcode_name(opcode) { opcode, #opcode } -#define show_admin_opcode_name(val) \ - __print_symbolic(val, \ - nvme_admin_opcode_name(nvme_admin_delete_sq), \ - nvme_admin_opcode_name(nvme_admin_create_sq), \ - nvme_admin_opcode_name(nvme_admin_get_log_page), \ - nvme_admin_opcode_name(nvme_admin_delete_cq), \ - nvme_admin_opcode_name(nvme_admin_create_cq), \ - nvme_admin_opcode_name(nvme_admin_identify), \ - nvme_admin_opcode_name(nvme_admin_abort_cmd), \ - nvme_admin_opcode_name(nvme_admin_set_features), \ - nvme_admin_opcode_name(nvme_admin_get_features), \ - nvme_admin_opcode_name(nvme_admin_async_event), \ - nvme_admin_opcode_name(nvme_admin_ns_mgmt), \ - nvme_admin_opcode_name(nvme_admin_activate_fw), \ - nvme_admin_opcode_name(nvme_admin_download_fw), \ - nvme_admin_opcode_name(nvme_admin_ns_attach), \ - nvme_admin_opcode_name(nvme_admin_keep_alive), \ - nvme_admin_opcode_name(nvme_admin_directive_send), \ - nvme_admin_opcode_name(nvme_admin_directive_recv), \ - nvme_admin_opcode_name(nvme_admin_dbbuf), \ - nvme_admin_opcode_name(nvme_admin_format_nvm), \ - nvme_admin_opcode_name(nvme_admin_security_send), \ - nvme_admin_opcode_name(nvme_admin_security_recv), \ - nvme_admin_opcode_name(nvme_admin_sanitize_nvm)) - -#define nvme_opcode_name(opcode) { opcode, #opcode } -#define show_nvm_opcode_name(val) \ - __print_symbolic(val, \ - nvme_opcode_name(nvme_cmd_flush), \ - nvme_opcode_name(nvme_cmd_write), \ - nvme_opcode_name(nvme_cmd_read), \ - nvme_opcode_name(nvme_cmd_write_uncor), \ - nvme_opcode_name(nvme_cmd_compare), \ - nvme_opcode_name(nvme_cmd_write_zeroes), \ - nvme_opcode_name(nvme_cmd_dsm), \ - nvme_opcode_name(nvme_cmd_resv_register), \ - nvme_opcode_name(nvme_cmd_resv_report), \ - nvme_opcode_name(nvme_cmd_resv_acquire), \ - nvme_opcode_name(nvme_cmd_resv_release)) - -#define show_opcode_name(qid, opcode) \ - (qid ? show_nvm_opcode_name(opcode) : show_admin_opcode_name(opcode)) - const char *nvme_trace_parse_admin_cmd(struct trace_seq *p, u8 opcode, u8 *cdw10); const char *nvme_trace_parse_nvm_cmd(struct trace_seq *p, u8 opcode, u8 *cdw10); +const char *nvme_trace_parse_fabrics_cmd(struct trace_seq *p, u8 fctype, + u8 *spc); -#define parse_nvme_cmd(qid, opcode, cdw10) \ - (qid ? \ - nvme_trace_parse_nvm_cmd(p, opcode, cdw10) : \ - nvme_trace_parse_admin_cmd(p, opcode, cdw10)) +#define parse_nvme_cmd(qid, opcode, fctype, cdw10) \ + ((opcode) == nvme_fabrics_command ? \ + nvme_trace_parse_fabrics_cmd(p, fctype, cdw10) : \ + ((qid) ? \ + nvme_trace_parse_nvm_cmd(p, opcode, cdw10) : \ + nvme_trace_parse_admin_cmd(p, opcode, cdw10))) const char *nvme_trace_disk_name(struct trace_seq *p, char *name); #define __print_disk_name(name) \ @@ -93,6 +53,7 @@ TRACE_EVENT(nvme_setup_cmd, __field(int, qid) __field(u8, opcode) __field(u8, flags) + __field(u8, fctype) __field(u16, cid) __field(u32, nsid) __field(u64, metadata) @@ -106,6 +67,7 @@ TRACE_EVENT(nvme_setup_cmd, __entry->cid = cmd->common.command_id; __entry->nsid = le32_to_cpu(cmd->common.nsid); __entry->metadata = le64_to_cpu(cmd->common.metadata); + __entry->fctype = cmd->fabrics.fctype; __assign_disk_name(__entry->disk, req->rq_disk); memcpy(__entry->cdw10, &cmd->common.cdw10, sizeof(__entry->cdw10)); @@ -114,8 +76,10 @@ TRACE_EVENT(nvme_setup_cmd, __entry->ctrl_id, __print_disk_name(__entry->disk), __entry->qid, __entry->cid, __entry->nsid, __entry->flags, __entry->metadata, - show_opcode_name(__entry->qid, __entry->opcode), - parse_nvme_cmd(__entry->qid, __entry->opcode, __entry->cdw10)) + show_opcode_name(__entry->qid, __entry->opcode, + __entry->fctype), + parse_nvme_cmd(__entry->qid, __entry->opcode, + __entry->fctype, __entry->cdw10)) ); TRACE_EVENT(nvme_complete_rq, @@ -141,7 +105,7 @@ TRACE_EVENT(nvme_complete_rq, __entry->status = nvme_req(req)->status; __assign_disk_name(__entry->disk, req->rq_disk); ), - TP_printk("nvme%d: %sqid=%d, cmdid=%u, res=%llu, retries=%u, flags=0x%x, status=%u", + TP_printk("nvme%d: %sqid=%d, cmdid=%u, res=%#llx, retries=%u, flags=0x%x, status=%#x", __entry->ctrl_id, __print_disk_name(__entry->disk), __entry->qid, __entry->cid, __entry->result, __entry->retries, __entry->flags, __entry->status) diff --git a/drivers/nvme/target/Makefile b/drivers/nvme/target/Makefile index 8c3ad0fb6860..2b33836f3d3e 100644 --- a/drivers/nvme/target/Makefile +++ b/drivers/nvme/target/Makefile @@ -1,5 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 +ccflags-y += -I$(src) + obj-$(CONFIG_NVME_TARGET) += nvmet.o obj-$(CONFIG_NVME_TARGET_LOOP) += nvme-loop.o obj-$(CONFIG_NVME_TARGET_RDMA) += nvmet-rdma.o @@ -14,3 +16,4 @@ nvmet-rdma-y += rdma.o nvmet-fc-y += fc.o nvme-fcloop-y += fcloop.o nvmet-tcp-y += tcp.o +nvmet-$(CONFIG_TRACING) += trace.o diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c index 7734a6acff85..dad0243c7c96 100644 --- a/drivers/nvme/target/core.c +++ b/drivers/nvme/target/core.c @@ -10,6 +10,9 @@ #include <linux/pci-p2pdma.h> #include <linux/scatterlist.h> +#define CREATE_TRACE_POINTS +#include "trace.h" + #include "nvmet.h" struct workqueue_struct *buffered_io_wq; @@ -311,6 +314,7 @@ int nvmet_enable_port(struct nvmet_port *port) port->inline_data_size = 0; port->enabled = true; + port->tr_ops = ops; return 0; } @@ -321,6 +325,7 @@ void nvmet_disable_port(struct nvmet_port *port) lockdep_assert_held(&nvmet_config_sem); port->enabled = false; + port->tr_ops = NULL; ops = nvmet_transports[port->disc_addr.trtype]; ops->remove_port(port); @@ -689,6 +694,9 @@ static void __nvmet_req_complete(struct nvmet_req *req, u16 status) if (unlikely(status)) nvmet_set_error(req, status); + + trace_nvmet_req_complete(req); + if (req->ns) nvmet_put_namespace(req->ns); req->ops->queue_response(req); @@ -848,6 +856,8 @@ bool nvmet_req_init(struct nvmet_req *req, struct nvmet_cq *cq, req->error_loc = NVMET_NO_ERROR_LOC; req->error_slba = 0; + trace_nvmet_req_init(req, req->cmd); + /* no support for fused commands yet */ if (unlikely(flags & (NVME_CMD_FUSE_FIRST | NVME_CMD_FUSE_SECOND))) { req->error_loc = offsetof(struct nvme_common_command, flags); @@ -871,7 +881,7 @@ bool nvmet_req_init(struct nvmet_req *req, struct nvmet_cq *cq, status = nvmet_parse_connect_cmd(req); else if (likely(req->sq->qid != 0)) status = nvmet_parse_io_cmd(req); - else if (req->cmd->common.opcode == nvme_fabrics_command) + else if (nvme_is_fabrics(req->cmd)) status = nvmet_parse_fabrics_cmd(req); else if (req->sq->ctrl->subsys->type == NVME_NQN_DISC) status = nvmet_parse_discovery_cmd(req); diff --git a/drivers/nvme/target/discovery.c b/drivers/nvme/target/discovery.c index 5baf269f3f8a..8efca26b4776 100644 --- a/drivers/nvme/target/discovery.c +++ b/drivers/nvme/target/discovery.c @@ -41,6 +41,10 @@ void nvmet_port_disc_changed(struct nvmet_port *port, __nvmet_disc_changed(port, ctrl); } mutex_unlock(&nvmet_disc_subsys->lock); + + /* If transport can signal change, notify transport */ + if (port->tr_ops && port->tr_ops->discovery_chg) + port->tr_ops->discovery_chg(port); } static void __nvmet_subsys_disc_changed(struct nvmet_port *port, diff --git a/drivers/nvme/target/fabrics-cmd.c b/drivers/nvme/target/fabrics-cmd.c index 3b9f79aba98f..d16b55ffe79f 100644 --- a/drivers/nvme/target/fabrics-cmd.c +++ b/drivers/nvme/target/fabrics-cmd.c @@ -268,7 +268,7 @@ u16 nvmet_parse_connect_cmd(struct nvmet_req *req) { struct nvme_command *cmd = req->cmd; - if (cmd->common.opcode != nvme_fabrics_command) { + if (!nvme_is_fabrics(cmd)) { pr_err("invalid command 0x%x on unconnected queue.\n", cmd->fabrics.opcode); req->error_loc = offsetof(struct nvme_common_command, opcode); diff --git a/drivers/nvme/target/fc.c b/drivers/nvme/target/fc.c index 508661af0f50..ce8d819f86cc 100644 --- a/drivers/nvme/target/fc.c +++ b/drivers/nvme/target/fc.c @@ -1806,7 +1806,7 @@ nvmet_fc_prep_fcp_rsp(struct nvmet_fc_tgtport *tgtport, */ rspcnt = atomic_inc_return(&fod->queue->zrspcnt); if (!(rspcnt % fod->queue->ersp_ratio) || - sqe->opcode == nvme_fabrics_command || + nvme_is_fabrics((struct nvme_command *) sqe) || xfr_length != fod->req.transfer_len || (le16_to_cpu(cqe->status) & 0xFFFE) || cqewd[0] || cqewd[1] || (sqe->flags & (NVME_CMD_FUSE_FIRST | NVME_CMD_FUSE_SECOND)) || @@ -2549,6 +2549,16 @@ nvmet_fc_remove_port(struct nvmet_port *port) kfree(pe); } +static void +nvmet_fc_discovery_chg(struct nvmet_port *port) +{ + struct nvmet_fc_port_entry *pe = port->priv; + struct nvmet_fc_tgtport *tgtport = pe->tgtport; + + if (tgtport && tgtport->ops->discovery_event) + tgtport->ops->discovery_event(&tgtport->fc_target_port); +} + static const struct nvmet_fabrics_ops nvmet_fc_tgt_fcp_ops = { .owner = THIS_MODULE, .type = NVMF_TRTYPE_FC, @@ -2557,6 +2567,7 @@ static const struct nvmet_fabrics_ops nvmet_fc_tgt_fcp_ops = { .remove_port = nvmet_fc_remove_port, .queue_response = nvmet_fc_fcp_nvme_cmd_done, .delete_ctrl = nvmet_fc_delete_ctrl, + .discovery_chg = nvmet_fc_discovery_chg, }; static int __init nvmet_fc_init_module(void) diff --git a/drivers/nvme/target/fcloop.c b/drivers/nvme/target/fcloop.c index 381b5a90c48b..b8c1cc54a0db 100644 --- a/drivers/nvme/target/fcloop.c +++ b/drivers/nvme/target/fcloop.c @@ -231,6 +231,11 @@ struct fcloop_lsreq { int status; }; +struct fcloop_rscn { + struct fcloop_tport *tport; + struct work_struct work; +}; + enum { INI_IO_START = 0, INI_IO_ACTIVE = 1, @@ -348,6 +353,37 @@ fcloop_xmt_ls_rsp(struct nvmet_fc_target_port *tport, return 0; } +/* + * Simulate reception of RSCN and converting it to a initiator transport + * call to rescan a remote port. + */ +static void +fcloop_tgt_rscn_work(struct work_struct *work) +{ + struct fcloop_rscn *tgt_rscn = + container_of(work, struct fcloop_rscn, work); + struct fcloop_tport *tport = tgt_rscn->tport; + + if (tport->remoteport) + nvme_fc_rescan_remoteport(tport->remoteport); + kfree(tgt_rscn); +} + +static void +fcloop_tgt_discovery_evt(struct nvmet_fc_target_port *tgtport) +{ + struct fcloop_rscn *tgt_rscn; + + tgt_rscn = kzalloc(sizeof(*tgt_rscn), GFP_KERNEL); + if (!tgt_rscn) + return; + + tgt_rscn->tport = tgtport->private; + INIT_WORK(&tgt_rscn->work, fcloop_tgt_rscn_work); + + schedule_work(&tgt_rscn->work); +} + static void fcloop_tfcp_req_free(struct kref *ref) { @@ -839,6 +875,7 @@ static struct nvmet_fc_target_template tgttemplate = { .fcp_op = fcloop_fcp_op, .fcp_abort = fcloop_tgt_fcp_abort, .fcp_req_release = fcloop_fcp_req_release, + .discovery_event = fcloop_tgt_discovery_evt, .max_hw_queues = FCLOOP_HW_QUEUES, .max_sgl_segments = FCLOOP_SGL_SEGS, .max_dif_sgl_segments = FCLOOP_SGL_SEGS, diff --git a/drivers/nvme/target/nvmet.h b/drivers/nvme/target/nvmet.h index c25d88fc9dec..dc270944bb25 100644 --- a/drivers/nvme/target/nvmet.h +++ b/drivers/nvme/target/nvmet.h @@ -140,6 +140,7 @@ struct nvmet_port { void *priv; bool enabled; int inline_data_size; + const struct nvmet_fabrics_ops *tr_ops; }; static inline struct nvmet_port *to_nvmet_port(struct config_item *item) @@ -277,6 +278,7 @@ struct nvmet_fabrics_ops { void (*disc_traddr)(struct nvmet_req *req, struct nvmet_port *port, char *traddr); u16 (*install_queue)(struct nvmet_sq *nvme_sq); + void (*discovery_chg)(struct nvmet_port *port); }; #define NVMET_MAX_INLINE_BIOVEC 8 diff --git a/drivers/nvme/target/trace.c b/drivers/nvme/target/trace.c new file mode 100644 index 000000000000..cdcdd14c6408 --- /dev/null +++ b/drivers/nvme/target/trace.c @@ -0,0 +1,201 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * NVM Express target device driver tracepoints + * Copyright (c) 2018 Johannes Thumshirn, SUSE Linux GmbH + */ + +#include <asm/unaligned.h> +#include "trace.h" + +static const char *nvmet_trace_admin_identify(struct trace_seq *p, u8 *cdw10) +{ + const char *ret = trace_seq_buffer_ptr(p); + u8 cns = cdw10[0]; + u16 ctrlid = get_unaligned_le16(cdw10 + 2); + + trace_seq_printf(p, "cns=%u, ctrlid=%u", cns, ctrlid); + trace_seq_putc(p, 0); + + return ret; +} + +static const char *nvmet_trace_admin_get_features(struct trace_seq *p, + u8 *cdw10) +{ + const char *ret = trace_seq_buffer_ptr(p); + u8 fid = cdw10[0]; + u8 sel = cdw10[1] & 0x7; + u32 cdw11 = get_unaligned_le32(cdw10 + 4); + + trace_seq_printf(p, "fid=0x%x sel=0x%x cdw11=0x%x", fid, sel, cdw11); + trace_seq_putc(p, 0); + + return ret; +} + +static const char *nvmet_trace_read_write(struct trace_seq *p, u8 *cdw10) +{ + const char *ret = trace_seq_buffer_ptr(p); + u64 slba = get_unaligned_le64(cdw10); + u16 length = get_unaligned_le16(cdw10 + 8); + u16 control = get_unaligned_le16(cdw10 + 10); + u32 dsmgmt = get_unaligned_le32(cdw10 + 12); + u32 reftag = get_unaligned_le32(cdw10 + 16); + + trace_seq_printf(p, + "slba=%llu, len=%u, ctrl=0x%x, dsmgmt=%u, reftag=%u", + slba, length, control, dsmgmt, reftag); + trace_seq_putc(p, 0); + + return ret; +} + +static const char *nvmet_trace_dsm(struct trace_seq *p, u8 *cdw10) +{ + const char *ret = trace_seq_buffer_ptr(p); + + trace_seq_printf(p, "nr=%u, attributes=%u", + get_unaligned_le32(cdw10), + get_unaligned_le32(cdw10 + 4)); + trace_seq_putc(p, 0); + + return ret; +} + +static const char *nvmet_trace_common(struct trace_seq *p, u8 *cdw10) +{ + const char *ret = trace_seq_buffer_ptr(p); + + trace_seq_printf(p, "cdw10=%*ph", 24, cdw10); + trace_seq_putc(p, 0); + + return ret; +} + +const char *nvmet_trace_parse_admin_cmd(struct trace_seq *p, + u8 opcode, u8 *cdw10) +{ + switch (opcode) { + case nvme_admin_identify: + return nvmet_trace_admin_identify(p, cdw10); + case nvme_admin_get_features: + return nvmet_trace_admin_get_features(p, cdw10); + default: + return nvmet_trace_common(p, cdw10); + } +} + +const char *nvmet_trace_parse_nvm_cmd(struct trace_seq *p, + u8 opcode, u8 *cdw10) +{ + switch (opcode) { + case nvme_cmd_read: + case nvme_cmd_write: + case nvme_cmd_write_zeroes: + return nvmet_trace_read_write(p, cdw10); + case nvme_cmd_dsm: + return nvmet_trace_dsm(p, cdw10); + default: + return nvmet_trace_common(p, cdw10); + } +} + +static const char *nvmet_trace_fabrics_property_set(struct trace_seq *p, + u8 *spc) +{ + const char *ret = trace_seq_buffer_ptr(p); + u8 attrib = spc[0]; + u32 ofst = get_unaligned_le32(spc + 4); + u64 value = get_unaligned_le64(spc + 8); + + trace_seq_printf(p, "attrib=%u, ofst=0x%x, value=0x%llx", + attrib, ofst, value); + trace_seq_putc(p, 0); + return ret; +} + +static const char *nvmet_trace_fabrics_connect(struct trace_seq *p, + u8 *spc) +{ + const char *ret = trace_seq_buffer_ptr(p); + u16 recfmt = get_unaligned_le16(spc); + u16 qid = get_unaligned_le16(spc + 2); + u16 sqsize = get_unaligned_le16(spc + 4); + u8 cattr = spc[6]; + u32 kato = get_unaligned_le32(spc + 8); + + trace_seq_printf(p, "recfmt=%u, qid=%u, sqsize=%u, cattr=%u, kato=%u", + recfmt, qid, sqsize, cattr, kato); + trace_seq_putc(p, 0); + return ret; +} + +static const char *nvmet_trace_fabrics_property_get(struct trace_seq *p, + u8 *spc) +{ + const char *ret = trace_seq_buffer_ptr(p); + u8 attrib = spc[0]; + u32 ofst = get_unaligned_le32(spc + 4); + + trace_seq_printf(p, "attrib=%u, ofst=0x%x", attrib, ofst); + trace_seq_putc(p, 0); + return ret; +} + +static const char *nvmet_trace_fabrics_common(struct trace_seq *p, u8 *spc) +{ + const char *ret = trace_seq_buffer_ptr(p); + + trace_seq_printf(p, "spcecific=%*ph", 24, spc); + trace_seq_putc(p, 0); + return ret; +} + +const char *nvmet_trace_parse_fabrics_cmd(struct trace_seq *p, + u8 fctype, u8 *spc) +{ + switch (fctype) { + case nvme_fabrics_type_property_set: + return nvmet_trace_fabrics_property_set(p, spc); + case nvme_fabrics_type_connect: + return nvmet_trace_fabrics_connect(p, spc); + case nvme_fabrics_type_property_get: + return nvmet_trace_fabrics_property_get(p, spc); + default: + return nvmet_trace_fabrics_common(p, spc); + } +} + +const char *nvmet_trace_disk_name(struct trace_seq *p, char *name) +{ + const char *ret = trace_seq_buffer_ptr(p); + + if (*name) + trace_seq_printf(p, "disk=%s, ", name); + trace_seq_putc(p, 0); + + return ret; +} + +const char *nvmet_trace_ctrl_name(struct trace_seq *p, struct nvmet_ctrl *ctrl) +{ + const char *ret = trace_seq_buffer_ptr(p); + + /* + * XXX: We don't know the controller instance before executing the + * connect command itself because the connect command for the admin + * queue will not provide the cntlid which will be allocated in this + * command. In case of io queues, the controller instance will be + * mapped by the extra data of the connect command. + * If we can know the extra data of the connect command in this stage, + * we can update this print statement later. + */ + if (ctrl) + trace_seq_printf(p, "%d", ctrl->cntlid); + else + trace_seq_printf(p, "_"); + trace_seq_putc(p, 0); + + return ret; +} + diff --git a/drivers/nvme/target/trace.h b/drivers/nvme/target/trace.h new file mode 100644 index 000000000000..e645caa882dd --- /dev/null +++ b/drivers/nvme/target/trace.h @@ -0,0 +1,141 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * NVM Express target device driver tracepoints + * Copyright (c) 2018 Johannes Thumshirn, SUSE Linux GmbH + * + * This is entirely based on drivers/nvme/host/trace.h + */ + +#undef TRACE_SYSTEM +#define TRACE_SYSTEM nvmet + +#if !defined(_TRACE_NVMET_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_NVMET_H + +#include <linux/nvme.h> +#include <linux/tracepoint.h> +#include <linux/trace_seq.h> + +#include "nvmet.h" + +const char *nvmet_trace_parse_admin_cmd(struct trace_seq *p, u8 opcode, + u8 *cdw10); +const char *nvmet_trace_parse_nvm_cmd(struct trace_seq *p, u8 opcode, + u8 *cdw10); +const char *nvmet_trace_parse_fabrics_cmd(struct trace_seq *p, u8 fctype, + u8 *spc); + +#define parse_nvme_cmd(qid, opcode, fctype, cdw10) \ + ((opcode) == nvme_fabrics_command ? \ + nvmet_trace_parse_fabrics_cmd(p, fctype, cdw10) : \ + (qid ? \ + nvmet_trace_parse_nvm_cmd(p, opcode, cdw10) : \ + nvmet_trace_parse_admin_cmd(p, opcode, cdw10))) + +const char *nvmet_trace_ctrl_name(struct trace_seq *p, struct nvmet_ctrl *ctrl); +#define __print_ctrl_name(ctrl) \ + nvmet_trace_ctrl_name(p, ctrl) + +const char *nvmet_trace_disk_name(struct trace_seq *p, char *name); +#define __print_disk_name(name) \ + nvmet_trace_disk_name(p, name) + +#ifndef TRACE_HEADER_MULTI_READ +static inline struct nvmet_ctrl *nvmet_req_to_ctrl(struct nvmet_req *req) +{ + return req->sq->ctrl; +} + +static inline void __assign_disk_name(char *name, struct nvmet_req *req, + bool init) +{ + struct nvmet_ctrl *ctrl = nvmet_req_to_ctrl(req); + struct nvmet_ns *ns; + + if ((init && req->sq->qid) || (!init && req->cq->qid)) { + ns = nvmet_find_namespace(ctrl, req->cmd->rw.nsid); + strncpy(name, ns->device_path, DISK_NAME_LEN); + return; + } + + memset(name, 0, DISK_NAME_LEN); +} +#endif + +TRACE_EVENT(nvmet_req_init, + TP_PROTO(struct nvmet_req *req, struct nvme_command *cmd), + TP_ARGS(req, cmd), + TP_STRUCT__entry( + __field(struct nvme_command *, cmd) + __field(struct nvmet_ctrl *, ctrl) + __array(char, disk, DISK_NAME_LEN) + __field(int, qid) + __field(u16, cid) + __field(u8, opcode) + __field(u8, fctype) + __field(u8, flags) + __field(u32, nsid) + __field(u64, metadata) + __array(u8, cdw10, 24) + ), + TP_fast_assign( + __entry->cmd = cmd; + __entry->ctrl = nvmet_req_to_ctrl(req); + __assign_disk_name(__entry->disk, req, true); + __entry->qid = req->sq->qid; + __entry->cid = cmd->common.command_id; + __entry->opcode = cmd->common.opcode; + __entry->fctype = cmd->fabrics.fctype; + __entry->flags = cmd->common.flags; + __entry->nsid = le32_to_cpu(cmd->common.nsid); + __entry->metadata = le64_to_cpu(cmd->common.metadata); + memcpy(__entry->cdw10, &cmd->common.cdw10, + sizeof(__entry->cdw10)); + ), + TP_printk("nvmet%s: %sqid=%d, cmdid=%u, nsid=%u, flags=%#x, " + "meta=%#llx, cmd=(%s, %s)", + __print_ctrl_name(__entry->ctrl), + __print_disk_name(__entry->disk), + __entry->qid, __entry->cid, __entry->nsid, + __entry->flags, __entry->metadata, + show_opcode_name(__entry->qid, __entry->opcode, + __entry->fctype), + parse_nvme_cmd(__entry->qid, __entry->opcode, + __entry->fctype, __entry->cdw10)) +); + +TRACE_EVENT(nvmet_req_complete, + TP_PROTO(struct nvmet_req *req), + TP_ARGS(req), + TP_STRUCT__entry( + __field(struct nvmet_ctrl *, ctrl) + __array(char, disk, DISK_NAME_LEN) + __field(int, qid) + __field(int, cid) + __field(u64, result) + __field(u16, status) + ), + TP_fast_assign( + __entry->ctrl = nvmet_req_to_ctrl(req); + __entry->qid = req->cq->qid; + __entry->cid = req->cqe->command_id; + __entry->result = le64_to_cpu(req->cqe->result.u64); + __entry->status = le16_to_cpu(req->cqe->status) >> 1; + __assign_disk_name(__entry->disk, req, false); + ), + TP_printk("nvmet%s: %sqid=%d, cmdid=%u, res=%#llx, status=%#x", + __print_ctrl_name(__entry->ctrl), + __print_disk_name(__entry->disk), + __entry->qid, __entry->cid, __entry->result, __entry->status) + +); + +#endif /* _TRACE_NVMET_H */ + +#undef TRACE_INCLUDE_PATH +#define TRACE_INCLUDE_PATH . +#undef TRACE_INCLUDE_FILE +#define TRACE_INCLUDE_FILE trace + +/* This part must be outside protection */ +#include <trace/define_trace.h> diff --git a/drivers/scsi/lpfc/lpfc.h b/drivers/scsi/lpfc/lpfc.h index aafcffaa25f7..2c3bb8a966e5 100644 --- a/drivers/scsi/lpfc/lpfc.h +++ b/drivers/scsi/lpfc/lpfc.h @@ -274,6 +274,7 @@ struct lpfc_stats { uint32_t elsXmitADISC; uint32_t elsXmitLOGO; uint32_t elsXmitSCR; + uint32_t elsXmitRSCN; uint32_t elsXmitRNID; uint32_t elsXmitFARP; uint32_t elsXmitFARPR; @@ -819,6 +820,7 @@ struct lpfc_hba { uint32_t cfg_use_msi; uint32_t cfg_auto_imax; uint32_t cfg_fcp_imax; + uint32_t cfg_force_rscn; uint32_t cfg_cq_poll_threshold; uint32_t cfg_cq_max_proc_limit; uint32_t cfg_fcp_cpu_map; diff --git a/drivers/scsi/lpfc/lpfc_attr.c b/drivers/scsi/lpfc/lpfc_attr.c index d4c65e2109e2..2bd1e014103b 100644 --- a/drivers/scsi/lpfc/lpfc_attr.c +++ b/drivers/scsi/lpfc/lpfc_attr.c @@ -4959,6 +4959,64 @@ static DEVICE_ATTR(lpfc_req_fw_upgrade, S_IRUGO | S_IWUSR, lpfc_request_firmware_upgrade_store); /** + * lpfc_force_rscn_store + * + * @dev: class device that is converted into a Scsi_host. + * @attr: device attribute, not used. + * @buf: unused string + * @count: unused variable. + * + * Description: + * Force the switch to send a RSCN to all other NPorts in our zone + * If we are direct connect pt2pt, build the RSCN command ourself + * and send to the other NPort. Not supported for private loop. + * + * Returns: + * 0 - on success + * -EIO - if command is not sent + **/ +static ssize_t +lpfc_force_rscn_store(struct device *dev, struct device_attribute *attr, + const char *buf, size_t count) +{ + struct Scsi_Host *shost = class_to_shost(dev); + struct lpfc_vport *vport = (struct lpfc_vport *)shost->hostdata; + int i; + + i = lpfc_issue_els_rscn(vport, 0); + if (i) + return -EIO; + return strlen(buf); +} + +/* + * lpfc_force_rscn: Force an RSCN to be sent to all remote NPorts + * connected to the HBA. + * + * Value range is any ascii value + */ +static int lpfc_force_rscn; +module_param(lpfc_force_rscn, int, 0644); +MODULE_PARM_DESC(lpfc_force_rscn, + "Force an RSCN to be sent to all remote NPorts"); +lpfc_param_show(force_rscn) + +/** + * lpfc_force_rscn_init - Force an RSCN to be sent to all remote NPorts + * @phba: lpfc_hba pointer. + * @val: unused value. + * + * Returns: + * zero if val saved. + **/ +static int +lpfc_force_rscn_init(struct lpfc_hba *phba, int val) +{ + return 0; +} +static DEVICE_ATTR_RW(lpfc_force_rscn); + +/** * lpfc_fcp_imax_store * * @dev: class device that is converted into a Scsi_host. @@ -5958,6 +6016,7 @@ struct device_attribute *lpfc_hba_attrs[] = { &dev_attr_lpfc_nvme_oas, &dev_attr_lpfc_nvme_embed_cmd, &dev_attr_lpfc_fcp_imax, + &dev_attr_lpfc_force_rscn, &dev_attr_lpfc_cq_poll_threshold, &dev_attr_lpfc_cq_max_proc_limit, &dev_attr_lpfc_fcp_cpu_map, @@ -7005,6 +7064,7 @@ lpfc_get_cfgparam(struct lpfc_hba *phba) lpfc_nvme_oas_init(phba, lpfc_nvme_oas); lpfc_nvme_embed_cmd_init(phba, lpfc_nvme_embed_cmd); lpfc_fcp_imax_init(phba, lpfc_fcp_imax); + lpfc_force_rscn_init(phba, lpfc_force_rscn); lpfc_cq_poll_threshold_init(phba, lpfc_cq_poll_threshold); lpfc_cq_max_proc_limit_init(phba, lpfc_cq_max_proc_limit); lpfc_fcp_cpu_map_init(phba, lpfc_fcp_cpu_map); diff --git a/drivers/scsi/lpfc/lpfc_crtn.h b/drivers/scsi/lpfc/lpfc_crtn.h index e0b14d791b8c..866374801140 100644 --- a/drivers/scsi/lpfc/lpfc_crtn.h +++ b/drivers/scsi/lpfc/lpfc_crtn.h @@ -141,6 +141,7 @@ int lpfc_issue_els_adisc(struct lpfc_vport *, struct lpfc_nodelist *, uint8_t); int lpfc_issue_els_logo(struct lpfc_vport *, struct lpfc_nodelist *, uint8_t); int lpfc_issue_els_npiv_logo(struct lpfc_vport *, struct lpfc_nodelist *); int lpfc_issue_els_scr(struct lpfc_vport *, uint32_t, uint8_t); +int lpfc_issue_els_rscn(struct lpfc_vport *vport, uint8_t retry); int lpfc_issue_fabric_reglogin(struct lpfc_vport *); int lpfc_els_free_iocb(struct lpfc_hba *, struct lpfc_iocbq *); int lpfc_ct_free_iocb(struct lpfc_hba *, struct lpfc_iocbq *); @@ -355,6 +356,7 @@ void lpfc_mbox_timeout_handler(struct lpfc_hba *); struct lpfc_nodelist *lpfc_findnode_did(struct lpfc_vport *, uint32_t); struct lpfc_nodelist *lpfc_findnode_wwpn(struct lpfc_vport *, struct lpfc_name *); +struct lpfc_nodelist *lpfc_findnode_mapped(struct lpfc_vport *vport); int lpfc_sli_issue_mbox_wait(struct lpfc_hba *, LPFC_MBOXQ_t *, uint32_t); @@ -555,6 +557,8 @@ void lpfc_ras_stop_fwlog(struct lpfc_hba *phba); int lpfc_check_fwlog_support(struct lpfc_hba *phba); /* NVME interfaces. */ +void lpfc_nvme_rescan_port(struct lpfc_vport *vport, + struct lpfc_nodelist *ndlp); void lpfc_nvme_unregister_port(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp); int lpfc_nvme_register_port(struct lpfc_vport *vport, diff --git a/drivers/scsi/lpfc/lpfc_els.c b/drivers/scsi/lpfc/lpfc_els.c index 5ac4f8d76b91..968ed0fd37f7 100644 --- a/drivers/scsi/lpfc/lpfc_els.c +++ b/drivers/scsi/lpfc/lpfc_els.c @@ -30,6 +30,8 @@ #include <scsi/scsi_device.h> #include <scsi/scsi_host.h> #include <scsi/scsi_transport_fc.h> +#include <uapi/scsi/fc/fc_fs.h> +#include <uapi/scsi/fc/fc_els.h> #include "lpfc_hw4.h" #include "lpfc_hw.h" @@ -3079,6 +3081,116 @@ lpfc_issue_els_scr(struct lpfc_vport *vport, uint32_t nportid, uint8_t retry) } /** + * lpfc_issue_els_rscn - Issue an RSCN to the Fabric Controller (Fabric) + * or the other nport (pt2pt). + * @vport: pointer to a host virtual N_Port data structure. + * @retry: number of retries to the command IOCB. + * + * This routine issues a RSCN to the Fabric Controller (DID 0xFFFFFD) + * when connected to a fabric, or to the remote port when connected + * in point-to-point mode. When sent to the Fabric Controller, it will + * replay the RSCN to registered recipients. + * + * Note that, in lpfc_prep_els_iocb() routine, the reference count of ndlp + * will be incremented by 1 for holding the ndlp and the reference to ndlp + * will be stored into the context1 field of the IOCB for the completion + * callback function to the RSCN ELS command. + * + * Return code + * 0 - Successfully issued RSCN command + * 1 - Failed to issue RSCN command + **/ +int +lpfc_issue_els_rscn(struct lpfc_vport *vport, uint8_t retry) +{ + struct lpfc_hba *phba = vport->phba; + struct lpfc_iocbq *elsiocb; + struct lpfc_nodelist *ndlp; + struct { + struct fc_els_rscn rscn; + struct fc_els_rscn_page portid; + } *event; + uint32_t nportid; + uint16_t cmdsize = sizeof(*event); + + /* Not supported for private loop */ + if (phba->fc_topology == LPFC_TOPOLOGY_LOOP && + !(vport->fc_flag & FC_PUBLIC_LOOP)) + return 1; + + if (vport->fc_flag & FC_PT2PT) { + /* find any mapped nport - that would be the other nport */ + ndlp = lpfc_findnode_mapped(vport); + if (!ndlp) + return 1; + } else { + nportid = FC_FID_FCTRL; + /* find the fabric controller node */ + ndlp = lpfc_findnode_did(vport, nportid); + if (!ndlp) { + /* if one didn't exist, make one */ + ndlp = lpfc_nlp_init(vport, nportid); + if (!ndlp) + return 1; + lpfc_enqueue_node(vport, ndlp); + } else if (!NLP_CHK_NODE_ACT(ndlp)) { + ndlp = lpfc_enable_node(vport, ndlp, + NLP_STE_UNUSED_NODE); + if (!ndlp) + return 1; + } + } + + elsiocb = lpfc_prep_els_iocb(vport, 1, cmdsize, retry, ndlp, + ndlp->nlp_DID, ELS_CMD_RSCN_XMT); + + if (!elsiocb) { + /* This will trigger the release of the node just + * allocated + */ + lpfc_nlp_put(ndlp); + return 1; + } + + event = ((struct lpfc_dmabuf *)elsiocb->context2)->virt; + + event->rscn.rscn_cmd = ELS_RSCN; + event->rscn.rscn_page_len = sizeof(struct fc_els_rscn_page); + event->rscn.rscn_plen = cpu_to_be16(cmdsize); + + nportid = vport->fc_myDID; + /* appears that page flags must be 0 for fabric to broadcast RSCN */ + event->portid.rscn_page_flags = 0; + event->portid.rscn_fid[0] = (nportid & 0x00FF0000) >> 16; + event->portid.rscn_fid[1] = (nportid & 0x0000FF00) >> 8; + event->portid.rscn_fid[2] = nportid & 0x000000FF; + + lpfc_debugfs_disc_trc(vport, LPFC_DISC_TRC_ELS_CMD, + "Issue RSCN: did:x%x", + ndlp->nlp_DID, 0, 0); + + phba->fc_stat.elsXmitRSCN++; + elsiocb->iocb_cmpl = lpfc_cmpl_els_cmd; + if (lpfc_sli_issue_iocb(phba, LPFC_ELS_RING, elsiocb, 0) == + IOCB_ERROR) { + /* The additional lpfc_nlp_put will cause the following + * lpfc_els_free_iocb routine to trigger the rlease of + * the node. + */ + lpfc_nlp_put(ndlp); + lpfc_els_free_iocb(phba, elsiocb); + return 1; + } + /* This will cause the callback-function lpfc_cmpl_els_cmd to + * trigger the release of node. + */ + if (!(vport->fc_flag & FC_PT2PT)) + lpfc_nlp_put(ndlp); + + return 0; +} + +/** * lpfc_issue_els_farpr - Issue a farp to an node on a vport * @vport: pointer to a host virtual N_Port data structure. * @nportid: N_Port identifier to the remote node. @@ -6214,6 +6326,8 @@ lpfc_rscn_recovery_check(struct lpfc_vport *vport) continue; } + if (ndlp->nlp_fc4_type & NLP_FC4_NVME) + lpfc_nvme_rescan_port(vport, ndlp); lpfc_disc_state_machine(vport, ndlp, NULL, NLP_EVT_DEVICE_RECOVERY); @@ -6318,6 +6432,19 @@ lpfc_els_rcv_rscn(struct lpfc_vport *vport, struct lpfc_iocbq *cmdiocb, fc_host_post_event(shost, fc_get_event_number(), FCH_EVT_RSCN, lp[i]); + /* Check if RSCN is coming from a direct-connected remote NPort */ + if (vport->fc_flag & FC_PT2PT) { + /* If so, just ACC it, no other action needed for now */ + lpfc_printf_vlog(vport, KERN_INFO, LOG_ELS, + "2024 pt2pt RSCN %08x Data: x%x x%x\n", + *lp, vport->fc_flag, payload_len); + lpfc_els_rsp_acc(vport, ELS_CMD_ACC, cmdiocb, ndlp, NULL); + + if (ndlp->nlp_fc4_type & NLP_FC4_NVME) + lpfc_nvme_rescan_port(vport, ndlp); + return 0; + } + /* If we are about to begin discovery, just ACC the RSCN. * Discovery processing will satisfy it. */ diff --git a/drivers/scsi/lpfc/lpfc_hbadisc.c b/drivers/scsi/lpfc/lpfc_hbadisc.c index c43852f97f25..28ecaa7fc715 100644 --- a/drivers/scsi/lpfc/lpfc_hbadisc.c +++ b/drivers/scsi/lpfc/lpfc_hbadisc.c @@ -5277,6 +5277,41 @@ lpfc_findnode_did(struct lpfc_vport *vport, uint32_t did) } struct lpfc_nodelist * +lpfc_findnode_mapped(struct lpfc_vport *vport) +{ + struct Scsi_Host *shost = lpfc_shost_from_vport(vport); + struct lpfc_nodelist *ndlp; + uint32_t data1; + unsigned long iflags; + + spin_lock_irqsave(shost->host_lock, iflags); + + list_for_each_entry(ndlp, &vport->fc_nodes, nlp_listp) { + if (ndlp->nlp_state == NLP_STE_UNMAPPED_NODE || + ndlp->nlp_state == NLP_STE_MAPPED_NODE) { + data1 = (((uint32_t)ndlp->nlp_state << 24) | + ((uint32_t)ndlp->nlp_xri << 16) | + ((uint32_t)ndlp->nlp_type << 8) | + ((uint32_t)ndlp->nlp_rpi & 0xff)); + spin_unlock_irqrestore(shost->host_lock, iflags); + lpfc_printf_vlog(vport, KERN_INFO, LOG_NODE, + "2025 FIND node DID " + "Data: x%p x%x x%x x%x %p\n", + ndlp, ndlp->nlp_DID, + ndlp->nlp_flag, data1, + ndlp->active_rrqs_xri_bitmap); + return ndlp; + } + } + spin_unlock_irqrestore(shost->host_lock, iflags); + + /* FIND node did <did> NOT FOUND */ + lpfc_printf_vlog(vport, KERN_INFO, LOG_NODE, + "2026 FIND mapped did NOT FOUND.\n"); + return NULL; +} + +struct lpfc_nodelist * lpfc_setup_disc_node(struct lpfc_vport *vport, uint32_t did) { struct Scsi_Host *shost = lpfc_shost_from_vport(vport); diff --git a/drivers/scsi/lpfc/lpfc_hw.h b/drivers/scsi/lpfc/lpfc_hw.h index edd8f3982023..5b439a6dcde1 100644 --- a/drivers/scsi/lpfc/lpfc_hw.h +++ b/drivers/scsi/lpfc/lpfc_hw.h @@ -601,6 +601,7 @@ struct fc_vft_header { #define ELS_CMD_RPL 0x57000000 #define ELS_CMD_FAN 0x60000000 #define ELS_CMD_RSCN 0x61040000 +#define ELS_CMD_RSCN_XMT 0x61040008 #define ELS_CMD_SCR 0x62000000 #define ELS_CMD_RNID 0x78000000 #define ELS_CMD_LIRR 0x7A000000 @@ -642,6 +643,7 @@ struct fc_vft_header { #define ELS_CMD_RPL 0x57 #define ELS_CMD_FAN 0x60 #define ELS_CMD_RSCN 0x0461 +#define ELS_CMD_RSCN_XMT 0x08000461 #define ELS_CMD_SCR 0x62 #define ELS_CMD_RNID 0x78 #define ELS_CMD_LIRR 0x7A diff --git a/drivers/scsi/lpfc/lpfc_nvme.c b/drivers/scsi/lpfc/lpfc_nvme.c index 9d99cb915390..fdd16d9f55a1 100644 --- a/drivers/scsi/lpfc/lpfc_nvme.c +++ b/drivers/scsi/lpfc/lpfc_nvme.c @@ -2402,6 +2402,50 @@ lpfc_nvme_register_port(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp) #endif } +/** + * lpfc_nvme_rescan_port - Check to see if we should rescan this remoteport + * + * If the ndlp represents an NVME Target, that we are logged into, + * ping the NVME FC Transport layer to initiate a device rescan + * on this remote NPort. + */ +void +lpfc_nvme_rescan_port(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp) +{ +#if (IS_ENABLED(CONFIG_NVME_FC)) + struct lpfc_nvme_rport *rport; + struct nvme_fc_remote_port *remoteport; + + rport = ndlp->nrport; + + lpfc_printf_vlog(vport, KERN_INFO, LOG_NVME_DISC, + "6170 Rescan NPort DID x%06x type x%x " + "state x%x rport %p\n", + ndlp->nlp_DID, ndlp->nlp_type, ndlp->nlp_state, rport); + if (!rport) + goto input_err; + remoteport = rport->remoteport; + if (!remoteport) + goto input_err; + + /* Only rescan if we are an NVME target in the MAPPED state */ + if (remoteport->port_role & FC_PORT_ROLE_NVME_DISCOVERY && + ndlp->nlp_state == NLP_STE_MAPPED_NODE) { + nvme_fc_rescan_remoteport(remoteport); + + lpfc_printf_vlog(vport, KERN_ERR, LOG_NVME_DISC, + "6172 NVME rescanned DID x%06x " + "port_state x%x\n", + ndlp->nlp_DID, remoteport->port_state); + } + return; +input_err: + lpfc_printf_vlog(vport, KERN_ERR, LOG_NVME_DISC, + "6169 State error: lport %p, rport%p FCID x%06x\n", + vport->localport, ndlp->rport, ndlp->nlp_DID); +#endif +} + /* lpfc_nvme_unregister_port - unbind the DID and port_role from this rport. * * There is no notion of Devloss or rport recovery from the current diff --git a/drivers/scsi/lpfc/lpfc_nvmet.c b/drivers/scsi/lpfc/lpfc_nvmet.c index d74bfd264495..06170824a69b 100644 --- a/drivers/scsi/lpfc/lpfc_nvmet.c +++ b/drivers/scsi/lpfc/lpfc_nvmet.c @@ -1139,6 +1139,22 @@ lpfc_nvmet_defer_rcv(struct nvmet_fc_target_port *tgtport, spin_unlock_irqrestore(&ctxp->ctxlock, iflag); } +static void +lpfc_nvmet_discovery_event(struct nvmet_fc_target_port *tgtport) +{ + struct lpfc_nvmet_tgtport *tgtp; + struct lpfc_hba *phba; + uint32_t rc; + + tgtp = tgtport->private; + phba = tgtp->phba; + + rc = lpfc_issue_els_rscn(phba->pport, 0); + lpfc_printf_log(phba, KERN_ERR, LOG_NVME, + "6420 NVMET subsystem change: Notification %s\n", + (rc) ? "Failed" : "Sent"); +} + static struct nvmet_fc_target_template lpfc_tgttemplate = { .targetport_delete = lpfc_nvmet_targetport_delete, .xmt_ls_rsp = lpfc_nvmet_xmt_ls_rsp, @@ -1146,6 +1162,7 @@ static struct nvmet_fc_target_template lpfc_tgttemplate = { .fcp_abort = lpfc_nvmet_xmt_fcp_abort, .fcp_req_release = lpfc_nvmet_xmt_fcp_release, .defer_rcv = lpfc_nvmet_defer_rcv, + .discovery_event = lpfc_nvmet_discovery_event, .max_hw_queues = 1, .max_sgl_segments = LPFC_NVMET_DEFAULT_SEGS, diff --git a/drivers/scsi/lpfc/lpfc_sli.c b/drivers/scsi/lpfc/lpfc_sli.c index d1512e4f9791..4329cc44bb55 100644 --- a/drivers/scsi/lpfc/lpfc_sli.c +++ b/drivers/scsi/lpfc/lpfc_sli.c @@ -9398,6 +9398,7 @@ lpfc_sli4_iocb2wqe(struct lpfc_hba *phba, struct lpfc_iocbq *iocbq, if (if_type >= LPFC_SLI_INTF_IF_TYPE_2) { if (pcmd && (*pcmd == ELS_CMD_FLOGI || *pcmd == ELS_CMD_SCR || + *pcmd == ELS_CMD_RSCN_XMT || *pcmd == ELS_CMD_FDISC || *pcmd == ELS_CMD_LOGO || *pcmd == ELS_CMD_PLOGI)) { diff --git a/include/linux/nvme-fc-driver.h b/include/linux/nvme-fc-driver.h index c48e96436f56..98d904961b33 100644 --- a/include/linux/nvme-fc-driver.h +++ b/include/linux/nvme-fc-driver.h @@ -791,6 +791,11 @@ struct nvmet_fc_target_port { * nvmefc_tgt_fcp_req. * Entrypoint is Optional. * + * @discovery_event: Called by the transport to generate an RSCN + * change notifications to NVME initiators. The RSCN notifications + * should cause the initiator to rescan the discovery controller + * on the targetport. + * * @max_hw_queues: indicates the maximum number of hw queues the LLDD * supports for cpu affinitization. * Value is Mandatory. Must be at least 1. @@ -832,6 +837,7 @@ struct nvmet_fc_target_template { struct nvmefc_tgt_fcp_req *fcpreq); void (*defer_rcv)(struct nvmet_fc_target_port *tgtport, struct nvmefc_tgt_fcp_req *fcpreq); + void (*discovery_event)(struct nvmet_fc_target_port *tgtport); u32 max_hw_queues; u16 max_sgl_segments; diff --git a/include/linux/nvme.h b/include/linux/nvme.h index 8028adacaff3..d98b2d8baf4e 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -562,6 +562,22 @@ enum nvme_opcode { nvme_cmd_resv_release = 0x15, }; +#define nvme_opcode_name(opcode) { opcode, #opcode } +#define show_nvm_opcode_name(val) \ + __print_symbolic(val, \ + nvme_opcode_name(nvme_cmd_flush), \ + nvme_opcode_name(nvme_cmd_write), \ + nvme_opcode_name(nvme_cmd_read), \ + nvme_opcode_name(nvme_cmd_write_uncor), \ + nvme_opcode_name(nvme_cmd_compare), \ + nvme_opcode_name(nvme_cmd_write_zeroes), \ + nvme_opcode_name(nvme_cmd_dsm), \ + nvme_opcode_name(nvme_cmd_resv_register), \ + nvme_opcode_name(nvme_cmd_resv_report), \ + nvme_opcode_name(nvme_cmd_resv_acquire), \ + nvme_opcode_name(nvme_cmd_resv_release)) + + /* * Descriptor subtype - lower 4 bits of nvme_(keyed_)sgl_desc identifier * @@ -794,6 +810,32 @@ enum nvme_admin_opcode { nvme_admin_sanitize_nvm = 0x84, }; +#define nvme_admin_opcode_name(opcode) { opcode, #opcode } +#define show_admin_opcode_name(val) \ + __print_symbolic(val, \ + nvme_admin_opcode_name(nvme_admin_delete_sq), \ + nvme_admin_opcode_name(nvme_admin_create_sq), \ + nvme_admin_opcode_name(nvme_admin_get_log_page), \ + nvme_admin_opcode_name(nvme_admin_delete_cq), \ + nvme_admin_opcode_name(nvme_admin_create_cq), \ + nvme_admin_opcode_name(nvme_admin_identify), \ + nvme_admin_opcode_name(nvme_admin_abort_cmd), \ + nvme_admin_opcode_name(nvme_admin_set_features), \ + nvme_admin_opcode_name(nvme_admin_get_features), \ + nvme_admin_opcode_name(nvme_admin_async_event), \ + nvme_admin_opcode_name(nvme_admin_ns_mgmt), \ + nvme_admin_opcode_name(nvme_admin_activate_fw), \ + nvme_admin_opcode_name(nvme_admin_download_fw), \ + nvme_admin_opcode_name(nvme_admin_ns_attach), \ + nvme_admin_opcode_name(nvme_admin_keep_alive), \ + nvme_admin_opcode_name(nvme_admin_directive_send), \ + nvme_admin_opcode_name(nvme_admin_directive_recv), \ + nvme_admin_opcode_name(nvme_admin_dbbuf), \ + nvme_admin_opcode_name(nvme_admin_format_nvm), \ + nvme_admin_opcode_name(nvme_admin_security_send), \ + nvme_admin_opcode_name(nvme_admin_security_recv), \ + nvme_admin_opcode_name(nvme_admin_sanitize_nvm)) + enum { NVME_QUEUE_PHYS_CONTIG = (1 << 0), NVME_CQ_IRQ_ENABLED = (1 << 1), @@ -1008,6 +1050,23 @@ enum nvmf_capsule_command { nvme_fabrics_type_property_get = 0x04, }; +#define nvme_fabrics_type_name(type) { type, #type } +#define show_fabrics_type_name(type) \ + __print_symbolic(type, \ + nvme_fabrics_type_name(nvme_fabrics_type_property_set), \ + nvme_fabrics_type_name(nvme_fabrics_type_connect), \ + nvme_fabrics_type_name(nvme_fabrics_type_property_get)) + +/* + * If not fabrics command, fctype will be ignored. + */ +#define show_opcode_name(qid, opcode, fctype) \ + ((opcode) == nvme_fabrics_command ? \ + show_fabrics_type_name(fctype) : \ + ((qid) ? \ + show_nvm_opcode_name(opcode) : \ + show_admin_opcode_name(opcode))) + struct nvmf_common_command { __u8 opcode; __u8 resv1; @@ -1165,6 +1224,11 @@ struct nvme_command { }; }; +static inline bool nvme_is_fabrics(struct nvme_command *cmd) +{ + return cmd->common.opcode == nvme_fabrics_command; +} + struct nvme_error_slot { __le64 error_count; __le16 sqid; @@ -1186,7 +1250,7 @@ static inline bool nvme_is_write(struct nvme_command *cmd) * * Why can't we simply have a Fabrics In and Fabrics out command? */ - if (unlikely(cmd->common.opcode == nvme_fabrics_command)) + if (unlikely(nvme_is_fabrics(cmd))) return cmd->fabrics.fctype & 1; return cmd->common.opcode & 1; } |