Merge branch 'nvme-5.3' of git://git.infradead.org/nvme into for-5.3/block

Pull NVMe updates from Christoph:

"A large chunk of NVMe updates for 5.3.  Highlights:

 - improved PCIe suspent support (Keith Busch)
 - error injection support for the admin queue (Akinobu Mita)
 - Fibre Channel discovery improvements (James Smart)
 - tracing improvements including nvmetc tracing support (Minwoo Im)
 - misc fixes and cleanups (Anton Eidelman, Minwoo Im, Chaitanya
   Kulkarni)"

* 'nvme-5.3' of git://git.infradead.org/nvme: (26 commits)
  Documentation: nvme: add an example for nvme fault injection
  nvme: enable to inject errors into admin commands
  nvme: prepare for fault injection into admin commands
  nvmet: introduce target-side trace
  nvme-trace: print result and status in hex format
  nvme-trace: support for fabrics commands in host-side
  nvme-trace: move opcode symbol print to nvme.h
  nvme-trace: do not export nvme_trace_disk_name
  nvme-pci: clean up nvme_remove_dead_ctrl a bit
  nvme-pci: properly report state change failure in nvme_reset_work
  nvme-pci: set the errno on ctrl state change error
  nvme-pci: adjust irq max_vector using num_possible_cpus()
  nvme-pci: remove queue_count_ops for write_queues and poll_queues
  nvme-pci: remove unnecessary zero for static var
  nvme-pci: use host managed power state for suspend
  nvme: introduce nvme_is_fabrics to check fabrics cmd
  nvme: export get and set features
  nvme: fix possible io failures when removing multipathed ns
  nvme-fc: add message when creating new association
  lpfc: add sysfs interface to post NVME RSCN
  ...

Author: axboe

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

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;
@@ -3343,24 +3361,26 @@ 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);
 		if (blk_get_integrity(ns->disk))
 			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);

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;

drivers/nvme/host/fault_inject.c

@@ -15,32 +15,31 @@ 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 */
 	if (fail_request)
 		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;
 	}

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
 	 */

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);