Merge tag 'nvme-5.18-2022-03-17' of git://git.infradead.org/nvme into for-5.18/drivers

Pull NVMe updates from Christoph:

"Second round of nvme updates for Linux 5.18

 - add lockdep annotations for in-kernel sockets (Chris Leech)
 - use vmalloc for ANA log buffer (Hannes Reinecke)
 - kerneldoc fixes (Chaitanya Kulkarni)
 - cleanups (Guoqing Jiang, Chaitanya Kulkarni, me)
 - warn about shared namespaces without multipathing (me)"

* tag 'nvme-5.18-2022-03-17' of git://git.infradead.org/nvme:
  nvme: warn about shared namespaces without CONFIG_NVME_MULTIPATH
  nvme: remove nvme_alloc_request and nvme_alloc_request_qid
  nvme: cleanup how disk->disk_name is assigned
  nvmet: move the call to nvmet_ns_changed out of nvmet_ns_revalidate
  nvmet: use snprintf() with PAGE_SIZE in configfs
  nvmet: don't fold lines
  nvmet-rdma: fix kernel-doc warning for nvmet_rdma_device_removal
  nvmet-fc: fix kernel-doc warning for nvmet_fc_unregister_targetport
  nvmet-fc: fix kernel-doc warning for nvmet_fc_register_targetport
  nvme-tcp: lockdep: annotate in-kernel sockets
  nvme-tcp: don't fold the line
  nvme-tcp: don't initialize ret variable
  nvme-multipath: call bio_io_error in nvme_ns_head_submit_bio
  nvme-multipath: use vmalloc for ANA log buffer

Author: axboe

drivers/block/loop.c

@@ -2092,6 +2092,7 @@ static void loop_remove(struct loop_device *lo)
 	del_gendisk(lo->lo_disk);
 	blk_cleanup_disk(lo->lo_disk);
 	blk_mq_free_tag_set(&lo->tag_set);
+
 	mutex_lock(&loop_ctl_mutex);
 	idr_remove(&loop_index_idr, lo->lo_number);
 	mutex_unlock(&loop_ctl_mutex);

drivers/nvme/host/core.c

@@ -639,13 +639,8 @@ static inline void nvme_clear_nvme_request(struct request *req)
 	req->rq_flags |= RQF_DONTPREP;
 }
 
-static inline unsigned int nvme_req_op(struct nvme_command *cmd)
-{
-	return nvme_is_write(cmd) ? REQ_OP_DRV_OUT : REQ_OP_DRV_IN;
-}
-
-static inline void nvme_init_request(struct request *req,
-		struct nvme_command *cmd)
+/* initialize a passthrough request */
+void nvme_init_request(struct request *req, struct nvme_command *cmd)
 {
 	if (req->q->queuedata)
 		req->timeout = NVME_IO_TIMEOUT;
@@ -661,30 +656,7 @@ static inline void nvme_init_request(struct request *req,
 	nvme_clear_nvme_request(req);
 	memcpy(nvme_req(req)->cmd, cmd, sizeof(*cmd));
 }
-
-struct request *nvme_alloc_request(struct request_queue *q,
-		struct nvme_command *cmd, blk_mq_req_flags_t flags)
-{
-	struct request *req;
-
-	req = blk_mq_alloc_request(q, nvme_req_op(cmd), flags);
-	if (!IS_ERR(req))
-		nvme_init_request(req, cmd);
-	return req;
-}
-EXPORT_SYMBOL_GPL(nvme_alloc_request);
-
-static struct request *nvme_alloc_request_qid(struct request_queue *q,
-		struct nvme_command *cmd, blk_mq_req_flags_t flags, int qid)
-{
-	struct request *req;
-
-	req = blk_mq_alloc_request_hctx(q, nvme_req_op(cmd), flags,
-			qid ? qid - 1 : 0);
-	if (!IS_ERR(req))
-		nvme_init_request(req, cmd);
-	return req;
-}
+EXPORT_SYMBOL_GPL(nvme_init_request);
 
 /*
  * For something we're not in a state to send to the device the default action
@@ -1110,11 +1082,14 @@ int __nvme_submit_sync_cmd(struct request_queue *q, struct nvme_command *cmd,
 	int ret;
 
 	if (qid == NVME_QID_ANY)
-		req = nvme_alloc_request(q, cmd, flags);
+		req = blk_mq_alloc_request(q, nvme_req_op(cmd), flags);
 	else
-		req = nvme_alloc_request_qid(q, cmd, flags, qid);
+		req = blk_mq_alloc_request_hctx(q, nvme_req_op(cmd), flags,
+						qid ? qid - 1 : 0);
+
 	if (IS_ERR(req))
 		return PTR_ERR(req);
+	nvme_init_request(req, cmd);
 
 	if (timeout)
 		req->timeout = timeout;
@@ -1304,14 +1279,15 @@ static void nvme_keep_alive_work(struct work_struct *work)
 		return;
 	}
 
-	rq = nvme_alloc_request(ctrl->admin_q, &ctrl->ka_cmd,
-				BLK_MQ_REQ_RESERVED | BLK_MQ_REQ_NOWAIT);
+	rq = blk_mq_alloc_request(ctrl->admin_q, nvme_req_op(&ctrl->ka_cmd),
+				  BLK_MQ_REQ_RESERVED | BLK_MQ_REQ_NOWAIT);
 	if (IS_ERR(rq)) {
 		/* allocation failure, reset the controller */
 		dev_err(ctrl->device, "keep-alive failed: %ld\n", PTR_ERR(rq));
 		nvme_reset_ctrl(ctrl);
 		return;
 	}
+	nvme_init_request(rq, &ctrl->ka_cmd);
 
 	rq->timeout = ctrl->kato * HZ;
 	rq->end_io_data = ctrl;
@@ -3879,6 +3855,14 @@ static int nvme_init_ns_head(struct nvme_ns *ns, unsigned nsid,
 					nsid);
 			goto out_put_ns_head;
 		}
+
+		if (!multipath && !list_empty(&head->list)) {
+			dev_warn(ctrl->device,
+				"Found shared namespace %d, but multipathing not supported.\n",
+				nsid);
+			dev_warn_once(ctrl->device,
+				"Support for shared namespaces without CONFIG_NVME_MULTIPATH is deprecated and will be removed in Linux 6.0\n.");
+		}
 	}
 
 	list_add_tail_rcu(&ns->siblings, &head->list);
@@ -3967,13 +3951,27 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid,
 		goto out_cleanup_disk;
 
 	/*
-	 * Without the multipath code enabled, multiple controller per
-	 * subsystems are visible as devices and thus we cannot use the
-	 * subsystem instance.
+	 * If multipathing is enabled, the device name for all disks and not
+	 * just those that represent shared namespaces needs to be based on the
+	 * subsystem instance.  Using the controller instance for private
+	 * namespaces could lead to naming collisions between shared and private
+	 * namespaces if they don't use a common numbering scheme.
+	 *
+	 * If multipathing is not enabled, disk names must use the controller
+	 * instance as shared namespaces will show up as multiple block
+	 * devices.
 	 */
-	if (!nvme_mpath_set_disk_name(ns, disk->disk_name, &disk->flags))
+	if (ns->head->disk) {
+		sprintf(disk->disk_name, "nvme%dc%dn%d", ctrl->subsys->instance,
+			ctrl->instance, ns->head->instance);
+		disk->flags |= GENHD_FL_HIDDEN;
+	} else if (multipath) {
+		sprintf(disk->disk_name, "nvme%dn%d", ctrl->subsys->instance,
+			ns->head->instance);
+	} else {
 		sprintf(disk->disk_name, "nvme%dn%d", ctrl->instance,
 			ns->head->instance);
+	}
 
 	if (nvme_update_ns_info(ns, id))
 		goto out_unlink_ns;

drivers/nvme/host/ioctl.c

@@ -66,9 +66,10 @@ static int nvme_submit_user_cmd(struct request_queue *q,
 	void *meta = NULL;
 	int ret;
 
-	req = nvme_alloc_request(q, cmd, 0);
+	req = blk_mq_alloc_request(q, nvme_req_op(cmd), 0);
 	if (IS_ERR(req))
 		return PTR_ERR(req);
+	nvme_init_request(req, cmd);
 
 	if (timeout)
 		req->timeout = timeout;

drivers/nvme/host/multipath.c

@@ -5,10 +5,11 @@
 
 #include <linux/backing-dev.h>
 #include <linux/moduleparam.h>
+#include <linux/vmalloc.h>
 #include <trace/events/block.h>
 #include "nvme.h"
 
-static bool multipath = true;
+bool multipath = true;
 module_param(multipath, bool, 0444);
 MODULE_PARM_DESC(multipath,
 	"turn on native support for multiple controllers per subsystem");
@@ -79,28 +80,6 @@ void nvme_mpath_start_freeze(struct nvme_subsystem *subsys)
 			blk_freeze_queue_start(h->disk->queue);
 }
 
-/*
- * If multipathing is enabled we need to always use the subsystem instance
- * number for numbering our devices to avoid conflicts between subsystems that
- * have multiple controllers and thus use the multipath-aware subsystem node
- * and those that have a single controller and use the controller node
- * directly.
- */
-bool nvme_mpath_set_disk_name(struct nvme_ns *ns, char *disk_name, int *flags)
-{
-	if (!multipath)
-		return false;
-	if (!ns->head->disk) {
-		sprintf(disk_name, "nvme%dn%d", ns->ctrl->subsys->instance,
-			ns->head->instance);
-		return true;
-	}
-	sprintf(disk_name, "nvme%dc%dn%d", ns->ctrl->subsys->instance,
-		ns->ctrl->instance, ns->head->instance);
-	*flags = GENHD_FL_HIDDEN;
-	return true;
-}
-
 void nvme_failover_req(struct request *req)
 {
 	struct nvme_ns *ns = req->q->queuedata;
@@ -386,8 +365,7 @@ static void nvme_ns_head_submit_bio(struct bio *bio)
 	} else {
 		dev_warn_ratelimited(dev, "no available path - failing I/O\n");
 
-		bio->bi_status = BLK_STS_IOERR;
-		bio_endio(bio);
+		bio_io_error(bio);
 	}
 
 	srcu_read_unlock(&head->srcu, srcu_idx);
@@ -898,7 +876,7 @@ int nvme_mpath_init_identify(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id)
 	if (ana_log_size > ctrl->ana_log_size) {
 		nvme_mpath_stop(ctrl);
 		nvme_mpath_uninit(ctrl);
-		ctrl->ana_log_buf = kmalloc(ana_log_size, GFP_KERNEL);
+		ctrl->ana_log_buf = kvmalloc(ana_log_size, GFP_KERNEL);
 		if (!ctrl->ana_log_buf)
 			return -ENOMEM;
 	}
@@ -915,7 +893,7 @@ int nvme_mpath_init_identify(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id)
 
 void nvme_mpath_uninit(struct nvme_ctrl *ctrl)
 {
-	kfree(ctrl->ana_log_buf);
+	kvfree(ctrl->ana_log_buf);
 	ctrl->ana_log_buf = NULL;
 	ctrl->ana_log_size = 0;
 }

drivers/nvme/host/nvme.h

@@ -698,9 +698,13 @@ void nvme_wait_freeze(struct nvme_ctrl *ctrl);
 int nvme_wait_freeze_timeout(struct nvme_ctrl *ctrl, long timeout);
 void nvme_start_freeze(struct nvme_ctrl *ctrl);
 
+static inline unsigned int nvme_req_op(struct nvme_command *cmd)
+{
+	return nvme_is_write(cmd) ? REQ_OP_DRV_OUT : REQ_OP_DRV_IN;
+}
+
 #define NVME_QID_ANY -1
-struct request *nvme_alloc_request(struct request_queue *q,
-		struct nvme_command *cmd, blk_mq_req_flags_t flags);
+void nvme_init_request(struct request *req, struct nvme_command *cmd);
 void nvme_cleanup_cmd(struct request *req);
 blk_status_t nvme_setup_cmd(struct nvme_ns *ns, struct request *req);
 blk_status_t nvme_fail_nonready_command(struct nvme_ctrl *ctrl,
@@ -770,7 +774,6 @@ void nvme_mpath_unfreeze(struct nvme_subsystem *subsys);
 void nvme_mpath_wait_freeze(struct nvme_subsystem *subsys);
 void nvme_mpath_start_freeze(struct nvme_subsystem *subsys);
 void nvme_mpath_default_iopolicy(struct nvme_subsystem *subsys);
-bool nvme_mpath_set_disk_name(struct nvme_ns *ns, char *disk_name, int *flags);
 void nvme_failover_req(struct request *req);
 void nvme_kick_requeue_lists(struct nvme_ctrl *ctrl);
 int nvme_mpath_alloc_disk(struct nvme_ctrl *ctrl,struct nvme_ns_head *head);
@@ -793,20 +796,17 @@ static inline void nvme_trace_bio_complete(struct request *req)
 		trace_block_bio_complete(ns->head->disk->queue, req->bio);
 }
 
+extern bool multipath;
 extern struct device_attribute dev_attr_ana_grpid;
 extern struct device_attribute dev_attr_ana_state;
 extern struct device_attribute subsys_attr_iopolicy;
 
 #else
+#define multipath false
 static inline bool nvme_ctrl_use_ana(struct nvme_ctrl *ctrl)
 {
 	return false;
 }
-static inline bool nvme_mpath_set_disk_name(struct nvme_ns *ns, char *disk_name,
-		int *flags)
-{
-	return false;
-}
 static inline void nvme_failover_req(struct request *req)
 {
 }

drivers/nvme/host/pci.c

@@ -424,8 +424,9 @@ static int nvme_init_hctx(struct blk_mq_hw_ctx *hctx, void *data,
 	return 0;
 }
 
-static int nvme_init_request(struct blk_mq_tag_set *set, struct request *req,
-		unsigned int hctx_idx, unsigned int numa_node)
+static int nvme_pci_init_request(struct blk_mq_tag_set *set,
+		struct request *req, unsigned int hctx_idx,
+		unsigned int numa_node)
 {
 	struct nvme_dev *dev = set->driver_data;
 	struct nvme_iod *iod = blk_mq_rq_to_pdu(req);
@@ -1428,12 +1429,13 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req, bool reserved)
 		"I/O %d QID %d timeout, aborting\n",
 		 req->tag, nvmeq->qid);
 
-	abort_req = nvme_alloc_request(dev->ctrl.admin_q, &cmd,
-			BLK_MQ_REQ_NOWAIT);
+	abort_req = blk_mq_alloc_request(dev->ctrl.admin_q, nvme_req_op(&cmd),
+					 BLK_MQ_REQ_NOWAIT);
 	if (IS_ERR(abort_req)) {
 		atomic_inc(&dev->ctrl.abort_limit);
 		return BLK_EH_RESET_TIMER;
 	}
+	nvme_init_request(abort_req, &cmd);
 
 	abort_req->end_io_data = NULL;
 	blk_execute_rq_nowait(abort_req, false, abort_endio);
@@ -1722,7 +1724,7 @@ static const struct blk_mq_ops nvme_mq_admin_ops = {
 	.queue_rq	= nvme_queue_rq,
 	.complete	= nvme_pci_complete_rq,
 	.init_hctx	= nvme_admin_init_hctx,
-	.init_request	= nvme_init_request,
+	.init_request	= nvme_pci_init_request,
 	.timeout	= nvme_timeout,
 };
 
@@ -1732,7 +1734,7 @@ static const struct blk_mq_ops nvme_mq_ops = {
 	.complete	= nvme_pci_complete_rq,
 	.commit_rqs	= nvme_commit_rqs,
 	.init_hctx	= nvme_init_hctx,
-	.init_request	= nvme_init_request,
+	.init_request	= nvme_pci_init_request,
 	.map_queues	= nvme_pci_map_queues,
 	.timeout	= nvme_timeout,
 	.poll		= nvme_poll,
@@ -2475,9 +2477,10 @@ static int nvme_delete_queue(struct nvme_queue *nvmeq, u8 opcode)
 	cmd.delete_queue.opcode = opcode;
 	cmd.delete_queue.qid = cpu_to_le16(nvmeq->qid);
 
-	req = nvme_alloc_request(q, &cmd, BLK_MQ_REQ_NOWAIT);
+	req = blk_mq_alloc_request(q, nvme_req_op(&cmd), BLK_MQ_REQ_NOWAIT);
 	if (IS_ERR(req))
 		return PTR_ERR(req);
+	nvme_init_request(req, &cmd);
 
 	req->end_io_data = nvmeq;
 

drivers/nvme/host/tcp.c

@@ -30,6 +30,44 @@ static int so_priority;
 module_param(so_priority, int, 0644);
 MODULE_PARM_DESC(so_priority, "nvme tcp socket optimize priority");
 
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+/* lockdep can detect a circular dependency of the form
+ *   sk_lock -> mmap_lock (page fault) -> fs locks -> sk_lock
+ * because dependencies are tracked for both nvme-tcp and user contexts. Using
+ * a separate class prevents lockdep from conflating nvme-tcp socket use with
+ * user-space socket API use.
+ */
+static struct lock_class_key nvme_tcp_sk_key[2];
+static struct lock_class_key nvme_tcp_slock_key[2];
+
+static void nvme_tcp_reclassify_socket(struct socket *sock)
+{
+	struct sock *sk = sock->sk;
+
+	if (WARN_ON_ONCE(!sock_allow_reclassification(sk)))
+		return;
+
+	switch (sk->sk_family) {
+	case AF_INET:
+		sock_lock_init_class_and_name(sk, "slock-AF_INET-NVME",
+					      &nvme_tcp_slock_key[0],
+					      "sk_lock-AF_INET-NVME",
+					      &nvme_tcp_sk_key[0]);
+		break;
+	case AF_INET6:
+		sock_lock_init_class_and_name(sk, "slock-AF_INET6-NVME",
+					      &nvme_tcp_slock_key[1],
+					      "sk_lock-AF_INET6-NVME",
+					      &nvme_tcp_sk_key[1]);
+		break;
+	default:
+		WARN_ON_ONCE(1);
+	}
+}
+#else
+static void nvme_tcp_reclassify_socket(struct socket *sock) { }
+#endif
+
 enum nvme_tcp_send_state {
 	NVME_TCP_SEND_CMD_PDU = 0,
 	NVME_TCP_SEND_H2C_PDU,
@@ -1427,6 +1465,8 @@ static int nvme_tcp_alloc_queue(struct nvme_ctrl *nctrl,
 		goto err_destroy_mutex;
 	}
 
+	nvme_tcp_reclassify_socket(queue->sock);
+
 	/* Single syn retry */
 	tcp_sock_set_syncnt(queue->sock->sk, 1);
 
@@ -1674,7 +1714,7 @@ static void nvme_tcp_stop_io_queues(struct nvme_ctrl *ctrl)
 
 static int nvme_tcp_start_io_queues(struct nvme_ctrl *ctrl)
 {
-	int i, ret = 0;
+	int i, ret;
 
 	for (i = 1; i < ctrl->queue_count; i++) {
 		ret = nvme_tcp_start_queue(ctrl, i);
@@ -1714,8 +1754,7 @@ static int __nvme_tcp_alloc_io_queues(struct nvme_ctrl *ctrl)
 	int i, ret;
 
 	for (i = 1; i < ctrl->queue_count; i++) {
-		ret = nvme_tcp_alloc_queue(ctrl, i,
-				ctrl->sqsize + 1);
+		ret = nvme_tcp_alloc_queue(ctrl, i, ctrl->sqsize + 1);
 		if (ret)
 			goto out_free_queues;
 	}