Merge tag 'for-linus-20180616' of git://git.kernel.dk/linux-block

Pull block fixes from Jens Axboe:
 "A collection of fixes that should go into -rc1. This contains:

   - bsg_open vs bsg_unregister race fix (Anatoliy)

   - NVMe pull request from Christoph, with fixes for regressions in
     this window, FC connect/reconnect path code unification, and a
     trace point addition.

   - timeout fix (Christoph)

   - remove a few unused functions (Christoph)

   - blk-mq tag_set reinit fix (Roman)"

* tag 'for-linus-20180616' of git://git.kernel.dk/linux-block:
  bsg: fix race of bsg_open and bsg_unregister
  block: remov blk_queue_invalidate_tags
  nvme-fabrics: fix and refine state checks in __nvmf_check_ready
  nvme-fabrics: handle the admin-only case properly in nvmf_check_ready
  nvme-fabrics: refactor queue ready check
  blk-mq: remove blk_mq_tagset_iter
  nvme: remove nvme_reinit_tagset
  nvme-fc: fix nulling of queue data on reconnect
  nvme-fc: remove reinit_request routine
  blk-mq: don't time out requests again that are in the timeout handler
  nvme-fc: change controllers first connect to use reconnect path
  nvme: don't rely on the changed namespace list log
  nvmet: free smart-log buffer after use
  nvme-rdma: fix error flow during mapping request data
  nvme: add bio remapping tracepoint
  nvme: fix NULL pointer dereference in nvme_init_subsystem
  blk-mq: reinit q->tag_set_list entry only after grace period

Documentation/block/biodoc.txt

@@ -752,18 +752,6 @@ completion of the request to the block layer. This means ending tag
 operations before calling end_that_request_last()! For an example of a user
 of these helpers, see the IDE tagged command queueing support.
 
-Certain hardware conditions may dictate a need to invalidate the block tag
-queue. For instance, on IDE any tagged request error needs to clear both
-the hardware and software block queue and enable the driver to sanely restart
-all the outstanding requests. There's a third helper to do that:
-
-	blk_queue_invalidate_tags(struct request_queue *q)
-
-	Clear the internal block tag queue and re-add all the pending requests
-	to the request queue. The driver will receive them again on the
-	next request_fn run, just like it did the first time it encountered
-	them.
-
 3.2.5.2 Tag info
 
 Some block functions exist to query current tag status or to go from a
@@ -805,8 +793,7 @@ Internally, block manages tags in the blk_queue_tag structure:
 Most of the above is simple and straight forward, however busy_list may need
 a bit of explaining. Normally we don't care too much about request ordering,
 but in the event of any barrier requests in the tag queue we need to ensure
-that requests are restarted in the order they were queue. This may happen
-if the driver needs to use blk_queue_invalidate_tags().
+that requests are restarted in the order they were queue.
 
 3.3 I/O Submission
 

block/blk-mq-tag.c

@@ -311,35 +311,6 @@ void blk_mq_tagset_busy_iter(struct blk_mq_tag_set *tagset,
 }
 EXPORT_SYMBOL(blk_mq_tagset_busy_iter);
 
-int blk_mq_tagset_iter(struct blk_mq_tag_set *set, void *data,
-			 int (fn)(void *, struct request *))
-{
-	int i, j, ret = 0;
-
-	if (WARN_ON_ONCE(!fn))
-		goto out;
-
-	for (i = 0; i < set->nr_hw_queues; i++) {
-		struct blk_mq_tags *tags = set->tags[i];
-
-		if (!tags)
-			continue;
-
-		for (j = 0; j < tags->nr_tags; j++) {
-			if (!tags->static_rqs[j])
-				continue;
-
-			ret = fn(data, tags->static_rqs[j]);
-			if (ret)
-				goto out;
-		}
-	}
-
-out:
-	return ret;
-}
-EXPORT_SYMBOL_GPL(blk_mq_tagset_iter);
-
 void blk_mq_queue_tag_busy_iter(struct request_queue *q, busy_iter_fn *fn,
 		void *priv)
 {

block/blk-mq.c

@@ -671,6 +671,7 @@ static void __blk_mq_requeue_request(struct request *rq)
 
 	if (blk_mq_request_started(rq)) {
 		WRITE_ONCE(rq->state, MQ_RQ_IDLE);
+		rq->rq_flags &= ~RQF_TIMED_OUT;
 		if (q->dma_drain_size && blk_rq_bytes(rq))
 			rq->nr_phys_segments--;
 	}
@@ -770,6 +771,7 @@ EXPORT_SYMBOL(blk_mq_tag_to_rq);
 
 static void blk_mq_rq_timed_out(struct request *req, bool reserved)
 {
+	req->rq_flags |= RQF_TIMED_OUT;
 	if (req->q->mq_ops->timeout) {
 		enum blk_eh_timer_return ret;
 
@@ -779,6 +781,7 @@ static void blk_mq_rq_timed_out(struct request *req, bool reserved)
 		WARN_ON_ONCE(ret != BLK_EH_RESET_TIMER);
 	}
 
+	req->rq_flags &= ~RQF_TIMED_OUT;
 	blk_add_timer(req);
 }
 
@@ -788,6 +791,8 @@ static bool blk_mq_req_expired(struct request *rq, unsigned long *next)
 
 	if (blk_mq_rq_state(rq) != MQ_RQ_IN_FLIGHT)
 		return false;
+	if (rq->rq_flags & RQF_TIMED_OUT)
+		return false;
 
 	deadline = blk_rq_deadline(rq);
 	if (time_after_eq(jiffies, deadline))
@@ -2349,16 +2354,15 @@ static void blk_mq_del_queue_tag_set(struct request_queue *q)
 
 	mutex_lock(&set->tag_list_lock);
 	list_del_rcu(&q->tag_set_list);
-	INIT_LIST_HEAD(&q->tag_set_list);
 	if (list_is_singular(&set->tag_list)) {
 		/* just transitioned to unshared */
 		set->flags &= ~BLK_MQ_F_TAG_SHARED;
 		/* update existing queue */
 		blk_mq_update_tag_set_depth(set, false);
 	}
 	mutex_unlock(&set->tag_list_lock);
-
 	synchronize_rcu();
+	INIT_LIST_HEAD(&q->tag_set_list);
 }
 
 static void blk_mq_add_queue_tag_set(struct blk_mq_tag_set *set,

block/blk-tag.c

@@ -188,7 +188,6 @@ int blk_queue_init_tags(struct request_queue *q, int depth,
 	 */
 	q->queue_tags = tags;
 	queue_flag_set_unlocked(QUEUE_FLAG_QUEUED, q);
-	INIT_LIST_HEAD(&q->tag_busy_list);
 	return 0;
 }
 EXPORT_SYMBOL(blk_queue_init_tags);
@@ -374,27 +373,6 @@ int blk_queue_start_tag(struct request_queue *q, struct request *rq)
 	rq->tag = tag;
 	bqt->tag_index[tag] = rq;
 	blk_start_request(rq);
-	list_add(&rq->queuelist, &q->tag_busy_list);
 	return 0;
 }
 EXPORT_SYMBOL(blk_queue_start_tag);
-
-/**
- * blk_queue_invalidate_tags - invalidate all pending tags
- * @q:  the request queue for the device
- *
- *  Description:
- *   Hardware conditions may dictate a need to stop all pending requests.
- *   In this case, we will safely clear the block side of the tag queue and
- *   readd all requests to the request queue in the right order.
- **/
-void blk_queue_invalidate_tags(struct request_queue *q)
-{
-	struct list_head *tmp, *n;
-
-	lockdep_assert_held(q->queue_lock);
-
-	list_for_each_safe(tmp, n, &q->tag_busy_list)
-		blk_requeue_request(q, list_entry_rq(tmp));
-}
-EXPORT_SYMBOL(blk_queue_invalidate_tags);

block/bsg.c

@@ -693,6 +693,8 @@ static struct bsg_device *bsg_add_device(struct inode *inode,
 	struct bsg_device *bd;
 	unsigned char buf[32];
 
+	lockdep_assert_held(&bsg_mutex);
+
 	if (!blk_get_queue(rq))
 		return ERR_PTR(-ENXIO);
 
@@ -707,22 +709,20 @@ static struct bsg_device *bsg_add_device(struct inode *inode,
 	bsg_set_block(bd, file);
 
 	atomic_set(&bd->ref_count, 1);
-	mutex_lock(&bsg_mutex);
 	hlist_add_head(&bd->dev_list, bsg_dev_idx_hash(iminor(inode)));
 
 	strncpy(bd->name, dev_name(rq->bsg_dev.class_dev), sizeof(bd->name) - 1);
 	bsg_dbg(bd, "bound to <%s>, max queue %d\n",
 		format_dev_t(buf, inode->i_rdev), bd->max_queue);
 
-	mutex_unlock(&bsg_mutex);
 	return bd;
 }
 
 static struct bsg_device *__bsg_get_device(int minor, struct request_queue *q)
 {
 	struct bsg_device *bd;
 
-	mutex_lock(&bsg_mutex);
+	lockdep_assert_held(&bsg_mutex);
 
 	hlist_for_each_entry(bd, bsg_dev_idx_hash(minor), dev_list) {
 		if (bd->queue == q) {
@@ -732,7 +732,6 @@ static struct bsg_device *__bsg_get_device(int minor, struct request_queue *q)
 	}
 	bd = NULL;
 found:
-	mutex_unlock(&bsg_mutex);
 	return bd;
 }
 
@@ -746,17 +745,18 @@ static struct bsg_device *bsg_get_device(struct inode *inode, struct file *file)
 	 */
 	mutex_lock(&bsg_mutex);
 	bcd = idr_find(&bsg_minor_idr, iminor(inode));
-	mutex_unlock(&bsg_mutex);
 
-	if (!bcd)
-		return ERR_PTR(-ENODEV);
+	if (!bcd) {
+		bd = ERR_PTR(-ENODEV);
+		goto out_unlock;
+	}
 
 	bd = __bsg_get_device(iminor(inode), bcd->queue);
-	if (bd)
-		return bd;
-
-	bd = bsg_add_device(inode, bcd->queue, file);
+	if (!bd)
+		bd = bsg_add_device(inode, bcd->queue, file);
 
+out_unlock:
+	mutex_unlock(&bsg_mutex);
 	return bd;
 }
 

drivers/nvme/host/core.c

@@ -2208,7 +2208,7 @@ static int nvme_init_subsystem(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id)
 		 * Verify that the subsystem actually supports multiple
 		 * controllers, else bail out.
 		 */
-		if (!ctrl->opts->discovery_nqn &&
+		if (!(ctrl->opts && ctrl->opts->discovery_nqn) &&
 		    nvme_active_ctrls(found) && !(id->cmic & (1 << 1))) {
 			dev_err(ctrl->device,
 				"ignoring ctrl due to duplicate subnqn (%s).\n",
@@ -3197,40 +3197,28 @@ static void nvme_scan_ns_sequential(struct nvme_ctrl *ctrl, unsigned nn)
 	nvme_remove_invalid_namespaces(ctrl, nn);
 }
 
-static bool nvme_scan_changed_ns_log(struct nvme_ctrl *ctrl)
+static void nvme_clear_changed_ns_log(struct nvme_ctrl *ctrl)
 {
 	size_t log_size = NVME_MAX_CHANGED_NAMESPACES * sizeof(__le32);
 	__le32 *log;
-	int error, i;
-	bool ret = false;
+	int error;
 
 	log = kzalloc(log_size, GFP_KERNEL);
 	if (!log)
-		return false;
+		return;
 
+	/*
+	 * We need to read the log to clear the AEN, but we don't want to rely
+	 * on it for the changed namespace information as userspace could have
+	 * raced with us in reading the log page, which could cause us to miss
+	 * updates.
+	 */
 	error = nvme_get_log(ctrl, NVME_LOG_CHANGED_NS, log, log_size);
-	if (error) {
+	if (error)
 		dev_warn(ctrl->device,
 			"reading changed ns log failed: %d\n", error);
-		goto out_free_log;
-	}
-
-	if (log[0] == cpu_to_le32(0xffffffff))
-		goto out_free_log;
-
-	for (i = 0; i < NVME_MAX_CHANGED_NAMESPACES; i++) {
-		u32 nsid = le32_to_cpu(log[i]);
 
-		if (nsid == 0)
-			break;
-		dev_info(ctrl->device, "rescanning namespace %d.\n", nsid);
-		nvme_validate_ns(ctrl, nsid);
-	}
-	ret = true;
-
-out_free_log:
 	kfree(log);
-	return ret;
 }
 
 static void nvme_scan_work(struct work_struct *work)
@@ -3246,9 +3234,8 @@ static void nvme_scan_work(struct work_struct *work)
 	WARN_ON_ONCE(!ctrl->tagset);
 
 	if (test_and_clear_bit(NVME_AER_NOTICE_NS_CHANGED, &ctrl->events)) {
-		if (nvme_scan_changed_ns_log(ctrl))
-			goto out_sort_namespaces;
 		dev_info(ctrl->device, "rescanning namespaces.\n");
+		nvme_clear_changed_ns_log(ctrl);
 	}
 
 	if (nvme_identify_ctrl(ctrl, &id))
@@ -3263,7 +3250,6 @@ static void nvme_scan_work(struct work_struct *work)
 	nvme_scan_ns_sequential(ctrl, nn);
 out_free_id:
 	kfree(id);
-out_sort_namespaces:
 	down_write(&ctrl->namespaces_rwsem);
 	list_sort(NULL, &ctrl->namespaces, ns_cmp);
 	up_write(&ctrl->namespaces_rwsem);
@@ -3641,16 +3627,6 @@ void nvme_start_queues(struct nvme_ctrl *ctrl)
 }
 EXPORT_SYMBOL_GPL(nvme_start_queues);
 
-int nvme_reinit_tagset(struct nvme_ctrl *ctrl, struct blk_mq_tag_set *set)
-{
-	if (!ctrl->ops->reinit_request)
-		return 0;
-
-	return blk_mq_tagset_iter(set, set->driver_data,
-			ctrl->ops->reinit_request);
-}
-EXPORT_SYMBOL_GPL(nvme_reinit_tagset);
-
 int __init nvme_core_init(void)
 {
 	int result = -ENOMEM;