Merge tag 'for-linus-20180309' of git://git.kernel.dk/linux-block

Pull block fixes from Jens Axboe:

 - a xen-blkfront fix from Bhavesh with a multiqueue fix when
   detaching/re-attaching

 - a few important NVMe fixes, including a revert for a sysfs fix that
   caused some user space confusion

 - two bcache fixes by way of Michael Lyle

 - a loop regression fix, fixing an issue with lost writes on DAX.

* tag 'for-linus-20180309' of git://git.kernel.dk/linux-block:
  loop: Fix lost writes caused by missing flag
  nvme_fc: rework sqsize handling
  nvme-fabrics: Ignore nr_io_queues option for discovery controllers
  xen-blkfront: move negotiate_mq to cover all cases of new VBDs
  Revert "nvme: create 'slaves' and 'holders' entries for hidden controllers"
  bcache: don't attach backing with duplicate UUID
  bcache: fix crashes in duplicate cache device register
  nvme: pci: pass max vectors as num_possible_cpus() to pci_alloc_irq_vectors
  nvme-pci: Fix EEH failure on ppc

9 files changed, 60 insertions, 73 deletions

diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index 87855b5123a6..ee62d2d517bf 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -266,7 +266,7 @@ static int lo_write_bvec(struct file *file, struct bio_vec *bvec, loff_t *ppos)
 	struct iov_iter i;
 	ssize_t bw;
 
-	iov_iter_bvec(&i, ITER_BVEC, bvec, 1, bvec->bv_len);
+	iov_iter_bvec(&i, ITER_BVEC | WRITE, bvec, 1, bvec->bv_len);
 
 	file_start_write(file);
 	bw = vfs_iter_write(file, &i, ppos, 0);
diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c
index e126e4cac2ca..92ec1bbece51 100644
--- a/drivers/block/xen-blkfront.c
+++ b/drivers/block/xen-blkfront.c
@@ -262,6 +262,7 @@ static DEFINE_SPINLOCK(minor_lock);
 
 static int blkfront_setup_indirect(struct blkfront_ring_info *rinfo);
 static void blkfront_gather_backend_features(struct blkfront_info *info);
+static int negotiate_mq(struct blkfront_info *info);
 
 static int get_id_from_freelist(struct blkfront_ring_info *rinfo)
 {
@@ -1774,11 +1775,18 @@ static int talk_to_blkback(struct xenbus_device *dev,
 	unsigned int i, max_page_order;
 	unsigned int ring_page_order;
 
+	if (!info)
+		return -ENODEV;
+
 	max_page_order = xenbus_read_unsigned(info->xbdev->otherend,
 					      "max-ring-page-order", 0);
 	ring_page_order = min(xen_blkif_max_ring_order, max_page_order);
 	info->nr_ring_pages = 1 << ring_page_order;
 
+	err = negotiate_mq(info);
+	if (err)
+		goto destroy_blkring;
+
 	for (i = 0; i < info->nr_rings; i++) {
 		struct blkfront_ring_info *rinfo = &info->rinfo[i];
 
@@ -1978,11 +1986,6 @@ static int blkfront_probe(struct xenbus_device *dev,
 	}
 
 	info->xbdev = dev;
-	err = negotiate_mq(info);
-	if (err) {
-		kfree(info);
-		return err;
-	}
 
 	mutex_init(&info->mutex);
 	info->vdevice = vdevice;
@@ -2099,10 +2102,6 @@ static int blkfront_resume(struct xenbus_device *dev)
 
 	blkif_free(info, info->connected == BLKIF_STATE_CONNECTED);
 
-	err = negotiate_mq(info);
-	if (err)
-		return err;
-
 	err = talk_to_blkback(dev, info);
 	if (!err)
 		blk_mq_update_nr_hw_queues(&info->tag_set, info->nr_rings);
diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c
index 4d1d8dfb2d2a..f2273143b3cb 100644
--- a/drivers/md/bcache/super.c
+++ b/drivers/md/bcache/super.c
@@ -963,6 +963,7 @@ int bch_cached_dev_attach(struct cached_dev *dc, struct cache_set *c,
 	uint32_t rtime = cpu_to_le32(get_seconds());
 	struct uuid_entry *u;
 	char buf[BDEVNAME_SIZE];
+	struct cached_dev *exist_dc, *t;
 
 	bdevname(dc->bdev, buf);
 
@@ -987,6 +988,16 @@ int bch_cached_dev_attach(struct cached_dev *dc, struct cache_set *c,
 		return -EINVAL;
 	}
 
+	/* Check whether already attached */
+	list_for_each_entry_safe(exist_dc, t, &c->cached_devs, list) {
+		if (!memcmp(dc->sb.uuid, exist_dc->sb.uuid, 16)) {
+			pr_err("Tried to attach %s but duplicate UUID already attached",
+				buf);
+
+			return -EINVAL;
+		}
+	}
+
 	u = uuid_find(c, dc->sb.uuid);
 
 	if (u &&
@@ -1204,7 +1215,7 @@ static void register_bdev(struct cache_sb *sb, struct page *sb_page,
 
 	return;
 err:
-	pr_notice("error opening %s: %s", bdevname(bdev, name), err);
+	pr_notice("error %s: %s", bdevname(bdev, name), err);
 	bcache_device_stop(&dc->disk);
 }
 
@@ -1883,6 +1894,8 @@ static int register_cache(struct cache_sb *sb, struct page *sb_page,
 	const char *err = NULL; /* must be set for any error case */
 	int ret = 0;
 
+	bdevname(bdev, name);
+
 	memcpy(&ca->sb, sb, sizeof(struct cache_sb));
 	ca->bdev = bdev;
 	ca->bdev->bd_holder = ca;
@@ -1891,11 +1904,12 @@ static int register_cache(struct cache_sb *sb, struct page *sb_page,
 	bio_first_bvec_all(&ca->sb_bio)->bv_page = sb_page;
 	get_page(sb_page);
 
-	if (blk_queue_discard(bdev_get_queue(ca->bdev)))
+	if (blk_queue_discard(bdev_get_queue(bdev)))
 		ca->discard = CACHE_DISCARD(&ca->sb);
 
 	ret = cache_alloc(ca);
 	if (ret != 0) {
+		blkdev_put(bdev, FMODE_READ|FMODE_WRITE|FMODE_EXCL);
 		if (ret == -ENOMEM)
 			err = "cache_alloc(): -ENOMEM";
 		else
@@ -1918,14 +1932,14 @@ static int register_cache(struct cache_sb *sb, struct page *sb_page,
 		goto out;
 	}
 
-	pr_info("registered cache device %s", bdevname(bdev, name));
+	pr_info("registered cache device %s", name);
 
 out:
 	kobject_put(&ca->kobj);
 
 err:
 	if (err)
-		pr_notice("error opening %s: %s", bdevname(bdev, name), err);
+		pr_notice("error %s: %s", name, err);
 
 	return ret;
 }
@@ -2014,6 +2028,7 @@ static ssize_t register_bcache(struct kobject *k, struct kobj_attribute *attr,
 	if (err)
 		goto err_close;
 
+	err = "failed to register device";
 	if (SB_IS_BDEV(sb)) {
 		struct cached_dev *dc = kzalloc(sizeof(*dc), GFP_KERNEL);
 		if (!dc)
@@ -2028,7 +2043,7 @@ static ssize_t register_bcache(struct kobject *k, struct kobj_attribute *attr,
 			goto err_close;
 
 		if (register_cache(sb, sb_page, bdev, ca) != 0)
-			goto err_close;
+			goto err;
 	}
 out:
 	if (sb_page)
@@ -2041,7 +2056,7 @@ out:
 err_close:
 	blkdev_put(bdev, FMODE_READ|FMODE_WRITE|FMODE_EXCL);
 err:
-	pr_info("error opening %s: %s", path, err);
+	pr_info("error %s: %s", path, err);
 	ret = -EINVAL;
 	goto out;
 }
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 817e5e2766da..7aeca5db7916 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -3033,7 +3033,6 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid)
 			ns->disk->disk_name);
 
 	nvme_mpath_add_disk(ns->head);
-	nvme_mpath_add_disk_links(ns);
 	return;
  out_unlink_ns:
 	mutex_lock(&ctrl->subsys->lock);
@@ -3053,7 +3052,6 @@ static void nvme_ns_remove(struct nvme_ns *ns)
 		return;
 
 	if (ns->disk && ns->disk->flags & GENHD_FL_UP) {
-		nvme_mpath_remove_disk_links(ns);
 		sysfs_remove_group(&disk_to_dev(ns->disk)->kobj,
 					&nvme_ns_id_attr_group);
 		if (ns->ndev)
diff --git a/drivers/nvme/host/fabrics.c b/drivers/nvme/host/fabrics.c
index a1c58e35075e..8f0f34d06d46 100644
--- a/drivers/nvme/host/fabrics.c
+++ b/drivers/nvme/host/fabrics.c
@@ -650,6 +650,11 @@ static int nvmf_parse_options(struct nvmf_ctrl_options *opts,
 				ret = -EINVAL;
 				goto out;
 			}
+			if (opts->discovery_nqn) {
+				pr_debug("Ignoring nr_io_queues value for discovery controller\n");
+				break;
+			}
+
 			opts->nr_io_queues = min_t(unsigned int,
 					num_online_cpus(), token);
 			break;
diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c
index 7f51f8414b97..1dc1387b7134 100644
--- a/drivers/nvme/host/fc.c
+++ b/drivers/nvme/host/fc.c
@@ -1206,7 +1206,7 @@ nvme_fc_connect_admin_queue(struct nvme_fc_ctrl *ctrl,
 				sizeof(struct fcnvme_lsdesc_cr_assoc_cmd));
 
 	assoc_rqst->assoc_cmd.ersp_ratio = cpu_to_be16(ersp_ratio);
-	assoc_rqst->assoc_cmd.sqsize = cpu_to_be16(qsize);
+	assoc_rqst->assoc_cmd.sqsize = cpu_to_be16(qsize - 1);
 	/* Linux supports only Dynamic controllers */
 	assoc_rqst->assoc_cmd.cntlid = cpu_to_be16(0xffff);
 	uuid_copy(&assoc_rqst->assoc_cmd.hostid, &ctrl->ctrl.opts->host->id);
@@ -1321,7 +1321,7 @@ nvme_fc_connect_queue(struct nvme_fc_ctrl *ctrl, struct nvme_fc_queue *queue,
 				sizeof(struct fcnvme_lsdesc_cr_conn_cmd));
 	conn_rqst->connect_cmd.ersp_ratio = cpu_to_be16(ersp_ratio);
 	conn_rqst->connect_cmd.qid  = cpu_to_be16(queue->qnum);
-	conn_rqst->connect_cmd.sqsize = cpu_to_be16(qsize);
+	conn_rqst->connect_cmd.sqsize = cpu_to_be16(qsize - 1);
 
 	lsop->queue = queue;
 	lsreq->rqstaddr = conn_rqst;
@@ -2481,11 +2481,11 @@ nvme_fc_create_io_queues(struct nvme_fc_ctrl *ctrl)
 		goto out_free_tag_set;
 	}
 
-	ret = nvme_fc_create_hw_io_queues(ctrl, ctrl->ctrl.opts->queue_size);
+	ret = nvme_fc_create_hw_io_queues(ctrl, ctrl->ctrl.sqsize + 1);
 	if (ret)
 		goto out_cleanup_blk_queue;
 
-	ret = nvme_fc_connect_io_queues(ctrl, ctrl->ctrl.opts->queue_size);
+	ret = nvme_fc_connect_io_queues(ctrl, ctrl->ctrl.sqsize + 1);
 	if (ret)
 		goto out_delete_hw_queues;
 
@@ -2532,11 +2532,11 @@ nvme_fc_reinit_io_queues(struct nvme_fc_ctrl *ctrl)
 	if (ret)
 		goto out_free_io_queues;
 
-	ret = nvme_fc_create_hw_io_queues(ctrl, ctrl->ctrl.opts->queue_size);
+	ret = nvme_fc_create_hw_io_queues(ctrl, ctrl->ctrl.sqsize + 1);
 	if (ret)
 		goto out_free_io_queues;
 
-	ret = nvme_fc_connect_io_queues(ctrl, ctrl->ctrl.opts->queue_size);
+	ret = nvme_fc_connect_io_queues(ctrl, ctrl->ctrl.sqsize + 1);
 	if (ret)
 		goto out_delete_hw_queues;
 
@@ -2632,13 +2632,12 @@ nvme_fc_create_association(struct nvme_fc_ctrl *ctrl)
 	nvme_fc_init_queue(ctrl, 0);
 
 	ret = __nvme_fc_create_hw_queue(ctrl, &ctrl->queues[0], 0,
-				NVME_AQ_BLK_MQ_DEPTH);
+				NVME_AQ_DEPTH);
 	if (ret)
 		goto out_free_queue;
 
 	ret = nvme_fc_connect_admin_queue(ctrl, &ctrl->queues[0],
-				NVME_AQ_BLK_MQ_DEPTH,
-				(NVME_AQ_BLK_MQ_DEPTH / 4));
+				NVME_AQ_DEPTH, (NVME_AQ_DEPTH / 4));
 	if (ret)
 		goto out_delete_hw_queue;
 
@@ -2666,7 +2665,7 @@ nvme_fc_create_association(struct nvme_fc_ctrl *ctrl)
 	}
 
 	ctrl->ctrl.sqsize =
-		min_t(int, NVME_CAP_MQES(ctrl->ctrl.cap) + 1, ctrl->ctrl.sqsize);
+		min_t(int, NVME_CAP_MQES(ctrl->ctrl.cap), ctrl->ctrl.sqsize);
 
 	ret = nvme_enable_ctrl(&ctrl->ctrl, ctrl->ctrl.cap);
 	if (ret)
@@ -2699,6 +2698,14 @@ nvme_fc_create_association(struct nvme_fc_ctrl *ctrl)
 		opts->queue_size = ctrl->ctrl.maxcmd;
 	}
 
+	if (opts->queue_size > ctrl->ctrl.sqsize + 1) {
+		/* warn if sqsize is lower than queue_size */
+		dev_warn(ctrl->ctrl.device,
+			"queue_size %zu > ctrl sqsize %u, clamping down\n",
+			opts->queue_size, ctrl->ctrl.sqsize + 1);
+		opts->queue_size = ctrl->ctrl.sqsize + 1;
+	}
+
 	ret = nvme_fc_init_aen_ops(ctrl);
 	if (ret)
 		goto out_term_aen_ops;
diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c
index b7e5c6db4d92..060f69e03427 100644
--- a/drivers/nvme/host/multipath.c
+++ b/drivers/nvme/host/multipath.c
@@ -210,25 +210,6 @@ void nvme_mpath_add_disk(struct nvme_ns_head *head)
 	mutex_unlock(&head->subsys->lock);
 }
 
-void nvme_mpath_add_disk_links(struct nvme_ns *ns)
-{
-	struct kobject *slave_disk_kobj, *holder_disk_kobj;
-
-	if (!ns->head->disk)
-		return;
-
-	slave_disk_kobj = &disk_to_dev(ns->disk)->kobj;
-	if (sysfs_create_link(ns->head->disk->slave_dir, slave_disk_kobj,
-			kobject_name(slave_disk_kobj)))
-		return;
-
-	holder_disk_kobj = &disk_to_dev(ns->head->disk)->kobj;
-	if (sysfs_create_link(ns->disk->part0.holder_dir, holder_disk_kobj,
-			kobject_name(holder_disk_kobj)))
-		sysfs_remove_link(ns->head->disk->slave_dir,
-			kobject_name(slave_disk_kobj));
-}
-
 void nvme_mpath_remove_disk(struct nvme_ns_head *head)
 {
 	if (!head->disk)
@@ -243,14 +224,3 @@ void nvme_mpath_remove_disk(struct nvme_ns_head *head)
 	blk_cleanup_queue(head->disk->queue);
 	put_disk(head->disk);
 }
-
-void nvme_mpath_remove_disk_links(struct nvme_ns *ns)
-{
-	if (!ns->head->disk)
-		return;
-
-	sysfs_remove_link(ns->disk->part0.holder_dir,
-			kobject_name(&disk_to_dev(ns->head->disk)->kobj));
-	sysfs_remove_link(ns->head->disk->slave_dir,
-			kobject_name(&disk_to_dev(ns->disk)->kobj));
-}
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index 0521e4707d1c..d733b14ede9d 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -410,9 +410,7 @@ bool nvme_req_needs_failover(struct request *req, blk_status_t error);
 void nvme_kick_requeue_lists(struct nvme_ctrl *ctrl);
 int nvme_mpath_alloc_disk(struct nvme_ctrl *ctrl,struct nvme_ns_head *head);
 void nvme_mpath_add_disk(struct nvme_ns_head *head);
-void nvme_mpath_add_disk_links(struct nvme_ns *ns);
 void nvme_mpath_remove_disk(struct nvme_ns_head *head);
-void nvme_mpath_remove_disk_links(struct nvme_ns *ns);
 
 static inline void nvme_mpath_clear_current_path(struct nvme_ns *ns)
 {
@@ -454,12 +452,6 @@ static inline void nvme_mpath_add_disk(struct nvme_ns_head *head)
 static inline void nvme_mpath_remove_disk(struct nvme_ns_head *head)
 {
 }
-static inline void nvme_mpath_add_disk_links(struct nvme_ns *ns)
-{
-}
-static inline void nvme_mpath_remove_disk_links(struct nvme_ns *ns)
-{
-}
 static inline void nvme_mpath_clear_current_path(struct nvme_ns *ns)
 {
 }
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 5933a5c732e8..b6f43b738f03 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -1153,12 +1153,6 @@ static bool nvme_should_reset(struct nvme_dev *dev, u32 csts)
 	if (!(csts & NVME_CSTS_CFS) && !nssro)
 		return false;
 
-	/* If PCI error recovery process is happening, we cannot reset or
-	 * the recovery mechanism will surely fail.
-	 */
-	if (pci_channel_offline(to_pci_dev(dev->dev)))
-		return false;
-
 	return true;
 }
 
@@ -1189,6 +1183,13 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req, bool reserved)
 	struct nvme_command cmd;
 	u32 csts = readl(dev->bar + NVME_REG_CSTS);
 
+	/* If PCI error recovery process is happening, we cannot reset or
+	 * the recovery mechanism will surely fail.
+	 */
+	mb();
+	if (pci_channel_offline(to_pci_dev(dev->dev)))
+		return BLK_EH_RESET_TIMER;
+
 	/*
 	 * Reset immediately if the controller is failed
 	 */
@@ -1913,7 +1914,7 @@ static int nvme_setup_io_queues(struct nvme_dev *dev)
 	int result, nr_io_queues;
 	unsigned long size;
 
-	nr_io_queues = num_present_cpus();
+	nr_io_queues = num_possible_cpus();
 	result = nvme_set_queue_count(&dev->ctrl, &nr_io_queues);
 	if (result < 0)
 		return result;