Merge tag 'for-5.18/drivers-2022-04-01' of git://git.kernel.dk/linux-block

Pull block driver fixes from Jens Axboe:
 "Followup block driver updates and fixes for the 5.18-rc1 merge window.
  In detail:

   - NVMe pull request
       - Fix multipath hang when disk goes live over reconnect (Anton
         Eidelman)
       - fix RCU hole that allowed for endless looping in multipath
         round robin (Chris Leech)
       - remove redundant assignment after left shift (Colin Ian King)
       - add quirks for Samsung X5 SSDs (Monish Kumar R)
       - fix the read-only state for zoned namespaces with unsupposed
         features (Pankaj Raghav)
       - use a private workqueue instead of the system workqueue in
         nvmet (Sagi Grimberg)
       - allow duplicate NSIDs for private namespaces (Sungup Moon)
       - expose use_threaded_interrupts read-only in sysfs (Xin Hao)"

   - nbd minor allocation fix (Zhang)

   - drbd fixes and maintainer addition (Lars, Jakob, Christoph)

   - n64cart build fix (Jackie)

   - loop compat ioctl fix (Carlos)

   - misc fixes (Colin, Dongli)"

* tag 'for-5.18/drivers-2022-04-01' of git://git.kernel.dk/linux-block:
  drbd: remove check of list iterator against head past the loop body
  drbd: remove usage of list iterator variable after loop
  nbd: fix possible overflow on 'first_minor' in nbd_dev_add()
  MAINTAINERS: add drbd co-maintainer
  drbd: fix potential silent data corruption
  loop: fix ioctl calls using compat_loop_info
  nvme-multipath: fix hang when disk goes live over reconnect
  nvme: fix RCU hole that allowed for endless looping in multipath round robin
  nvme: allow duplicate NSIDs for private namespaces
  nvmet: remove redundant assignment after left shift
  nvmet: use a private workqueue instead of the system workqueue
  nvme-pci: add quirks for Samsung X5 SSDs
  nvme-pci: expose use_threaded_interrupts read-only in sysfs
  nvme: fix the read-only state for zoned namespaces with unsupposed features
  n64cart: convert bi_disk to bi_bdev->bd_disk fix build
  xen/blkfront: fix comment for need_copy
  xen-blkback: remove redundant assignment to variable i

Author: torvalds

MAINTAINERS

@@ -6052,6 +6052,7 @@ F:	drivers/scsi/dpt/
 DRBD DRIVER
 M:	Philipp Reisner <philipp.reisner@linbit.com>
 M:	Lars Ellenberg <lars.ellenberg@linbit.com>
+M:	Christoph Böhmwalder <christoph.boehmwalder@linbit.com>
 L:	drbd-dev@lists.linbit.com
 S:	Supported
 W:	http://www.drbd.org

drivers/block/drbd/drbd_main.c

@@ -171,7 +171,7 @@ void tl_release(struct drbd_connection *connection, unsigned int barrier_nr,
 		unsigned int set_size)
 {
 	struct drbd_request *r;
-	struct drbd_request *req = NULL;
+	struct drbd_request *req = NULL, *tmp = NULL;
 	int expect_epoch = 0;
 	int expect_size = 0;
 
@@ -225,8 +225,11 @@ void tl_release(struct drbd_connection *connection, unsigned int barrier_nr,
 	 * to catch requests being barrier-acked "unexpectedly".
 	 * It usually should find the same req again, or some READ preceding it. */
 	list_for_each_entry(req, &connection->transfer_log, tl_requests)
-		if (req->epoch == expect_epoch)
+		if (req->epoch == expect_epoch) {
+			tmp = req;
 			break;
+		}
+	req = list_prepare_entry(tmp, &connection->transfer_log, tl_requests);
 	list_for_each_entry_safe_from(req, r, &connection->transfer_log, tl_requests) {
 		if (req->epoch != expect_epoch)
 			break;

drivers/block/drbd/drbd_req.c

@@ -180,7 +180,8 @@ void start_new_tl_epoch(struct drbd_connection *connection)
 void complete_master_bio(struct drbd_device *device,
 		struct bio_and_error *m)
 {
-	m->bio->bi_status = errno_to_blk_status(m->error);
+	if (unlikely(m->error))
+		m->bio->bi_status = errno_to_blk_status(m->error);
 	bio_endio(m->bio);
 	dec_ap_bio(device);
 }
@@ -332,17 +333,21 @@ static void set_if_null_req_next(struct drbd_peer_device *peer_device, struct dr
 static void advance_conn_req_next(struct drbd_peer_device *peer_device, struct drbd_request *req)
 {
 	struct drbd_connection *connection = peer_device ? peer_device->connection : NULL;
+	struct drbd_request *iter = req;
 	if (!connection)
 		return;
 	if (connection->req_next != req)
 		return;
-	list_for_each_entry_continue(req, &connection->transfer_log, tl_requests) {
-		const unsigned s = req->rq_state;
-		if (s & RQ_NET_QUEUED)
+
+	req = NULL;
+	list_for_each_entry_continue(iter, &connection->transfer_log, tl_requests) {
+		const unsigned int s = iter->rq_state;
+
+		if (s & RQ_NET_QUEUED) {
+			req = iter;
 			break;
+		}
 	}
-	if (&req->tl_requests == &connection->transfer_log)
-		req = NULL;
 	connection->req_next = req;
 }
 
@@ -358,17 +363,21 @@ static void set_if_null_req_ack_pending(struct drbd_peer_device *peer_device, st
 static void advance_conn_req_ack_pending(struct drbd_peer_device *peer_device, struct drbd_request *req)
 {
 	struct drbd_connection *connection = peer_device ? peer_device->connection : NULL;
+	struct drbd_request *iter = req;
 	if (!connection)
 		return;
 	if (connection->req_ack_pending != req)
 		return;
-	list_for_each_entry_continue(req, &connection->transfer_log, tl_requests) {
-		const unsigned s = req->rq_state;
-		if ((s & RQ_NET_SENT) && (s & RQ_NET_PENDING))
+
+	req = NULL;
+	list_for_each_entry_continue(iter, &connection->transfer_log, tl_requests) {
+		const unsigned int s = iter->rq_state;
+
+		if ((s & RQ_NET_SENT) && (s & RQ_NET_PENDING)) {
+			req = iter;
 			break;
+		}
 	}
-	if (&req->tl_requests == &connection->transfer_log)
-		req = NULL;
 	connection->req_ack_pending = req;
 }
 
@@ -384,17 +393,21 @@ static void set_if_null_req_not_net_done(struct drbd_peer_device *peer_device, s
 static void advance_conn_req_not_net_done(struct drbd_peer_device *peer_device, struct drbd_request *req)
 {
 	struct drbd_connection *connection = peer_device ? peer_device->connection : NULL;
+	struct drbd_request *iter = req;
 	if (!connection)
 		return;
 	if (connection->req_not_net_done != req)
 		return;
-	list_for_each_entry_continue(req, &connection->transfer_log, tl_requests) {
-		const unsigned s = req->rq_state;
-		if ((s & RQ_NET_SENT) && !(s & RQ_NET_DONE))
+
+	req = NULL;
+	list_for_each_entry_continue(iter, &connection->transfer_log, tl_requests) {
+		const unsigned int s = iter->rq_state;
+
+		if ((s & RQ_NET_SENT) && !(s & RQ_NET_DONE)) {
+			req = iter;
 			break;
+		}
 	}
-	if (&req->tl_requests == &connection->transfer_log)
-		req = NULL;
 	connection->req_not_net_done = req;
 }
 

drivers/block/loop.c

@@ -1591,6 +1591,7 @@ struct compat_loop_info {
 	compat_ulong_t	lo_inode;       /* ioctl r/o */
 	compat_dev_t	lo_rdevice;     /* ioctl r/o */
 	compat_int_t	lo_offset;
+	compat_int_t	lo_encrypt_type;        /* obsolete, ignored */
 	compat_int_t	lo_encrypt_key_size;    /* ioctl w/o */
 	compat_int_t	lo_flags;       /* ioctl r/o */
 	char		lo_name[LO_NAME_SIZE];

drivers/block/n64cart.c

@@ -88,7 +88,7 @@ static void n64cart_submit_bio(struct bio *bio)
 {
 	struct bio_vec bvec;
 	struct bvec_iter iter;
-	struct device *dev = bio->bi_disk->private_data;
+	struct device *dev = bio->bi_bdev->bd_disk->private_data;
 	u32 pos = bio->bi_iter.bi_sector << SECTOR_SHIFT;
 
 	bio_for_each_segment(bvec, bio, iter) {

drivers/block/nbd.c

@@ -1800,17 +1800,6 @@ static struct nbd_device *nbd_dev_add(int index, unsigned int refs)
 	refcount_set(&nbd->refs, 0);
 	INIT_LIST_HEAD(&nbd->list);
 	disk->major = NBD_MAJOR;
-
-	/* Too big first_minor can cause duplicate creation of
-	 * sysfs files/links, since index << part_shift might overflow, or
-	 * MKDEV() expect that the max bits of first_minor is 20.
-	 */
-	disk->first_minor = index << part_shift;
-	if (disk->first_minor < index || disk->first_minor > MINORMASK) {
-		err = -EINVAL;
-		goto out_free_work;
-	}
-
 	disk->minors = 1 << part_shift;
 	disk->fops = &nbd_fops;
 	disk->private_data = nbd;
@@ -1915,8 +1904,19 @@ static int nbd_genl_connect(struct sk_buff *skb, struct genl_info *info)
 	if (!netlink_capable(skb, CAP_SYS_ADMIN))
 		return -EPERM;
 
-	if (info->attrs[NBD_ATTR_INDEX])
+	if (info->attrs[NBD_ATTR_INDEX]) {
 		index = nla_get_u32(info->attrs[NBD_ATTR_INDEX]);
+
+		/*
+		 * Too big first_minor can cause duplicate creation of
+		 * sysfs files/links, since index << part_shift might overflow, or
+		 * MKDEV() expect that the max bits of first_minor is 20.
+		 */
+		if (index < 0 || index > MINORMASK >> part_shift) {
+			printk(KERN_ERR "nbd: illegal input index %d\n", index);
+			return -EINVAL;
+		}
+	}
 	if (!info->attrs[NBD_ATTR_SOCKETS]) {
 		printk(KERN_ERR "nbd: must specify at least one socket\n");
 		return -EINVAL;

drivers/block/xen-blkback/blkback.c

@@ -931,7 +931,7 @@ static int xen_blkbk_parse_indirect(struct blkif_request *req,
 	if (rc)
 		goto unmap;
 
-	for (n = 0, i = 0; n < nseg; n++) {
+	for (n = 0; n < nseg; n++) {
 		uint8_t first_sect, last_sect;
 
 		if ((n % SEGS_PER_INDIRECT_FRAME) == 0) {

drivers/block/xen-blkfront.c

@@ -576,7 +576,7 @@ struct setup_rw_req {
 	struct blkif_request *ring_req;
 	grant_ref_t gref_head;
 	unsigned int id;
-	/* Only used when persistent grant is used and it's a read request */
+	/* Only used when persistent grant is used and it's a write request */
 	bool need_copy;
 	unsigned int bvec_off;
 	char *bvec_data;

drivers/nvme/host/core.c

@@ -1830,9 +1830,6 @@ static void nvme_update_disk_info(struct gendisk *disk,
 	nvme_config_discard(disk, ns);
 	blk_queue_max_write_zeroes_sectors(disk->queue,
 					   ns->ctrl->max_zeroes_sectors);
-
-	set_disk_ro(disk, (id->nsattr & NVME_NS_ATTR_RO) ||
-		test_bit(NVME_NS_FORCE_RO, &ns->flags));
 }
 
 static inline bool nvme_first_scan(struct gendisk *disk)
@@ -1891,6 +1888,8 @@ static int nvme_update_ns_info(struct nvme_ns *ns, struct nvme_id_ns *id)
 			goto out_unfreeze;
 	}
 
+	set_disk_ro(ns->disk, (id->nsattr & NVME_NS_ATTR_RO) ||
+		test_bit(NVME_NS_FORCE_RO, &ns->flags));
 	set_bit(NVME_NS_READY, &ns->flags);
 	blk_mq_unfreeze_queue(ns->disk->queue);
 
@@ -1903,6 +1902,9 @@ static int nvme_update_ns_info(struct nvme_ns *ns, struct nvme_id_ns *id)
 	if (nvme_ns_head_multipath(ns->head)) {
 		blk_mq_freeze_queue(ns->head->disk->queue);
 		nvme_update_disk_info(ns->head->disk, ns, id);
+		set_disk_ro(ns->head->disk,
+			    (id->nsattr & NVME_NS_ATTR_RO) ||
+				    test_bit(NVME_NS_FORCE_RO, &ns->flags));
 		nvme_mpath_revalidate_paths(ns);
 		blk_stack_limits(&ns->head->disk->queue->limits,
 				 &ns->queue->limits, 0);
@@ -3589,15 +3591,20 @@ static const struct attribute_group *nvme_dev_attr_groups[] = {
 	NULL,
 };
 
-static struct nvme_ns_head *nvme_find_ns_head(struct nvme_subsystem *subsys,
+static struct nvme_ns_head *nvme_find_ns_head(struct nvme_ctrl *ctrl,
 		unsigned nsid)
 {
 	struct nvme_ns_head *h;
 
-	lockdep_assert_held(&subsys->lock);
+	lockdep_assert_held(&ctrl->subsys->lock);
 
-	list_for_each_entry(h, &subsys->nsheads, entry) {
-		if (h->ns_id != nsid)
+	list_for_each_entry(h, &ctrl->subsys->nsheads, entry) {
+		/*
+		 * Private namespaces can share NSIDs under some conditions.
+		 * In that case we can't use the same ns_head for namespaces
+		 * with the same NSID.
+		 */
+		if (h->ns_id != nsid || !nvme_is_unique_nsid(ctrl, h))
 			continue;
 		if (!list_empty(&h->list) && nvme_tryget_ns_head(h))
 			return h;
@@ -3791,7 +3798,7 @@ static int nvme_init_ns_head(struct nvme_ns *ns, unsigned nsid,
 	}
 
 	mutex_lock(&ctrl->subsys->lock);
-	head = nvme_find_ns_head(ctrl->subsys, nsid);
+	head = nvme_find_ns_head(ctrl, nsid);
 	if (!head) {
 		ret = nvme_subsys_check_duplicate_ids(ctrl->subsys, ids);
 		if (ret) {
@@ -3988,6 +3995,16 @@ static void nvme_ns_remove(struct nvme_ns *ns)
 	set_capacity(ns->disk, 0);
 	nvme_fault_inject_fini(&ns->fault_inject);
 
+	/*
+	 * Ensure that !NVME_NS_READY is seen by other threads to prevent
+	 * this ns going back into current_path.
+	 */
+	synchronize_srcu(&ns->head->srcu);
+
+	/* wait for concurrent submissions */
+	if (nvme_mpath_clear_current_path(ns))
+		synchronize_srcu(&ns->head->srcu);
+
 	mutex_lock(&ns->ctrl->subsys->lock);
 	list_del_rcu(&ns->siblings);
 	if (list_empty(&ns->head->list)) {
@@ -3999,10 +4016,6 @@ static void nvme_ns_remove(struct nvme_ns *ns)
 	/* guarantee not available in head->list */
 	synchronize_rcu();
 
-	/* wait for concurrent submissions */
-	if (nvme_mpath_clear_current_path(ns))
-		synchronize_srcu(&ns->head->srcu);
-
 	if (!nvme_ns_head_multipath(ns->head))
 		nvme_cdev_del(&ns->cdev, &ns->cdev_device);
 	del_gendisk(ns->disk);
@@ -4480,6 +4493,7 @@ void nvme_start_ctrl(struct nvme_ctrl *ctrl)
 	if (ctrl->queue_count > 1) {
 		nvme_queue_scan(ctrl);
 		nvme_start_queues(ctrl);
+		nvme_mpath_update(ctrl);
 	}
 
 	nvme_change_uevent(ctrl, "NVME_EVENT=connected");

drivers/nvme/host/multipath.c

@@ -482,10 +482,11 @@ int nvme_mpath_alloc_disk(struct nvme_ctrl *ctrl, struct nvme_ns_head *head)
 
 	/*
 	 * Add a multipath node if the subsystems supports multiple controllers.
-	 * We also do this for private namespaces as the namespace sharing data could
-	 * change after a rescan.
+	 * We also do this for private namespaces as the namespace sharing flag
+	 * could change after a rescan.
 	 */
-	if (!(ctrl->subsys->cmic & NVME_CTRL_CMIC_MULTI_CTRL) || !multipath)
+	if (!(ctrl->subsys->cmic & NVME_CTRL_CMIC_MULTI_CTRL) ||
+	    !nvme_is_unique_nsid(ctrl, head) || !multipath)
 		return 0;
 
 	head->disk = blk_alloc_disk(ctrl->numa_node);
@@ -612,8 +613,17 @@ static void nvme_update_ns_ana_state(struct nvme_ana_group_desc *desc,
 	ns->ana_grpid = le32_to_cpu(desc->grpid);
 	ns->ana_state = desc->state;
 	clear_bit(NVME_NS_ANA_PENDING, &ns->flags);
-
-	if (nvme_state_is_live(ns->ana_state))
+	/*
+	 * nvme_mpath_set_live() will trigger I/O to the multipath path device
+	 * and in turn to this path device.  However we cannot accept this I/O
+	 * if the controller is not live.  This may deadlock if called from
+	 * nvme_mpath_init_identify() and the ctrl will never complete
+	 * initialization, preventing I/O from completing.  For this case we
+	 * will reprocess the ANA log page in nvme_mpath_update() once the
+	 * controller is ready.
+	 */
+	if (nvme_state_is_live(ns->ana_state) &&
+	    ns->ctrl->state == NVME_CTRL_LIVE)
 		nvme_mpath_set_live(ns);
 }
 
@@ -700,6 +710,18 @@ static void nvme_ana_work(struct work_struct *work)
 	nvme_read_ana_log(ctrl);
 }
 
+void nvme_mpath_update(struct nvme_ctrl *ctrl)
+{
+	u32 nr_change_groups = 0;
+
+	if (!ctrl->ana_log_buf)
+		return;
+
+	mutex_lock(&ctrl->ana_lock);
+	nvme_parse_ana_log(ctrl, &nr_change_groups, nvme_update_ana_state);
+	mutex_unlock(&ctrl->ana_lock);
+}
+
 static void nvme_anatt_timeout(struct timer_list *t)
 {
 	struct nvme_ctrl *ctrl = from_timer(ctrl, t, anatt_timer);