Merge tag 'block-5.16-2021-12-10' of git://git.kernel.dk/linux-block

Pull block fixes from Jens Axboe:
 "A few block fixes that should go into this release:

   - NVMe pull request:
        - set ana_log_size to 0 after freeing ana_log_buf (Hou Tao)
        - show subsys nqn for duplicate cntlids (Keith Busch)
        - disable namespace access for unsupported metadata (Keith
          Busch)
        - report write pointer for a full zone as zone start + zone len
          (Niklas Cassel)
        - fix use after free when disconnecting a reconnecting ctrl
          (Ruozhu Li)
        - fix a list corruption in nvmet-tcp (Sagi Grimberg)

   - Fix for a regression on DIO single bio async IO (Pavel)

   - ioprio seteuid fix (Davidlohr)

   - mtd fix that subsequently got reverted as it was broken, will get
     re-done and submitted for the next round

   - Two MD fixes via Song (Markus, zhangyue)"

* tag 'block-5.16-2021-12-10' of git://git.kernel.dk/linux-block:
  Revert "mtd_blkdevs: don't scan partitions for plain mtdblock"
  block: fix ioprio_get(IOPRIO_WHO_PGRP) vs setuid(2)
  md: fix double free of mddev->private in autorun_array()
  md: fix update super 1.0 on rdev size change
  nvmet-tcp: fix possible list corruption for unexpected command failure
  block: fix single bio async DIO error handling
  nvme: fix use after free when disconnecting a reconnecting ctrl
  nvme-multipath: set ana_log_size to 0 after free ana_log_buf
  mtd_blkdevs: don't scan partitions for plain mtdblock
  nvme: report write pointer for a full zone as zone start + zone len
  nvme: disable namespace access for unsupported metadata
  nvme: show subsys nqn for duplicate cntlids

8 files changed, 40 insertions, 12 deletions

diff --git a/block/fops.c b/block/fops.c
index 3cb1e81929bc6..0da147edbd186 100644
--- a/block/fops.c
+++ b/block/fops.c
@@ -341,8 +341,7 @@ static ssize_t __blkdev_direct_IO_async(struct kiocb *iocb,
 	} else {
 		ret = bio_iov_iter_get_pages(bio, iter);
 		if (unlikely(ret)) {
-			bio->bi_status = BLK_STS_IOERR;
-			bio_endio(bio);
+			bio_put(bio);
 			return ret;
 		}
 	}
diff --git a/block/ioprio.c b/block/ioprio.c
index 313c14a70bbd3..6f01d35a5145a 100644
--- a/block/ioprio.c
+++ b/block/ioprio.c
@@ -220,6 +220,7 @@ SYSCALL_DEFINE2(ioprio_get, int, which, int, who)
 				pgrp = task_pgrp(current);
 			else
 				pgrp = find_vpid(who);
+			read_lock(&tasklist_lock);
 			do_each_pid_thread(pgrp, PIDTYPE_PGID, p) {
 				tmpio = get_task_ioprio(p);
 				if (tmpio < 0)
@@ -229,6 +230,8 @@ SYSCALL_DEFINE2(ioprio_get, int, which, int, who)
 				else
 					ret = ioprio_best(ret, tmpio);
 			} while_each_pid_thread(pgrp, PIDTYPE_PGID, p);
+			read_unlock(&tasklist_lock);
+
 			break;
 		case IOPRIO_WHO_USER:
 			uid = make_kuid(current_user_ns(), who);
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 5111ed966947e..41d6e2383517b 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -2189,6 +2189,7 @@ super_1_rdev_size_change(struct md_rdev *rdev, sector_t num_sectors)
 
 		if (!num_sectors || num_sectors > max_sectors)
 			num_sectors = max_sectors;
+		rdev->sb_start = sb_start;
 	}
 	sb = page_address(rdev->sb_page);
 	sb->data_size = cpu_to_le64(num_sectors);
@@ -6270,7 +6271,8 @@ static void __md_stop(struct mddev *mddev)
 	spin_lock(&mddev->lock);
 	mddev->pers = NULL;
 	spin_unlock(&mddev->lock);
-	pers->free(mddev, mddev->private);
+	if (mddev->private)
+		pers->free(mddev, mddev->private);
 	mddev->private = NULL;
 	if (pers->sync_request && mddev->to_remove == NULL)
 		mddev->to_remove = &md_redundancy_group;
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 4c63564adeaa6..1af8a4513708a 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -666,6 +666,7 @@ blk_status_t nvme_fail_nonready_command(struct nvme_ctrl *ctrl,
 		struct request *rq)
 {
 	if (ctrl->state != NVME_CTRL_DELETING_NOIO &&
+	    ctrl->state != NVME_CTRL_DELETING &&
 	    ctrl->state != NVME_CTRL_DEAD &&
 	    !test_bit(NVME_CTRL_FAILFAST_EXPIRED, &ctrl->flags) &&
 	    !blk_noretry_request(rq) && !(rq->cmd_flags & REQ_NVME_MPATH))
@@ -1749,9 +1750,20 @@ static int nvme_configure_metadata(struct nvme_ns *ns, struct nvme_id_ns *id)
 		 */
 		if (WARN_ON_ONCE(!(id->flbas & NVME_NS_FLBAS_META_EXT)))
 			return -EINVAL;
-		if (ctrl->max_integrity_segments)
-			ns->features |=
-				(NVME_NS_METADATA_SUPPORTED | NVME_NS_EXT_LBAS);
+
+		ns->features |= NVME_NS_EXT_LBAS;
+
+		/*
+		 * The current fabrics transport drivers support namespace
+		 * metadata formats only if nvme_ns_has_pi() returns true.
+		 * Suppress support for all other formats so the namespace will
+		 * have a 0 capacity and not be usable through the block stack.
+		 *
+		 * Note, this check will need to be modified if any drivers
+		 * gain the ability to use other metadata formats.
+		 */
+		if (ctrl->max_integrity_segments && nvme_ns_has_pi(ns))
+			ns->features |= NVME_NS_METADATA_SUPPORTED;
 	} else {
 		/*
 		 * For PCIe controllers, we can't easily remap the separate
@@ -2696,8 +2708,9 @@ static bool nvme_validate_cntlid(struct nvme_subsystem *subsys,
 
 		if (tmp->cntlid == ctrl->cntlid) {
 			dev_err(ctrl->device,
-				"Duplicate cntlid %u with %s, rejecting\n",
-				ctrl->cntlid, dev_name(tmp->device));
+				"Duplicate cntlid %u with %s, subsys %s, rejecting\n",
+				ctrl->cntlid, dev_name(tmp->device),
+				subsys->subnqn);
 			return false;
 		}
 
diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c
index 7f2071f2460c8..13e5d503ed076 100644
--- a/drivers/nvme/host/multipath.c
+++ b/drivers/nvme/host/multipath.c
@@ -866,7 +866,7 @@ 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);
-		kfree(ctrl->ana_log_buf);
+		nvme_mpath_uninit(ctrl);
 		ctrl->ana_log_buf = kmalloc(ana_log_size, GFP_KERNEL);
 		if (!ctrl->ana_log_buf)
 			return -ENOMEM;
@@ -886,4 +886,5 @@ void nvme_mpath_uninit(struct nvme_ctrl *ctrl)
 {
 	kfree(ctrl->ana_log_buf);
 	ctrl->ana_log_buf = NULL;
+	ctrl->ana_log_size = 0;
 }
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index b334af8aa2642..9b095ee013649 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -709,7 +709,7 @@ static inline bool nvme_check_ready(struct nvme_ctrl *ctrl, struct request *rq,
 		return true;
 	if (ctrl->ops->flags & NVME_F_FABRICS &&
 	    ctrl->state == NVME_CTRL_DELETING)
-		return true;
+		return queue_live;
 	return __nvme_check_ready(ctrl, rq, queue_live);
 }
 int nvme_submit_sync_cmd(struct request_queue *q, struct nvme_command *cmd,
diff --git a/drivers/nvme/host/zns.c b/drivers/nvme/host/zns.c
index bfc259e0d7b87..9f81beb4df4ef 100644
--- a/drivers/nvme/host/zns.c
+++ b/drivers/nvme/host/zns.c
@@ -166,7 +166,10 @@ static int nvme_zone_parse_entry(struct nvme_ns *ns,
 	zone.len = ns->zsze;
 	zone.capacity = nvme_lba_to_sect(ns, le64_to_cpu(entry->zcap));
 	zone.start = nvme_lba_to_sect(ns, le64_to_cpu(entry->zslba));
-	zone.wp = nvme_lba_to_sect(ns, le64_to_cpu(entry->wp));
+	if (zone.cond == BLK_ZONE_COND_FULL)
+		zone.wp = zone.start + zone.len;
+	else
+		zone.wp = nvme_lba_to_sect(ns, le64_to_cpu(entry->wp));
 
 	return cb(&zone, idx, data);
 }
diff --git a/drivers/nvme/target/tcp.c b/drivers/nvme/target/tcp.c
index cb6a473c3eafa..7c1c43ce466bc 100644
--- a/drivers/nvme/target/tcp.c
+++ b/drivers/nvme/target/tcp.c
@@ -922,7 +922,14 @@ static void nvmet_tcp_handle_req_failure(struct nvmet_tcp_queue *queue,
 	size_t data_len = le32_to_cpu(req->cmd->common.dptr.sgl.length);
 	int ret;
 
-	if (!nvme_is_write(cmd->req.cmd) ||
+	/*
+	 * This command has not been processed yet, hence we are trying to
+	 * figure out if there is still pending data left to receive. If
+	 * we don't, we can simply prepare for the next pdu and bail out,
+	 * otherwise we will need to prepare a buffer and receive the
+	 * stale data before continuing forward.
+	 */
+	if (!nvme_is_write(cmd->req.cmd) || !data_len ||
 	    data_len > cmd->req.port->inline_data_size) {
 		nvmet_prepare_receive_pdu(queue);
 		return;