Merge tag 'block-6.16-20250606' of git://git.kernel.dk/linux

Pull more block updates from Jens Axboe:

 - NVMe pull request via Christoph:
      - TCP error handling fix (Shin'ichiro Kawasaki)
      - TCP I/O stall handling fixes (Hannes Reinecke)
      - fix command limits status code (Keith Busch)
      - support vectored buffers also for passthrough (Pavel Begunkov)
      - spelling fixes (Yi Zhang)

 - MD pull request via Yu:
      - fix REQ_RAHEAD and REQ_NOWAIT IO err handling for raid1/10
      - fix max_write_behind setting for dm-raid
      - some minor cleanups

 - Integrity data direction fix and cleanup

 - bcache NULL pointer fix

 - Fix for loop missing write start/end handling

 - Decouple hardware queues and IO threads in ublk

 - Slew of ublk selftests additions and updates

* tag 'block-6.16-20250606' of git://git.kernel.dk/linux: (29 commits)
  nvme: spelling fixes
  nvme-tcp: fix I/O stalls on congested sockets
  nvme-tcp: sanitize request list handling
  nvme-tcp: remove tag set when second admin queue config fails
  nvme: enable vectored registered bufs for passthrough cmds
  nvme: fix implicit bool to flags conversion
  nvme: fix command limits status code
  selftests: ublk: kublk: improve behavior on init failure
  block: flip iter directions in blk_rq_integrity_map_user()
  block: drop direction param from bio_integrity_copy_user()
  selftests: ublk: cover PER_IO_DAEMON in more stress tests
  Documentation: ublk: document UBLK_F_PER_IO_DAEMON
  selftests: ublk: add stress test for per io daemons
  selftests: ublk: add functional test for per io daemons
  selftests: ublk: kublk: decouple ublk_queues from ublk server threads
  selftests: ublk: kublk: move per-thread data out of ublk_queue
  selftests: ublk: kublk: lift queue initialization out of thread
  selftests: ublk: kublk: tie sqe allocation to io instead of queue
  selftests: ublk: kublk: plumb q_id in io_uring user_data
  ublk: have a per-io daemon instead of a per-queue daemon
  ...

30 files changed, 224 insertions, 173 deletions

diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index e2b1f377f585..f8d136684109 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -308,11 +308,14 @@ end_io:
 static void lo_rw_aio_do_completion(struct loop_cmd *cmd)
 {
 	struct request *rq = blk_mq_rq_from_pdu(cmd);
+	struct loop_device *lo = rq->q->queuedata;
 
 	if (!atomic_dec_and_test(&cmd->ref))
 		return;
 	kfree(cmd->bvec);
 	cmd->bvec = NULL;
+	if (req_op(rq) == REQ_OP_WRITE)
+		file_end_write(lo->lo_backing_file);
 	if (likely(!blk_should_fake_timeout(rq->q)))
 		blk_mq_complete_request(rq);
 }
@@ -387,9 +390,10 @@ static int lo_rw_aio(struct loop_device *lo, struct loop_cmd *cmd,
 		cmd->iocb.ki_flags = 0;
 	}
 
-	if (rw == ITER_SOURCE)
+	if (rw == ITER_SOURCE) {
+		file_start_write(lo->lo_backing_file);
 		ret = file->f_op->write_iter(&cmd->iocb, &iter);
-	else
+	} else
 		ret = file->f_op->read_iter(&cmd->iocb, &iter);
 
 	lo_rw_aio_do_completion(cmd);
diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c
index 6f51072776f1..c637ea010d34 100644
--- a/drivers/block/ublk_drv.c
+++ b/drivers/block/ublk_drv.c
@@ -69,7 +69,8 @@
 		| UBLK_F_USER_RECOVERY_FAIL_IO \
 		| UBLK_F_UPDATE_SIZE \
 		| UBLK_F_AUTO_BUF_REG \
-		| UBLK_F_QUIESCE)
+		| UBLK_F_QUIESCE \
+		| UBLK_F_PER_IO_DAEMON)
 
 #define UBLK_F_ALL_RECOVERY_FLAGS (UBLK_F_USER_RECOVERY \
 		| UBLK_F_USER_RECOVERY_REISSUE \
@@ -166,6 +167,8 @@ struct ublk_io {
 		/* valid if UBLK_IO_FLAG_OWNED_BY_SRV is set */
 		struct request *req;
 	};
+
+	struct task_struct *task;
 };
 
 struct ublk_queue {
@@ -173,11 +176,9 @@ struct ublk_queue {
 	int q_depth;
 
 	unsigned long flags;
-	struct task_struct	*ubq_daemon;
 	struct ublksrv_io_desc *io_cmd_buf;
 
 	bool force_abort;
-	bool timeout;
 	bool canceling;
 	bool fail_io; /* copy of dev->state == UBLK_S_DEV_FAIL_IO */
 	unsigned short nr_io_ready;	/* how many ios setup */
@@ -1099,11 +1100,6 @@ static inline struct ublk_uring_cmd_pdu *ublk_get_uring_cmd_pdu(
 	return io_uring_cmd_to_pdu(ioucmd, struct ublk_uring_cmd_pdu);
 }
 
-static inline bool ubq_daemon_is_dying(struct ublk_queue *ubq)
-{
-	return !ubq->ubq_daemon || ubq->ubq_daemon->flags & PF_EXITING;
-}
-
 /* todo: handle partial completion */
 static inline void __ublk_complete_rq(struct request *req)
 {
@@ -1275,13 +1271,13 @@ static void ublk_dispatch_req(struct ublk_queue *ubq,
 	/*
 	 * Task is exiting if either:
 	 *
-	 * (1) current != ubq_daemon.
+	 * (1) current != io->task.
 	 * io_uring_cmd_complete_in_task() tries to run task_work
-	 * in a workqueue if ubq_daemon(cmd's task) is PF_EXITING.
+	 * in a workqueue if cmd's task is PF_EXITING.
 	 *
 	 * (2) current->flags & PF_EXITING.
 	 */
-	if (unlikely(current != ubq->ubq_daemon || current->flags & PF_EXITING)) {
+	if (unlikely(current != io->task || current->flags & PF_EXITING)) {
 		__ublk_abort_rq(ubq, req);
 		return;
 	}
@@ -1330,24 +1326,22 @@ static void ublk_cmd_list_tw_cb(struct io_uring_cmd *cmd,
 {
 	struct ublk_uring_cmd_pdu *pdu = ublk_get_uring_cmd_pdu(cmd);
 	struct request *rq = pdu->req_list;
-	struct ublk_queue *ubq = pdu->ubq;
 	struct request *next;
 
 	do {
 		next = rq->rq_next;
 		rq->rq_next = NULL;
-		ublk_dispatch_req(ubq, rq, issue_flags);
+		ublk_dispatch_req(rq->mq_hctx->driver_data, rq, issue_flags);
 		rq = next;
 	} while (rq);
 }
 
-static void ublk_queue_cmd_list(struct ublk_queue *ubq, struct rq_list *l)
+static void ublk_queue_cmd_list(struct ublk_io *io, struct rq_list *l)
 {
-	struct request *rq = rq_list_peek(l);
-	struct io_uring_cmd *cmd = ubq->ios[rq->tag].cmd;
+	struct io_uring_cmd *cmd = io->cmd;
 	struct ublk_uring_cmd_pdu *pdu = ublk_get_uring_cmd_pdu(cmd);
 
-	pdu->req_list = rq;
+	pdu->req_list = rq_list_peek(l);
 	rq_list_init(l);
 	io_uring_cmd_complete_in_task(cmd, ublk_cmd_list_tw_cb);
 }
@@ -1355,13 +1349,10 @@ static void ublk_queue_cmd_list(struct ublk_queue *ubq, struct rq_list *l)
 static enum blk_eh_timer_return ublk_timeout(struct request *rq)
 {
 	struct ublk_queue *ubq = rq->mq_hctx->driver_data;
+	struct ublk_io *io = &ubq->ios[rq->tag];
 
 	if (ubq->flags & UBLK_F_UNPRIVILEGED_DEV) {
-		if (!ubq->timeout) {
-			send_sig(SIGKILL, ubq->ubq_daemon, 0);
-			ubq->timeout = true;
-		}
-
+		send_sig(SIGKILL, io->task, 0);
 		return BLK_EH_DONE;
 	}
 
@@ -1429,24 +1420,25 @@ static void ublk_queue_rqs(struct rq_list *rqlist)
 {
 	struct rq_list requeue_list = { };
 	struct rq_list submit_list = { };
-	struct ublk_queue *ubq = NULL;
+	struct ublk_io *io = NULL;
 	struct request *req;
 
 	while ((req = rq_list_pop(rqlist))) {
 		struct ublk_queue *this_q = req->mq_hctx->driver_data;
+		struct ublk_io *this_io = &this_q->ios[req->tag];
 
-		if (ubq && ubq != this_q && !rq_list_empty(&submit_list))
-			ublk_queue_cmd_list(ubq, &submit_list);
-		ubq = this_q;
+		if (io && io->task != this_io->task && !rq_list_empty(&submit_list))
+			ublk_queue_cmd_list(io, &submit_list);
+		io = this_io;
 
-		if (ublk_prep_req(ubq, req, true) == BLK_STS_OK)
+		if (ublk_prep_req(this_q, req, true) == BLK_STS_OK)
 			rq_list_add_tail(&submit_list, req);
 		else
 			rq_list_add_tail(&requeue_list, req);
 	}
 
-	if (ubq && !rq_list_empty(&submit_list))
-		ublk_queue_cmd_list(ubq, &submit_list);
+	if (!rq_list_empty(&submit_list))
+		ublk_queue_cmd_list(io, &submit_list);
 	*rqlist = requeue_list;
 }
 
@@ -1474,17 +1466,6 @@ static void ublk_queue_reinit(struct ublk_device *ub, struct ublk_queue *ubq)
 	/* All old ioucmds have to be completed */
 	ubq->nr_io_ready = 0;
 
-	/*
-	 * old daemon is PF_EXITING, put it now
-	 *
-	 * It could be NULL in case of closing one quisced device.
-	 */
-	if (ubq->ubq_daemon)
-		put_task_struct(ubq->ubq_daemon);
-	/* We have to reset it to NULL, otherwise ub won't accept new FETCH_REQ */
-	ubq->ubq_daemon = NULL;
-	ubq->timeout = false;
-
 	for (i = 0; i < ubq->q_depth; i++) {
 		struct ublk_io *io = &ubq->ios[i];
 
@@ -1495,6 +1476,17 @@ static void ublk_queue_reinit(struct ublk_device *ub, struct ublk_queue *ubq)
 		io->flags &= UBLK_IO_FLAG_CANCELED;
 		io->cmd = NULL;
 		io->addr = 0;
+
+		/*
+		 * old task is PF_EXITING, put it now
+		 *
+		 * It could be NULL in case of closing one quiesced
+		 * device.
+		 */
+		if (io->task) {
+			put_task_struct(io->task);
+			io->task = NULL;
+		}
 	}
 }
 
@@ -1516,7 +1508,7 @@ static void ublk_reset_ch_dev(struct ublk_device *ub)
 	for (i = 0; i < ub->dev_info.nr_hw_queues; i++)
 		ublk_queue_reinit(ub, ublk_get_queue(ub, i));
 
-	/* set to NULL, otherwise new ubq_daemon cannot mmap the io_cmd_buf */
+	/* set to NULL, otherwise new tasks cannot mmap io_cmd_buf */
 	ub->mm = NULL;
 	ub->nr_queues_ready = 0;
 	ub->nr_privileged_daemon = 0;
@@ -1783,6 +1775,7 @@ static void ublk_uring_cmd_cancel_fn(struct io_uring_cmd *cmd,
 	struct ublk_uring_cmd_pdu *pdu = ublk_get_uring_cmd_pdu(cmd);
 	struct ublk_queue *ubq = pdu->ubq;
 	struct task_struct *task;
+	struct ublk_io *io;
 
 	if (WARN_ON_ONCE(!ubq))
 		return;
@@ -1791,13 +1784,14 @@ static void ublk_uring_cmd_cancel_fn(struct io_uring_cmd *cmd,
 		return;
 
 	task = io_uring_cmd_get_task(cmd);
-	if (WARN_ON_ONCE(task && task != ubq->ubq_daemon))
+	io = &ubq->ios[pdu->tag];
+	if (WARN_ON_ONCE(task && task != io->task))
 		return;
 
 	if (!ubq->canceling)
 		ublk_start_cancel(ubq);
 
-	WARN_ON_ONCE(ubq->ios[pdu->tag].cmd != cmd);
+	WARN_ON_ONCE(io->cmd != cmd);
 	ublk_cancel_cmd(ubq, pdu->tag, issue_flags);
 }
 
@@ -1930,8 +1924,6 @@ static void ublk_mark_io_ready(struct ublk_device *ub, struct ublk_queue *ubq)
 {
 	ubq->nr_io_ready++;
 	if (ublk_queue_ready(ubq)) {
-		ubq->ubq_daemon = current;
-		get_task_struct(ubq->ubq_daemon);
 		ub->nr_queues_ready++;
 
 		if (capable(CAP_SYS_ADMIN))
@@ -2084,6 +2076,7 @@ static int ublk_fetch(struct io_uring_cmd *cmd, struct ublk_queue *ubq,
 	}
 
 	ublk_fill_io_cmd(io, cmd, buf_addr);
+	WRITE_ONCE(io->task, get_task_struct(current));
 	ublk_mark_io_ready(ub, ubq);
 out:
 	mutex_unlock(&ub->mutex);
@@ -2179,6 +2172,7 @@ static int __ublk_ch_uring_cmd(struct io_uring_cmd *cmd,
 			       const struct ublksrv_io_cmd *ub_cmd)
 {
 	struct ublk_device *ub = cmd->file->private_data;
+	struct task_struct *task;
 	struct ublk_queue *ubq;
 	struct ublk_io *io;
 	u32 cmd_op = cmd->cmd_op;
@@ -2193,13 +2187,14 @@ static int __ublk_ch_uring_cmd(struct io_uring_cmd *cmd,
 		goto out;
 
 	ubq = ublk_get_queue(ub, ub_cmd->q_id);
-	if (ubq->ubq_daemon && ubq->ubq_daemon != current)
-		goto out;
 
 	if (tag >= ubq->q_depth)
 		goto out;
 
 	io = &ubq->ios[tag];
+	task = READ_ONCE(io->task);
+	if (task && task != current)
+		goto out;
 
 	/* there is pending io cmd, something must be wrong */
 	if (io->flags & UBLK_IO_FLAG_ACTIVE) {
@@ -2449,9 +2444,14 @@ static void ublk_deinit_queue(struct ublk_device *ub, int q_id)
 {
 	int size = ublk_queue_cmd_buf_size(ub, q_id);
 	struct ublk_queue *ubq = ublk_get_queue(ub, q_id);
+	int i;
+
+	for (i = 0; i < ubq->q_depth; i++) {
+		struct ublk_io *io = &ubq->ios[i];
+		if (io->task)
+			put_task_struct(io->task);
+	}
 
-	if (ubq->ubq_daemon)
-		put_task_struct(ubq->ubq_daemon);
 	if (ubq->io_cmd_buf)
 		free_pages((unsigned long)ubq->io_cmd_buf, get_order(size));
 }
@@ -2923,7 +2923,8 @@ static int ublk_ctrl_add_dev(const struct ublksrv_ctrl_cmd *header)
 	ub->dev_info.flags &= UBLK_F_ALL;
 
 	ub->dev_info.flags |= UBLK_F_CMD_IOCTL_ENCODE |
-		UBLK_F_URING_CMD_COMP_IN_TASK;
+		UBLK_F_URING_CMD_COMP_IN_TASK |
+		UBLK_F_PER_IO_DAEMON;
 
 	/* GET_DATA isn't needed any more with USER_COPY or ZERO COPY */
 	if (ub->dev_info.flags & (UBLK_F_USER_COPY | UBLK_F_SUPPORT_ZERO_COPY |
@@ -3188,14 +3189,14 @@ static int ublk_ctrl_end_recovery(struct ublk_device *ub,
 	int ublksrv_pid = (int)header->data[0];
 	int ret = -EINVAL;
 
-	pr_devel("%s: Waiting for new ubq_daemons(nr: %d) are ready, dev id %d...\n",
-			__func__, ub->dev_info.nr_hw_queues, header->dev_id);
-	/* wait until new ubq_daemon sending all FETCH_REQ */
+	pr_devel("%s: Waiting for all FETCH_REQs, dev id %d...\n", __func__,
+		 header->dev_id);
+
 	if (wait_for_completion_interruptible(&ub->completion))
 		return -EINTR;
 
-	pr_devel("%s: All new ubq_daemons(nr: %d) are ready, dev id %d\n",
-			__func__, ub->dev_info.nr_hw_queues, header->dev_id);
+	pr_devel("%s: All FETCH_REQs received, dev id %d\n", __func__,
+		 header->dev_id);
 
 	mutex_lock(&ub->mutex);
 	if (ublk_nosrv_should_stop_dev(ub))
diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c
index 2cc2eb24dc8a..1d0100677357 100644
--- a/drivers/md/bcache/btree.c
+++ b/drivers/md/bcache/btree.c
@@ -89,8 +89,6 @@
  * Test module load/unload
  */
 
-#define MAX_NEED_GC		64
-#define MAX_SAVE_PRIO		72
 #define MAX_GC_TIMES		100
 #define MIN_GC_NODES		100
 #define GC_SLEEP_MS		100
diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c
index 1a2ce1a4b456..1efb768b2890 100644
--- a/drivers/md/bcache/super.c
+++ b/drivers/md/bcache/super.c
@@ -1733,7 +1733,12 @@ static CLOSURE_CALLBACK(cache_set_flush)
 			mutex_unlock(&b->write_lock);
 		}
 
-	if (ca->alloc_thread)
+	/*
+	 * If the register_cache_set() call to bch_cache_set_alloc() failed,
+	 * ca has not been assigned a value and return error.
+	 * So we need check ca is not NULL during bch_cache_set_unregister().
+	 */
+	if (ca && ca->alloc_thread)
 		kthread_stop(ca->alloc_thread);
 
 	if (c->journal.cur) {
@@ -2233,15 +2238,47 @@ static int cache_alloc(struct cache *ca)
 	bio_init(&ca->journal.bio, NULL, ca->journal.bio.bi_inline_vecs, 8, 0);
 
 	/*
-	 * when ca->sb.njournal_buckets is not zero, journal exists,
-	 * and in bch_journal_replay(), tree node may split,
-	 * so bucket of RESERVE_BTREE type is needed,
-	 * the worst situation is all journal buckets are valid journal,
-	 * and all the keys need to replay,
-	 * so the number of  RESERVE_BTREE type buckets should be as much
-	 * as journal buckets
+	 * When the cache disk is first registered, ca->sb.njournal_buckets
+	 * is zero, and it is assigned in run_cache_set().
+	 *
+	 * When ca->sb.njournal_buckets is not zero, journal exists,
+	 * and in bch_journal_replay(), tree node may split.
+	 * The worst situation is all journal buckets are valid journal,
+	 * and all the keys need to replay, so the number of RESERVE_BTREE
+	 * type buckets should be as much as journal buckets.
+	 *
+	 * If the number of RESERVE_BTREE type buckets is too few, the
+	 * bch_allocator_thread() may hang up and unable to allocate
+	 * bucket. The situation is roughly as follows:
+	 *
+	 * 1. In bch_data_insert_keys(), if the operation is not op->replace,
+	 *    it will call the bch_journal(), which increments the journal_ref
+	 *    counter. This counter is only decremented after bch_btree_insert
+	 *    completes.
+	 *
+	 * 2. When calling bch_btree_insert, if the btree needs to split,
+	 *    it will call btree_split() and btree_check_reserve() to check
+	 *    whether there are enough reserved buckets in the RESERVE_BTREE
+	 *    slot. If not enough, bcache_btree_root() will repeatedly retry.
+	 *
+	 * 3. Normally, the bch_allocator_thread is responsible for filling
+	 *    the reservation slots from the free_inc bucket list. When the
+	 *    free_inc bucket list is exhausted, the bch_allocator_thread
+	 *    will call invalidate_buckets() until free_inc is refilled.
+	 *    Then bch_allocator_thread calls bch_prio_write() once. and
+	 *    bch_prio_write() will call bch_journal_meta() and waits for
+	 *    the journal write to complete.
+	 *
+	 * 4. During journal_write, journal_write_unlocked() is be called.
+	 *    If journal full occurs, journal_reclaim() and btree_flush_write()
+	 *    will be called sequentially, then retry journal_write.
+	 *
+	 * 5. When 2 and 4 occur together, IO will hung up and cannot recover.
+	 *
+	 * Therefore, reserve more RESERVE_BTREE type buckets.
 	 */
-	btree_buckets = ca->sb.njournal_buckets ?: 8;
+	btree_buckets = clamp_t(size_t, ca->sb.nbuckets >> 7,
+				32, SB_JOURNAL_BUCKETS);
 	free = roundup_pow_of_two(ca->sb.nbuckets) >> 10;
 	if (!free) {
 		ret = -EPERM;
diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c
index 127138c61be5..d296770478b2 100644
--- a/drivers/md/dm-raid.c
+++ b/drivers/md/dm-raid.c
@@ -1356,11 +1356,7 @@ static int parse_raid_params(struct raid_set *rs, struct dm_arg_set *as,
 				return -EINVAL;
 			}
 
-			/*
-			 * In device-mapper, we specify things in sectors, but
-			 * MD records this value in kB
-			 */
-			if (value < 0 || value / 2 > COUNTER_MAX) {
+			if (value < 0) {
 				rs->ti->error = "Max write-behind limit out of range";
 				return -EINVAL;
 			}
diff --git a/drivers/md/md-bitmap.c b/drivers/md/md-bitmap.c
index 37b08f26c62f..bd694910b01b 100644
--- a/drivers/md/md-bitmap.c
+++ b/drivers/md/md-bitmap.c
@@ -105,9 +105,19 @@
  *
  */
 
+typedef __u16 bitmap_counter_t;
+
 #define PAGE_BITS (PAGE_SIZE << 3)
 #define PAGE_BIT_SHIFT (PAGE_SHIFT + 3)
 
+#define COUNTER_BITS 16
+#define COUNTER_BIT_SHIFT 4
+#define COUNTER_BYTE_SHIFT (COUNTER_BIT_SHIFT - 3)
+
+#define NEEDED_MASK ((bitmap_counter_t) (1 << (COUNTER_BITS - 1)))
+#define RESYNC_MASK ((bitmap_counter_t) (1 << (COUNTER_BITS - 2)))
+#define COUNTER_MAX ((bitmap_counter_t) RESYNC_MASK - 1)
+
 #define NEEDED(x) (((bitmap_counter_t) x) & NEEDED_MASK)
 #define RESYNC(x) (((bitmap_counter_t) x) & RESYNC_MASK)
 #define COUNTER(x) (((bitmap_counter_t) x) & COUNTER_MAX)
@@ -789,7 +799,7 @@ static int md_bitmap_new_disk_sb(struct bitmap *bitmap)
 	 * is a good choice?  We choose COUNTER_MAX / 2 arbitrarily.
 	 */
 	write_behind = bitmap->mddev->bitmap_info.max_write_behind;
-	if (write_behind > COUNTER_MAX)
+	if (write_behind > COUNTER_MAX / 2)
 		write_behind = COUNTER_MAX / 2;
 	sb->write_behind = cpu_to_le32(write_behind);
 	bitmap->mddev->bitmap_info.max_write_behind = write_behind;
@@ -1672,13 +1682,13 @@ __acquires(bitmap->lock)
 			&(bitmap->bp[page].map[pageoff]);
 }
 
-static int bitmap_startwrite(struct mddev *mddev, sector_t offset,
-			     unsigned long sectors)
+static void bitmap_start_write(struct mddev *mddev, sector_t offset,
+			       unsigned long sectors)
 {
 	struct bitmap *bitmap = mddev->bitmap;
 
 	if (!bitmap)
-		return 0;
+		return;
 
 	while (sectors) {
 		sector_t blocks;
@@ -1688,7 +1698,7 @@ static int bitmap_startwrite(struct mddev *mddev, sector_t offset,
 		bmc = md_bitmap_get_counter(&bitmap->counts, offset, &blocks, 1);
 		if (!bmc) {
 			spin_unlock_irq(&bitmap->counts.lock);
-			return 0;
+			return;
 		}
 
 		if (unlikely(COUNTER(*bmc) == COUNTER_MAX)) {
@@ -1724,11 +1734,10 @@ static int bitmap_startwrite(struct mddev *mddev, sector_t offset,
 		else
 			sectors = 0;
 	}
-	return 0;
 }
 
-static void bitmap_endwrite(struct mddev *mddev, sector_t offset,
-			    unsigned long sectors)
+static void bitmap_end_write(struct mddev *mddev, sector_t offset,
+			     unsigned long sectors)
 {
 	struct bitmap *bitmap = mddev->bitmap;
 
@@ -2205,9 +2214,9 @@ static struct bitmap *__bitmap_create(struct mddev *mddev, int slot)
 	return ERR_PTR(err);
 }
 
-static int bitmap_create(struct mddev *mddev, int slot)
+static int bitmap_create(struct mddev *mddev)
 {
-	struct bitmap *bitmap = __bitmap_create(mddev, slot);
+	struct bitmap *bitmap = __bitmap_create(mddev, -1);
 
 	if (IS_ERR(bitmap))
 		return PTR_ERR(bitmap);
@@ -2670,7 +2679,7 @@ location_store(struct mddev *mddev, const char *buf, size_t len)
 			}
 
 			mddev->bitmap_info.offset = offset;
-			rv = bitmap_create(mddev, -1);
+			rv = bitmap_create(mddev);
 			if (rv)
 				goto out;
 
@@ -3003,8 +3012,8 @@ static struct bitmap_operations bitmap_ops = {
 	.end_behind_write	= bitmap_end_behind_write,
 	.wait_behind_writes	= bitmap_wait_behind_writes,
 
-	.startwrite		= bitmap_startwrite,
-	.endwrite		= bitmap_endwrite,
+	.start_write		= bitmap_start_write,
+	.end_write		= bitmap_end_write,
 	.start_sync		= bitmap_start_sync,
 	.end_sync		= bitmap_end_sync,
 	.cond_end_sync		= bitmap_cond_end_sync,
diff --git a/drivers/md/md-bitmap.h b/drivers/md/md-bitmap.h
index 31c93019c76b..59e9dd45cfde 100644
--- a/drivers/md/md-bitmap.h
+++ b/drivers/md/md-bitmap.h
@@ -9,15 +9,6 @@
 
 #define BITMAP_MAGIC 0x6d746962
 
-typedef __u16 bitmap_counter_t;
-#define COUNTER_BITS 16
-#define COUNTER_BIT_SHIFT 4
-#define COUNTER_BYTE_SHIFT (COUNTER_BIT_SHIFT - 3)
-
-#define NEEDED_MASK ((bitmap_counter_t) (1 << (COUNTER_BITS - 1)))
-#define RESYNC_MASK ((bitmap_counter_t) (1 << (COUNTER_BITS - 2)))
-#define COUNTER_MAX ((bitmap_counter_t) RESYNC_MASK - 1)
-
 /* use these for bitmap->flags and bitmap->sb->state bit-fields */
 enum bitmap_state {
 	BITMAP_STALE	   = 1,  /* the bitmap file is out of date or had -EIO */
@@ -72,7 +63,7 @@ struct md_bitmap_stats {
 
 struct bitmap_operations {
 	bool (*enabled)(struct mddev *mddev);
-	int (*create)(struct mddev *mddev, int slot);
+	int (*create)(struct mddev *mddev);
 	int (*resize)(struct mddev *mddev, sector_t blocks, int chunksize,
 		      bool init);
 
@@ -89,10 +80,10 @@ struct bitmap_operations {
 	void (*end_behind_write)(struct mddev *mddev);
 	void (*wait_behind_writes)(struct mddev *mddev);
 
-	int (*startwrite)(struct mddev *mddev, sector_t offset,
+	void (*start_write)(struct mddev *mddev, sector_t offset,
+			    unsigned long sectors);
+	void (*end_write)(struct mddev *mddev, sector_t offset,
 			  unsigned long sectors);
-	void (*endwrite)(struct mddev *mddev, sector_t offset,
-			 unsigned long sectors);
 	bool (*start_sync)(struct mddev *mddev, sector_t offset,
 			   sector_t *blocks, bool degraded);
 	void (*end_sync)(struct mddev *mddev, sector_t offset, sector_t *blocks);
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 0fde115e921f..09042b060086 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -6225,7 +6225,7 @@ int md_run(struct mddev *mddev)
 	}
 	if (err == 0 && pers->sync_request &&
 	    (mddev->bitmap_info.file || mddev->bitmap_info.offset)) {
-		err = mddev->bitmap_ops->create(mddev, -1);
+		err = mddev->bitmap_ops->create(mddev);
 		if (err)
 			pr_warn("%s: failed to create bitmap (%d)\n",
 				mdname(mddev), err);
@@ -7285,7 +7285,7 @@ static int set_bitmap_file(struct mddev *mddev, int fd)
 	err = 0;
 	if (mddev->pers) {
 		if (fd >= 0) {
-			err = mddev->bitmap_ops->create(mddev, -1);
+			err = mddev->bitmap_ops->create(mddev);
 			if (!err)
 				err = mddev->bitmap_ops->load(mddev);
 
@@ -7601,7 +7601,7 @@ static int update_array_info(struct mddev *mddev, mdu_array_info_t *info)
 				mddev->bitmap_info.default_offset;
 			mddev->bitmap_info.space =
 				mddev->bitmap_info.default_space;
-			rv = mddev->bitmap_ops->create(mddev, -1);
+			rv = mddev->bitmap_ops->create(mddev);
 			if (!rv)
 				rv = mddev->bitmap_ops->load(mddev);
 
@@ -8799,14 +8799,14 @@ static void md_bitmap_start(struct mddev *mddev,
 		mddev->pers->bitmap_sector(mddev, &md_io_clone->offset,
 					   &md_io_clone->sectors);
 
-	mddev->bitmap_ops->startwrite(mddev, md_io_clone->offset,
-				      md_io_clone->sectors);
+	mddev->bitmap_ops->start_write(mddev, md_io_clone->offset,
+				       md_io_clone->sectors);
 }
 
 static void md_bitmap_end(struct mddev *mddev, struct md_io_clone *md_io_clone)
 {
-	mddev->bitmap_ops->endwrite(mddev, md_io_clone->offset,
-				    md_io_clone->sectors);
+	mddev->bitmap_ops->end_write(mddev, md_io_clone->offset,
+				     md_io_clone->sectors);
 }
 
 static void md_end_clone_io(struct bio *bio)
diff --git a/drivers/md/raid1-10.c b/drivers/md/raid1-10.c
index c7efd8aab675..b8b3a9069701 100644
--- a/drivers/md/raid1-10.c
+++ b/drivers/md/raid1-10.c
@@ -293,3 +293,13 @@ static inline bool raid1_should_read_first(struct mddev *mddev,
 
 	return false;
 }
+
+/*
+ * bio with REQ_RAHEAD or REQ_NOWAIT can fail at anytime, before such IO is
+ * submitted to the underlying disks, hence don't record badblocks or retry
+ * in this case.
+ */
+static inline bool raid1_should_handle_error(struct bio *bio)
+{
+	return !(bio->bi_opf & (REQ_RAHEAD | REQ_NOWAIT));
+}
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index 657d481525be..19c5a0ce5a40 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -373,14 +373,16 @@ static void raid1_end_read_request(struct bio *bio)
 	 */
 	update_head_pos(r1_bio->read_disk, r1_bio);
 
-	if (uptodate)
+	if (uptodate) {
 		set_bit(R1BIO_Uptodate, &r1_bio->state);
-	else if (test_bit(FailFast, &rdev->flags) &&
-		 test_bit(R1BIO_FailFast, &r1_bio->state))
+	} else if (test_bit(FailFast, &rdev->flags) &&
+		 test_bit(R1BIO_FailFast, &r1_bio->state)) {
 		/* This was a fail-fast read so we definitely
 		 * want to retry */
 		;
-	else {
+	} else if (!raid1_should_handle_error(bio)) {
+		uptodate = 1;
+	} else {
 		/* If all other devices have failed, we want to return
 		 * the error upwards rather than fail the last device.
 		 * Here we redefine "uptodate" to mean "Don't want to retry"
@@ -451,16 +453,15 @@ static void raid1_end_write_request(struct bio *bio)
 	struct bio *to_put = NULL;
 	int mirror = find_bio_disk(r1_bio, bio);
 	struct md_rdev *rdev = conf->mirrors[mirror].rdev;
-	bool discard_error;
 	sector_t lo = r1_bio->sector;
 	sector_t hi = r1_bio->sector + r1_bio->sectors;
-
-	discard_error = bio->bi_status && bio_op(bio) == REQ_OP_DISCARD;
+	bool ignore_error = !raid1_should_handle_error(bio) ||
+		(bio->bi_status && bio_op(bio) == REQ_OP_DISCARD);
 
 	/*
 	 * 'one mirror IO has finished' event handler:
 	 */
-	if (bio->bi_status && !discard_error) {
+	if (bio->bi_status && !ignore_error) {
 		set_bit(WriteErrorSeen,	&rdev->flags);
 		if (!test_and_set_bit(WantReplacement, &rdev->flags))
 			set_bit(MD_RECOVERY_NEEDED, &
@@ -511,7 +512,7 @@ static void raid1_end_write_request(struct bio *bio)
 
 		/* Maybe we can clear some bad blocks. */
 		if (rdev_has_badblock(rdev, r1_bio->sector, r1_bio->sectors) &&
-		    !discard_error) {
+		    !ignore_error) {
 			r1_bio->bios[mirror] = IO_MADE_GOOD;
 			set_bit(R1BIO_MadeGood, &r1_bio->state);
 		}
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index dce06bf65016..b74780af4c22 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -399,6 +399,8 @@ static void raid10_end_read_request(struct bio *bio)
 		 * wait for the 'master' bio.
 		 */
 		set_bit(R10BIO_Uptodate, &r10_bio->state);
+	} else if (!raid1_should_handle_error(bio)) {
+		uptodate = 1;
 	} else {
 		/* If all other devices that store this block have
 		 * failed, we want to return the error upwards rather
@@ -456,9 +458,8 @@ static void raid10_end_write_request(struct bio *bio)
 	int slot, repl;
 	struct md_rdev *rdev = NULL;
 	struct bio *to_put = NULL;
-	bool discard_error;
-
-	discard_error = bio->bi_status && bio_op(bio) == REQ_OP_DISCARD;
+	bool ignore_error = !raid1_should_handle_error(bio) ||
+		(bio->bi_status && bio_op(bio) == REQ_OP_DISCARD);
 
 	dev = find_bio_disk(conf, r10_bio, bio, &slot, &repl);
 
@@ -472,7 +473,7 @@ static void raid10_end_write_request(struct bio *bio)
 	/*
 	 * this branch is our 'one mirror IO has finished' event handler:
 	 */
-	if (bio->bi_status && !discard_error) {
+	if (bio->bi_status && !ignore_error) {
 		if (repl)
 			/* Never record new bad blocks to replacement,
 			 * just fail it.
@@ -527,7 +528,7 @@ static void raid10_end_write_request(struct bio *bio)
 		/* Maybe we can clear some bad blocks. */
 		if (rdev_has_badblock(rdev, r10_bio->devs[slot].addr,
 				      r10_bio->sectors) &&
-		    !discard_error) {
+		    !ignore_error) {
 			bio_put(bio);
 			if (repl)
 				r10_bio->devs[slot].repl_bio = IO_MADE_GOOD;
diff --git a/drivers/nvme/common/auth.c b/drivers/nvme/common/auth.c
index 3b6d759bcdf2..91e273b89fea 100644
--- a/drivers/nvme/common/auth.c
+++ b/drivers/nvme/common/auth.c
@@ -471,7 +471,7 @@ EXPORT_SYMBOL_GPL(nvme_auth_generate_key);
  * @c1: Value of challenge C1
  * @c2: Value of challenge C2
  * @hash_len: Hash length of the hash algorithm
- * @ret_psk: Pointer too the resulting generated PSK
+ * @ret_psk: Pointer to the resulting generated PSK
  * @ret_len: length of @ret_psk
  *
  * Generate a PSK for TLS as specified in NVMe base specification, section
@@ -759,8 +759,8 @@ int nvme_auth_derive_tls_psk(int hmac_id, u8 *psk, size_t psk_len,
 		goto out_free_prk;
 
 	/*
-	 * 2 addtional bytes for the length field from HDKF-Expand-Label,
-	 * 2 addtional bytes for the HMAC ID, and one byte for the space
+	 * 2 additional bytes for the length field from HDKF-Expand-Label,
+	 * 2 additional bytes for the HMAC ID, and one byte for the space
 	 * separator.
 	 */
 	info_len = strlen(psk_digest) + strlen(psk_prefix) + 5;
diff --git a/drivers/nvme/host/Kconfig b/drivers/nvme/host/Kconfig
index 7dca58f0a237..31974c7dd20c 100644
--- a/drivers/nvme/host/Kconfig
+++ b/drivers/nvme/host/Kconfig
@@ -106,7 +106,7 @@ config NVME_TCP_TLS
 	help
 	  Enables TLS encryption for NVMe TCP using the netlink handshake API.
 
-	  The TLS handshake daemon is availble at
+	  The TLS handshake daemon is available at
 	  https://github.com/oracle/ktls-utils.
 
 	  If unsure, say N.
diff --git a/drivers/nvme/host/constants.c b/drivers/nvme/host/constants.c
index 2b9e6cfaf2a8..1a0058be5821 100644
--- a/drivers/nvme/host/constants.c
+++ b/drivers/nvme/host/constants.c
@@ -145,7 +145,7 @@ static const char * const nvme_statuses[] = {
 	[NVME_SC_BAD_ATTRIBUTES] = "Conflicting Attributes",
 	[NVME_SC_INVALID_PI] = "Invalid Protection Information",
 	[NVME_SC_READ_ONLY] = "Attempted Write to Read Only Range",
-	[NVME_SC_ONCS_NOT_SUPPORTED] = "ONCS Not Supported",
+	[NVME_SC_CMD_SIZE_LIM_EXCEEDED	] = "Command Size Limits Exceeded",
 	[NVME_SC_ZONE_BOUNDARY_ERROR] = "Zoned Boundary Error",
 	[NVME_SC_ZONE_FULL] = "Zone Is Full",
 	[NVME_SC_ZONE_READ_ONLY] = "Zone Is Read Only",
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index f69a232a000a..92697f98c601 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -290,7 +290,6 @@ static blk_status_t nvme_error_status(u16 status)
 	case NVME_SC_NS_NOT_READY:
 		return BLK_STS_TARGET;
 	case NVME_SC_BAD_ATTRIBUTES:
-	case NVME_SC_ONCS_NOT_SUPPORTED:
 	case NVME_SC_INVALID_OPCODE:
 	case NVME_SC_INVALID_FIELD:
 	case NVME_SC_INVALID_NS:
@@ -1027,7 +1026,7 @@ static inline blk_status_t nvme_setup_rw(struct nvme_ns *ns,
 
 	if (ns->head->ms) {
 		/*
-		 * If formated with metadata, the block layer always provides a
+		 * If formatted with metadata, the block layer always provides a
 		 * metadata buffer if CONFIG_BLK_DEV_INTEGRITY is enabled.  Else
 		 * we enable the PRACT bit for protection information or set the
 		 * namespace capacity to zero to prevent any I/O.
diff --git a/drivers/nvme/host/fabrics.c b/drivers/nvme/host/fabrics.c
index 93e9041b9657..2e58a7ce1090 100644
--- a/drivers/nvme/host/fabrics.c
+++ b/drivers/nvme/host/fabrics.c
@@ -582,7 +582,7 @@ EXPORT_SYMBOL_GPL(nvmf_connect_io_queue);
  * Do not retry when:
  *
  * - the DNR bit is set and the specification states no further connect
- *   attempts with the same set of paramenters should be attempted.
+ *   attempts with the same set of parameters should be attempted.
  *
  * - when the authentication attempt fails, because the key was invalid.
  *   This error code is set on the host side.
diff --git a/drivers/nvme/host/fabrics.h b/drivers/nvme/host/fabrics.h
index 9cf5b020adba..1b58ee7d0dce 100644
--- a/drivers/nvme/host/fabrics.h
+++ b/drivers/nvme/host/fabrics.h
@@ -80,7 +80,7 @@ enum {
  * @transport:	Holds the fabric transport "technology name" (for a lack of
  *		better description) that will be used by an NVMe controller
  *		being added.
- * @subsysnqn:	Hold the fully qualified NQN subystem name (format defined
+ * @subsysnqn:	Hold the fully qualified NQN subsystem name (format defined
  *		in the NVMe specification, "NVMe Qualified Names").
  * @traddr:	The transport-specific TRADDR field for a port on the
  *              subsystem which is adding a controller.
@@ -156,7 +156,7 @@ struct nvmf_ctrl_options {
  * @create_ctrl():	function pointer that points to a non-NVMe
  *			implementation-specific fabric technology
  *			that would go into starting up that fabric
- *			for the purpose of conneciton to an NVMe controller
+ *			for the purpose of connection to an NVMe controller
  *			using that fabric technology.
  *
  * Notes:
@@ -165,7 +165,7 @@ struct nvmf_ctrl_options {
  *	2. create_ctrl() must be defined (even if it does nothing)
  *	3. struct nvmf_transport_ops must be statically allocated in the
  *	   modules .bss section so that a pure module_get on @module
- *	   prevents the memory from beeing freed.
+ *	   prevents the memory from being freed.
  */
 struct nvmf_transport_ops {
 	struct list_head	entry;
diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c
index fdafa3e9e66f..014b387f1e8b 100644
--- a/drivers/nvme/host/fc.c
+++ b/drivers/nvme/host/fc.c
@@ -1955,7 +1955,7 @@ nvme_fc_fcpio_done(struct nvmefc_fcp_req *req)
 	}
 
 	/*
-	 * For the linux implementation, if we have an unsuccesful
+	 * For the linux implementation, if we have an unsucceesful
 	 * status, they blk-mq layer can typically be called with the
 	 * non-zero status and the content of the cqe isn't important.
 	 */
@@ -2479,7 +2479,7 @@ __nvme_fc_abort_outstanding_ios(struct nvme_fc_ctrl *ctrl, bool start_queues)
 	 * writing the registers for shutdown and polling (call
 	 * nvme_disable_ctrl()). Given a bunch of i/o was potentially
 	 * just aborted and we will wait on those contexts, and given
-	 * there was no indication of how live the controlelr is on the
+	 * there was no indication of how live the controller is on the
 	 * link, don't send more io to create more contexts for the
 	 * shutdown. Let the controller fail via keepalive failure if
 	 * its still present.
diff --git a/drivers/nvme/host/ioctl.c b/drivers/nvme/host/ioctl.c
index ca86d3bf7ea4..0b50da2f1175 100644
--- a/drivers/nvme/host/ioctl.c
+++ b/drivers/nvme/host/ioctl.c
@@ -493,13 +493,15 @@ static int nvme_uring_cmd_io(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
 	d.timeout_ms = READ_ONCE(cmd->timeout_ms);
 
 	if (d.data_len && (ioucmd->flags & IORING_URING_CMD_FIXED)) {
-		/* fixedbufs is only for non-vectored io */
-		if (vec)
-			return -EINVAL;
+		int ddir = nvme_is_write(&c) ? WRITE : READ;
 
-		ret = io_uring_cmd_import_fixed(d.addr, d.data_len,
-			nvme_is_write(&c) ? WRITE : READ, &iter, ioucmd,
-			issue_flags);
+		if (vec)
+			ret = io_uring_cmd_import_fixed_vec(ioucmd,
+					u64_to_user_ptr(d.addr), d.data_len,
+					ddir, &iter, issue_flags);
+		else
+			ret = io_uring_cmd_import_fixed(d.addr, d.data_len,
+					ddir, &iter, ioucmd, issue_flags);
 		if (ret < 0)
 			return ret;
 
@@ -521,7 +523,7 @@ static int nvme_uring_cmd_io(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
 	if (d.data_len) {
 		ret = nvme_map_user_request(req, d.addr, d.data_len,
 			nvme_to_user_ptr(d.metadata), d.metadata_len,
-			map_iter, vec);
+			map_iter, vec ? NVME_IOCTL_VEC : 0);
 		if (ret)
 			goto out_free_req;
 	}
@@ -727,7 +729,7 @@ int nvme_ns_head_ioctl(struct block_device *bdev, blk_mode_t mode,
 
 	/*
 	 * Handle ioctls that apply to the controller instead of the namespace
-	 * seperately and drop the ns SRCU reference early.  This avoids a
+	 * separately and drop the ns SRCU reference early.  This avoids a
 	 * deadlock when deleting namespaces using the passthrough interface.
 	 */
 	if (is_ctrl_ioctl(cmd))
diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c
index 878ea8b1a0ac..140079ff86e6 100644
--- a/drivers/nvme/host/multipath.c
+++ b/drivers/nvme/host/multipath.c
@@ -760,7 +760,7 @@ int nvme_mpath_alloc_disk(struct nvme_ctrl *ctrl, struct nvme_ns_head *head)
 	 * controller's scan_work context. If a path error occurs here, the IO
 	 * will wait until a path becomes available or all paths are torn down,
 	 * but that action also occurs within scan_work, so it would deadlock.
-	 * Defer the partion scan to a different context that does not block
+	 * Defer the partition scan to a different context that does not block
 	 * scan_work.
 	 */
 	set_bit(GD_SUPPRESS_PART_SCAN, &head->disk->state);
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index ad0c1f834f09..a468cdc5b5cb 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -523,7 +523,7 @@ static inline bool nvme_ns_head_multipath(struct nvme_ns_head *head)
 enum nvme_ns_features {
 	NVME_NS_EXT_LBAS = 1 << 0, /* support extended LBA format */
 	NVME_NS_METADATA_SUPPORTED = 1 << 1, /* support getting generated md */
-	NVME_NS_DEAC = 1 << 2,		/* DEAC bit in Write Zeores supported */
+	NVME_NS_DEAC = 1 << 2,		/* DEAC bit in Write Zeroes supported */
 };
 
 struct nvme_ns {
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index e0bfe04a2bc2..8ff12e415cb5 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -3015,7 +3015,7 @@ static void nvme_reset_work(struct work_struct *work)
 		goto out;
 
 	/*
-	 * Freeze and update the number of I/O queues as thos might have
+	 * Freeze and update the number of I/O queues as those might have
 	 * changed.  If there are no I/O queues left after this reset, keep the
 	 * controller around but remove all namespaces.
 	 */
@@ -3186,7 +3186,7 @@ static unsigned long check_vendor_combination_bug(struct pci_dev *pdev)
 		/*
 		 * Exclude some Kingston NV1 and A2000 devices from
 		 * NVME_QUIRK_SIMPLE_SUSPEND. Do a full suspend to save a
-		 * lot fo energy with s2idle sleep on some TUXEDO platforms.
+		 * lot of energy with s2idle sleep on some TUXEDO platforms.
 		 */
 		if (dmi_match(DMI_BOARD_NAME, "NS5X_NS7XAU") ||
 		    dmi_match(DMI_BOARD_NAME, "NS5x_7xAU") ||
diff --git a/drivers/nvme/host/pr.c b/drivers/nvme/host/pr.c
index cf2d2c5039dd..ca6a74607b13 100644
--- a/drivers/nvme/host/pr.c
+++ b/drivers/nvme/host/pr.c
@@ -82,8 +82,6 @@ static int nvme_status_to_pr_err(int status)
 		return PR_STS_SUCCESS;
 	case NVME_SC_RESERVATION_CONFLICT:
 		return PR_STS_RESERVATION_CONFLICT;
-	case NVME_SC_ONCS_NOT_SUPPORTED:
-		return -EOPNOTSUPP;
 	case NVME_SC_BAD_ATTRIBUTES:
 	case NVME_SC_INVALID_OPCODE:
 	case NVME_SC_INVALID_FIELD:
diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c
index b5a0295b5bf4..9bd3646568d0 100644
--- a/drivers/nvme/host/rdma.c
+++ b/drivers/nvme/host/rdma.c
@@ -221,7 +221,7 @@ static struct nvme_rdma_qe *nvme_rdma_alloc_ring(struct ib_device *ibdev,
 
 	/*
 	 * Bind the CQEs (post recv buffers) DMA mapping to the RDMA queue
-	 * lifetime. It's safe, since any chage in the underlying RDMA device
+	 * lifetime. It's safe, since any change in the underlying RDMA device
 	 * will issue error recovery and queue re-creation.
 	 */
 	for (i = 0; i < ib_queue_size; i++) {
@@ -800,7 +800,7 @@ static int nvme_rdma_configure_admin_queue(struct nvme_rdma_ctrl *ctrl,
 
 	/*
 	 * Bind the async event SQE DMA mapping to the admin queue lifetime.
-	 * It's safe, since any chage in the underlying RDMA device will issue
+	 * It's safe, since any change in the underlying RDMA device will issue
 	 * error recovery and queue re-creation.
 	 */
 	error = nvme_rdma_alloc_qe(ctrl->device->dev, &ctrl->async_event_sqe,
diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
index f6379aa33d77..d924008c3949 100644
--- a/drivers/nvme/host/tcp.c
+++ b/drivers/nvme/host/tcp.c
@@ -452,7 +452,8 @@ nvme_tcp_fetch_request(struct nvme_tcp_queue *queue)
 			return NULL;
 	}
 
-	list_del(&req->entry);
+	list_del_init(&req->entry);
+	init_llist_node(&req->lentry);
 	return req;
 }
 
@@ -565,6 +566,8 @@ static int nvme_tcp_init_request(struct blk_mq_tag_set *set,
 	req->queue = queue;
 	nvme_req(rq)->ctrl = &ctrl->ctrl;
 	nvme_req(rq)->cmd = &pdu->cmd;
+	init_llist_node(&req->lentry);
+	INIT_LIST_HEAD(&req->entry);
 
 	return 0;
 }
@@ -769,6 +772,14 @@ static int nvme_tcp_handle_r2t(struct nvme_tcp_queue *queue,
 		return -EPROTO;
 	}
 
+	if (llist_on_list(&req->lentry) ||
+	    !list_empty(&req->entry)) {
+		dev_err(queue->ctrl->ctrl.device,
+			"req %d unexpected r2t while processing request\n",
+			rq->tag);
+		return -EPROTO;
+	}
+
 	req->pdu_len = 0;
 	req->h2cdata_left = r2t_length;
 	req->h2cdata_offset = r2t_offset;
@@ -1355,7 +1366,7 @@ static int nvme_tcp_try_recv(struct nvme_tcp_queue *queue)
 	queue->nr_cqe = 0;
 	consumed = sock->ops->read_sock(sk, &rd_desc, nvme_tcp_recv_skb);
 	release_sock(sk);
-	return consumed;
+	return consumed == -EAGAIN ? 0 : consumed;
 }
 
 static void nvme_tcp_io_work(struct work_struct *w)
@@ -1383,6 +1394,11 @@ static void nvme_tcp_io_work(struct work_struct *w)
 		else if (unlikely(result < 0))
 			return;
 
+		/* did we get some space after spending time in recv? */
+		if (nvme_tcp_queue_has_pending(queue) &&
+		    sk_stream_is_writeable(queue->sock->sk))
+			pending = true;
+
 		if (!pending || !queue->rd_enabled)
 			return;
 
@@ -2350,7 +2366,7 @@ static int nvme_tcp_setup_ctrl(struct nvme_ctrl *ctrl, bool new)
 		nvme_tcp_teardown_admin_queue(ctrl, false);
 		ret = nvme_tcp_configure_admin_queue(ctrl, false);
 		if (ret)
-			return ret;
+			goto destroy_admin;
 	}
 
 	if (ctrl->icdoff) {
@@ -2594,6 +2610,8 @@ static void nvme_tcp_submit_async_event(struct nvme_ctrl *arg)
 	ctrl->async_req.offset = 0;
 	ctrl->async_req.curr_bio = NULL;
 	ctrl->async_req.data_len = 0;
+	init_llist_node(&ctrl->async_req.lentry);
+	INIT_LIST_HEAD(&ctrl->async_req.entry);
 
 	nvme_tcp_queue_request(&ctrl->async_req, true);
 }
diff --git a/drivers/nvme/target/admin-cmd.c b/drivers/nvme/target/admin-cmd.c
index c7317299078d..3e378153a781 100644
--- a/drivers/nvme/target/admin-cmd.c
+++ b/drivers/nvme/target/admin-cmd.c
@@ -1165,7 +1165,7 @@ static void nvmet_execute_identify(struct nvmet_req *req)
  * A "minimum viable" abort implementation: the command is mandatory in the
  * spec, but we are not required to do any useful work.  We couldn't really
  * do a useful abort, so don't bother even with waiting for the command
- * to be exectuted and return immediately telling the command to abort
+ * to be executed and return immediately telling the command to abort
  * wasn't found.
  */
 static void nvmet_execute_abort(struct nvmet_req *req)
diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c
index db7b17d1094e..175c5b6d4dd5 100644
--- a/drivers/nvme/target/core.c
+++ b/drivers/nvme/target/core.c
@@ -62,14 +62,7 @@ inline u16 errno_to_nvme_status(struct nvmet_req *req, int errno)
 		return  NVME_SC_LBA_RANGE | NVME_STATUS_DNR;
 	case -EOPNOTSUPP:
 		req->error_loc = offsetof(struct nvme_common_command, opcode);
-		switch (req->cmd->common.opcode) {
-		case nvme_cmd_dsm:
-		case nvme_cmd_write_zeroes:
-			return NVME_SC_ONCS_NOT_SUPPORTED | NVME_STATUS_DNR;
-		default:
-			return NVME_SC_INVALID_OPCODE | NVME_STATUS_DNR;
-		}
-		break;
+		return NVME_SC_INVALID_OPCODE | NVME_STATUS_DNR;
 	case -ENODATA:
 		req->error_loc = offsetof(struct nvme_rw_command, nsid);
 		return NVME_SC_ACCESS_DENIED;
@@ -651,7 +644,7 @@ void nvmet_ns_disable(struct nvmet_ns *ns)
 	 * Now that we removed the namespaces from the lookup list, we
 	 * can kill the per_cpu ref and wait for any remaining references
 	 * to be dropped, as well as a RCU grace period for anyone only
-	 * using the namepace under rcu_read_lock().  Note that we can't
+	 * using the namespace under rcu_read_lock().  Note that we can't
 	 * use call_rcu here as we need to ensure the namespaces have
 	 * been fully destroyed before unloading the module.
 	 */
diff --git a/drivers/nvme/target/fc.c b/drivers/nvme/target/fc.c
index 254537b93e63..25598a46bf0d 100644
--- a/drivers/nvme/target/fc.c
+++ b/drivers/nvme/target/fc.c
@@ -1339,7 +1339,7 @@ nvmet_fc_portentry_rebind_tgt(struct nvmet_fc_tgtport *tgtport)
 /**
  * nvmet_fc_register_targetport - transport entry point called by an
  *                              LLDD to register the existence of a local
- *                              NVME subystem FC port.
+ *                              NVME subsystem FC port.
  * @pinfo:     pointer to information about the port to be registered
  * @template:  LLDD entrypoints and operational parameters for the port
  * @dev:       physical hardware device node port corresponds to. Will be
diff --git a/drivers/nvme/target/io-cmd-bdev.c b/drivers/nvme/target/io-cmd-bdev.c
index 83be0657e6df..eba42df2f821 100644
--- a/drivers/nvme/target/io-cmd-bdev.c
+++ b/drivers/nvme/target/io-cmd-bdev.c
@@ -133,7 +133,7 @@ u16 blk_to_nvme_status(struct nvmet_req *req, blk_status_t blk_sts)
 	 * Right now there exists M : 1 mapping between block layer error
 	 * to the NVMe status code (see nvme_error_status()). For consistency,
 	 * when we reverse map we use most appropriate NVMe Status code from
-	 * the group of the NVMe staus codes used in the nvme_error_status().
+	 * the group of the NVMe status codes used in the nvme_error_status().
 	 */
 	switch (blk_sts) {
 	case BLK_STS_NOSPC:
@@ -145,15 +145,8 @@ u16 blk_to_nvme_status(struct nvmet_req *req, blk_status_t blk_sts)
 		req->error_loc = offsetof(struct nvme_rw_command, slba);
 		break;
 	case BLK_STS_NOTSUPP:
+		status = NVME_SC_INVALID_OPCODE | NVME_STATUS_DNR;
 		req->error_loc = offsetof(struct nvme_common_command, opcode);
-		switch (req->cmd->common.opcode) {
-		case nvme_cmd_dsm:
-		case nvme_cmd_write_zeroes:
-			status = NVME_SC_ONCS_NOT_SUPPORTED | NVME_STATUS_DNR;
-			break;
-		default:
-			status = NVME_SC_INVALID_OPCODE | NVME_STATUS_DNR;
-		}
 		break;
 	case BLK_STS_MEDIUM:
 		status = NVME_SC_ACCESS_DENIED;
diff --git a/drivers/nvme/target/passthru.c b/drivers/nvme/target/passthru.c
index 26e2907ce8bb..b7515c53829b 100644
--- a/drivers/nvme/target/passthru.c
+++ b/drivers/nvme/target/passthru.c
@@ -99,7 +99,7 @@ static u16 nvmet_passthru_override_id_ctrl(struct nvmet_req *req)
 
 	/*
 	 * The passthru NVMe driver may have a limit on the number of segments
-	 * which depends on the host's memory fragementation. To solve this,
+	 * which depends on the host's memory fragmentation. To solve this,
 	 * ensure mdts is limited to the pages equal to the number of segments.
 	 */
 	max_hw_sectors = min_not_zero(pctrl->max_segments << PAGE_SECTORS_SHIFT,