Merge branch 'for-4.15/block' of git://git.kernel.dk/linux-block

Pull core block layer updates from Jens Axboe:
 "This is the main pull request for block storage for 4.15-rc1.

  Nothing out of the ordinary in here, and no API changes or anything
  like that. Just various new features for drivers, core changes, etc.
  In particular, this pull request contains:

   - A patch series from Bart, closing the whole on blk/scsi-mq queue
     quescing.

   - A series from Christoph, building towards hidden gendisks (for
     multipath) and ability to move bio chains around.

   - NVMe
        - Support for native multipath for NVMe (Christoph).
        - Userspace notifications for AENs (Keith).
        - Command side-effects support (Keith).
        - SGL support (Chaitanya Kulkarni)
        - FC fixes and improvements (James Smart)
        - Lots of fixes and tweaks (Various)

   - bcache
        - New maintainer (Michael Lyle)
        - Writeback control improvements (Michael)
        - Various fixes (Coly, Elena, Eric, Liang, et al)

   - lightnvm updates, mostly centered around the pblk interface
     (Javier, Hans, and Rakesh).

   - Removal of unused bio/bvec kmap atomic interfaces (me, Christoph)

   - Writeback series that fix the much discussed hundreds of millions
     of sync-all units. This goes all the way, as discussed previously
     (me).

   - Fix for missing wakeup on writeback timer adjustments (Yafang
     Shao).

   - Fix laptop mode on blk-mq (me).

   - {mq,name} tupple lookup for IO schedulers, allowing us to have
     alias names. This means you can use 'deadline' on both !mq and on
     mq (where it's called mq-deadline). (me).

   - blktrace race fix, oopsing on sg load (me).

   - blk-mq optimizations (me).

   - Obscure waitqueue race fix for kyber (Omar).

   - NBD fixes (Josef).

   - Disable writeback throttling by default on bfq, like we do on cfq
     (Luca Miccio).

   - Series from Ming that enable us to treat flush requests on blk-mq
     like any other request. This is a really nice cleanup.

   - Series from Ming that improves merging on blk-mq with schedulers,
     getting us closer to flipping the switch on scsi-mq again.

   - BFQ updates (Paolo).

   - blk-mq atomic flags memory ordering fixes (Peter Z).

   - Loop cgroup support (Shaohua).

   - Lots of minor fixes from lots of different folks, both for core and
     driver code"

* 'for-4.15/block' of git://git.kernel.dk/linux-block: (294 commits)
  nvme: fix visibility of "uuid" ns attribute
  blk-mq: fixup some comment typos and lengths
  ide: ide-atapi: fix compile error with defining macro DEBUG
  blk-mq: improve tag waiting setup for non-shared tags
  brd: remove unused brd_mutex
  blk-mq: only run the hardware queue if IO is pending
  block: avoid null pointer dereference on null disk
  fs: guard_bio_eod() needs to consider partitions
  xtensa/simdisk: fix compile error
  nvme: expose subsys attribute to sysfs
  nvme: create 'slaves' and 'holders' entries for hidden controllers
  block: create 'slaves' and 'holders' entries for hidden gendisks
  nvme: also expose the namespace identification sysfs files for mpath nodes
  nvme: implement multipath access to nvme subsystems
  nvme: track shared namespaces
  nvme: introduce a nvme_ns_ids structure
  nvme: track subsystems
  block, nvme: Introduce blk_mq_req_flags_t
  block, scsi: Make SCSI quiesce and resume work reliably
  block: Add the QUEUE_FLAG_PREEMPT_ONLY request queue flag
  ...

7 files changed, 89 insertions, 111 deletions

diff --git a/drivers/nvme/target/admin-cmd.c b/drivers/nvme/target/admin-cmd.c
index c4a0bf36e752..90dcdc40ac71 100644
--- a/drivers/nvme/target/admin-cmd.c
+++ b/drivers/nvme/target/admin-cmd.c
@@ -35,17 +35,14 @@ u32 nvmet_get_log_page_len(struct nvme_command *cmd)
 static u16 nvmet_get_smart_log_nsid(struct nvmet_req *req,
 		struct nvme_smart_log *slog)
 {
-	u16 status;
 	struct nvmet_ns *ns;
 	u64 host_reads, host_writes, data_units_read, data_units_written;
 
-	status = NVME_SC_SUCCESS;
 	ns = nvmet_find_namespace(req->sq->ctrl, req->cmd->get_log_page.nsid);
 	if (!ns) {
-		status = NVME_SC_INVALID_NS;
 		pr_err("nvmet : Could not find namespace id : %d\n",
 				le32_to_cpu(req->cmd->get_log_page.nsid));
-		goto out;
+		return NVME_SC_INVALID_NS;
 	}
 
 	host_reads = part_stat_read(ns->bdev->bd_part, ios[READ]);
@@ -58,20 +55,18 @@ static u16 nvmet_get_smart_log_nsid(struct nvmet_req *req,
 	put_unaligned_le64(host_writes, &slog->host_writes[0]);
 	put_unaligned_le64(data_units_written, &slog->data_units_written[0]);
 	nvmet_put_namespace(ns);
-out:
-	return status;
+
+	return NVME_SC_SUCCESS;
 }
 
 static u16 nvmet_get_smart_log_all(struct nvmet_req *req,
 		struct nvme_smart_log *slog)
 {
-	u16 status;
 	u64 host_reads = 0, host_writes = 0;
 	u64 data_units_read = 0, data_units_written = 0;
 	struct nvmet_ns *ns;
 	struct nvmet_ctrl *ctrl;
 
-	status = NVME_SC_SUCCESS;
 	ctrl = req->sq->ctrl;
 
 	rcu_read_lock();
@@ -91,7 +86,7 @@ static u16 nvmet_get_smart_log_all(struct nvmet_req *req,
 	put_unaligned_le64(host_writes, &slog->host_writes[0]);
 	put_unaligned_le64(data_units_written, &slog->data_units_written[0]);
 
-	return status;
+	return NVME_SC_SUCCESS;
 }
 
 static u16 nvmet_get_smart_log(struct nvmet_req *req,
@@ -144,10 +139,8 @@ static void nvmet_execute_get_log_page(struct nvmet_req *req)
 		}
 		smart_log = buf;
 		status = nvmet_get_smart_log(req, smart_log);
-		if (status) {
-			memset(buf, '\0', data_len);
+		if (status)
 			goto err;
-		}
 		break;
 	case NVME_LOG_FW_SLOT:
 		/*
@@ -300,7 +293,7 @@ static void nvmet_execute_identify_ns(struct nvmet_req *req)
 	}
 
 	/*
-	 * nuse = ncap = nsze isn't aways true, but we have no way to find
+	 * nuse = ncap = nsze isn't always true, but we have no way to find
 	 * that out from the underlying device.
 	 */
 	id->ncap = id->nuse = id->nsze =
@@ -424,7 +417,7 @@ out:
 }
 
 /*
- * A "mimimum viable" abort implementation: the command is mandatory in the
+ * 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
diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c
index 645ba7eee35d..b54748ad5f48 100644
--- a/drivers/nvme/target/core.c
+++ b/drivers/nvme/target/core.c
@@ -57,6 +57,17 @@ u16 nvmet_copy_from_sgl(struct nvmet_req *req, off_t off, void *buf, size_t len)
 	return 0;
 }
 
+static unsigned int nvmet_max_nsid(struct nvmet_subsys *subsys)
+{
+	struct nvmet_ns *ns;
+
+	if (list_empty(&subsys->namespaces))
+		return 0;
+
+	ns = list_last_entry(&subsys->namespaces, struct nvmet_ns, dev_link);
+	return ns->nsid;
+}
+
 static u32 nvmet_async_event_result(struct nvmet_async_event *aen)
 {
 	return aen->event_type | (aen->event_info << 8) | (aen->log_page << 16);
@@ -334,6 +345,8 @@ void nvmet_ns_disable(struct nvmet_ns *ns)
 
 	ns->enabled = false;
 	list_del_rcu(&ns->dev_link);
+	if (ns->nsid == subsys->max_nsid)
+		subsys->max_nsid = nvmet_max_nsid(subsys);
 	mutex_unlock(&subsys->lock);
 
 	/*
@@ -497,6 +510,7 @@ bool nvmet_req_init(struct nvmet_req *req, struct nvmet_cq *cq,
 	req->ops = ops;
 	req->sg = NULL;
 	req->sg_cnt = 0;
+	req->transfer_len = 0;
 	req->rsp->status = 0;
 
 	/* no support for fused commands yet */
@@ -546,6 +560,15 @@ void nvmet_req_uninit(struct nvmet_req *req)
 }
 EXPORT_SYMBOL_GPL(nvmet_req_uninit);
 
+void nvmet_req_execute(struct nvmet_req *req)
+{
+	if (unlikely(req->data_len != req->transfer_len))
+		nvmet_req_complete(req, NVME_SC_SGL_INVALID_DATA | NVME_SC_DNR);
+	else
+		req->execute(req);
+}
+EXPORT_SYMBOL_GPL(nvmet_req_execute);
+
 static inline bool nvmet_cc_en(u32 cc)
 {
 	return (cc >> NVME_CC_EN_SHIFT) & 0x1;
diff --git a/drivers/nvme/target/fc.c b/drivers/nvme/target/fc.c
index 58e010bdda3e..739b8feadc7d 100644
--- a/drivers/nvme/target/fc.c
+++ b/drivers/nvme/target/fc.c
@@ -76,7 +76,6 @@ struct nvmet_fc_fcp_iod {
 	dma_addr_t			rspdma;
 	struct scatterlist		*data_sg;
 	int				data_sg_cnt;
-	u32				total_length;
 	u32				offset;
 	enum nvmet_fcp_datadir		io_dir;
 	bool				active;
@@ -150,6 +149,7 @@ struct nvmet_fc_tgt_assoc {
 	struct list_head		a_list;
 	struct nvmet_fc_tgt_queue	*queues[NVMET_NR_QUEUES + 1];
 	struct kref			ref;
+	struct work_struct		del_work;
 };
 
 
@@ -232,6 +232,7 @@ static void nvmet_fc_tgtport_put(struct nvmet_fc_tgtport *tgtport);
 static int nvmet_fc_tgtport_get(struct nvmet_fc_tgtport *tgtport);
 static void nvmet_fc_handle_fcp_rqst(struct nvmet_fc_tgtport *tgtport,
 					struct nvmet_fc_fcp_iod *fod);
+static void nvmet_fc_delete_target_assoc(struct nvmet_fc_tgt_assoc *assoc);
 
 
 /* *********************** FC-NVME DMA Handling **************************** */
@@ -802,6 +803,16 @@ nvmet_fc_find_target_queue(struct nvmet_fc_tgtport *tgtport,
 	return NULL;
 }
 
+static void
+nvmet_fc_delete_assoc(struct work_struct *work)
+{
+	struct nvmet_fc_tgt_assoc *assoc =
+		container_of(work, struct nvmet_fc_tgt_assoc, del_work);
+
+	nvmet_fc_delete_target_assoc(assoc);
+	nvmet_fc_tgt_a_put(assoc);
+}
+
 static struct nvmet_fc_tgt_assoc *
 nvmet_fc_alloc_target_assoc(struct nvmet_fc_tgtport *tgtport)
 {
@@ -826,6 +837,7 @@ nvmet_fc_alloc_target_assoc(struct nvmet_fc_tgtport *tgtport)
 	assoc->a_id = idx;
 	INIT_LIST_HEAD(&assoc->a_list);
 	kref_init(&assoc->ref);
+	INIT_WORK(&assoc->del_work, nvmet_fc_delete_assoc);
 
 	while (needrandom) {
 		get_random_bytes(&ran, sizeof(ran) - BYTES_FOR_QID);
@@ -1118,8 +1130,7 @@ nvmet_fc_delete_ctrl(struct nvmet_ctrl *ctrl)
 		nvmet_fc_tgtport_put(tgtport);
 
 		if (found_ctrl) {
-			nvmet_fc_delete_target_assoc(assoc);
-			nvmet_fc_tgt_a_put(assoc);
+			schedule_work(&assoc->del_work);
 			return;
 		}
 
@@ -1688,7 +1699,7 @@ nvmet_fc_alloc_tgt_pgs(struct nvmet_fc_fcp_iod *fod)
 	u32 page_len, length;
 	int i = 0;
 
-	length = fod->total_length;
+	length = fod->req.transfer_len;
 	nent = DIV_ROUND_UP(length, PAGE_SIZE);
 	sg = kmalloc_array(nent, sizeof(struct scatterlist), GFP_KERNEL);
 	if (!sg)
@@ -1777,7 +1788,7 @@ nvmet_fc_prep_fcp_rsp(struct nvmet_fc_tgtport *tgtport,
 	u32 rsn, rspcnt, xfr_length;
 
 	if (fod->fcpreq->op == NVMET_FCOP_READDATA_RSP)
-		xfr_length = fod->total_length;
+		xfr_length = fod->req.transfer_len;
 	else
 		xfr_length = fod->offset;
 
@@ -1803,7 +1814,7 @@ nvmet_fc_prep_fcp_rsp(struct nvmet_fc_tgtport *tgtport,
 	rspcnt = atomic_inc_return(&fod->queue->zrspcnt);
 	if (!(rspcnt % fod->queue->ersp_ratio) ||
 	    sqe->opcode == nvme_fabrics_command ||
-	    xfr_length != fod->total_length ||
+	    xfr_length != fod->req.transfer_len ||
 	    (le16_to_cpu(cqe->status) & 0xFFFE) || cqewd[0] || cqewd[1] ||
 	    (sqe->flags & (NVME_CMD_FUSE_FIRST | NVME_CMD_FUSE_SECOND)) ||
 	    queue_90percent_full(fod->queue, le16_to_cpu(cqe->sq_head)))
@@ -1880,7 +1891,7 @@ nvmet_fc_transfer_fcp_data(struct nvmet_fc_tgtport *tgtport,
 	fcpreq->timeout = NVME_FC_TGTOP_TIMEOUT_SEC;
 
 	tlen = min_t(u32, tgtport->max_sg_cnt * PAGE_SIZE,
-			(fod->total_length - fod->offset));
+			(fod->req.transfer_len - fod->offset));
 	fcpreq->transfer_length = tlen;
 	fcpreq->transferred_length = 0;
 	fcpreq->fcp_error = 0;
@@ -1894,7 +1905,7 @@ nvmet_fc_transfer_fcp_data(struct nvmet_fc_tgtport *tgtport,
 	 * combined xfr with response.
 	 */
 	if ((op == NVMET_FCOP_READDATA) &&
-	    ((fod->offset + fcpreq->transfer_length) == fod->total_length) &&
+	    ((fod->offset + fcpreq->transfer_length) == fod->req.transfer_len) &&
 	    (tgtport->ops->target_features & NVMET_FCTGTFEAT_READDATA_RSP)) {
 		fcpreq->op = NVMET_FCOP_READDATA_RSP;
 		nvmet_fc_prep_fcp_rsp(tgtport, fod);
@@ -1974,7 +1985,7 @@ nvmet_fc_fod_op_done(struct nvmet_fc_fcp_iod *fod)
 		}
 
 		fod->offset += fcpreq->transferred_length;
-		if (fod->offset != fod->total_length) {
+		if (fod->offset != fod->req.transfer_len) {
 			spin_lock_irqsave(&fod->flock, flags);
 			fod->writedataactive = true;
 			spin_unlock_irqrestore(&fod->flock, flags);
@@ -1986,9 +1997,7 @@ nvmet_fc_fod_op_done(struct nvmet_fc_fcp_iod *fod)
 		}
 
 		/* data transfer complete, resume with nvmet layer */
-
-		fod->req.execute(&fod->req);
-
+		nvmet_req_execute(&fod->req);
 		break;
 
 	case NVMET_FCOP_READDATA:
@@ -2011,7 +2020,7 @@ nvmet_fc_fod_op_done(struct nvmet_fc_fcp_iod *fod)
 		}
 
 		fod->offset += fcpreq->transferred_length;
-		if (fod->offset != fod->total_length) {
+		if (fod->offset != fod->req.transfer_len) {
 			/* transfer the next chunk */
 			nvmet_fc_transfer_fcp_data(tgtport, fod,
 						NVMET_FCOP_READDATA);
@@ -2148,7 +2157,7 @@ nvmet_fc_handle_fcp_rqst(struct nvmet_fc_tgtport *tgtport,
 
 	fod->fcpreq->done = nvmet_fc_xmt_fcp_op_done;
 
-	fod->total_length = be32_to_cpu(cmdiu->data_len);
+	fod->req.transfer_len = be32_to_cpu(cmdiu->data_len);
 	if (cmdiu->flags & FCNVME_CMD_FLAGS_WRITE) {
 		fod->io_dir = NVMET_FCP_WRITE;
 		if (!nvme_is_write(&cmdiu->sqe))
@@ -2159,7 +2168,7 @@ nvmet_fc_handle_fcp_rqst(struct nvmet_fc_tgtport *tgtport,
 			goto transport_error;
 	} else {
 		fod->io_dir = NVMET_FCP_NODATA;
-		if (fod->total_length)
+		if (fod->req.transfer_len)
 			goto transport_error;
 	}
 
@@ -2167,9 +2176,6 @@ nvmet_fc_handle_fcp_rqst(struct nvmet_fc_tgtport *tgtport,
 	fod->req.rsp = &fod->rspiubuf.cqe;
 	fod->req.port = fod->queue->port;
 
-	/* ensure nvmet handlers will set cmd handler callback */
-	fod->req.execute = NULL;
-
 	/* clear any response payload */
 	memset(&fod->rspiubuf, 0, sizeof(fod->rspiubuf));
 
@@ -2189,7 +2195,7 @@ nvmet_fc_handle_fcp_rqst(struct nvmet_fc_tgtport *tgtport,
 	/* keep a running counter of tail position */
 	atomic_inc(&fod->queue->sqtail);
 
-	if (fod->total_length) {
+	if (fod->req.transfer_len) {
 		ret = nvmet_fc_alloc_tgt_pgs(fod);
 		if (ret) {
 			nvmet_req_complete(&fod->req, ret);
@@ -2212,9 +2218,7 @@ nvmet_fc_handle_fcp_rqst(struct nvmet_fc_tgtport *tgtport,
 	 * can invoke the nvmet_layer now. If read data, cmd completion will
 	 * push the data
 	 */
-
-	fod->req.execute(&fod->req);
-
+	nvmet_req_execute(&fod->req);
 	return;
 
 transport_error:
diff --git a/drivers/nvme/target/io-cmd.c b/drivers/nvme/target/io-cmd.c
index 0d4c23dc4532..0a4372a016f2 100644
--- a/drivers/nvme/target/io-cmd.c
+++ b/drivers/nvme/target/io-cmd.c
@@ -33,18 +33,11 @@ static inline u32 nvmet_rw_len(struct nvmet_req *req)
 			req->ns->blksize_shift;
 }
 
-static void nvmet_inline_bio_init(struct nvmet_req *req)
-{
-	struct bio *bio = &req->inline_bio;
-
-	bio_init(bio, req->inline_bvec, NVMET_MAX_INLINE_BIOVEC);
-}
-
 static void nvmet_execute_rw(struct nvmet_req *req)
 {
 	int sg_cnt = req->sg_cnt;
+	struct bio *bio = &req->inline_bio;
 	struct scatterlist *sg;
-	struct bio *bio;
 	sector_t sector;
 	blk_qc_t cookie;
 	int op, op_flags = 0, i;
@@ -66,8 +59,7 @@ static void nvmet_execute_rw(struct nvmet_req *req)
 	sector = le64_to_cpu(req->cmd->rw.slba);
 	sector <<= (req->ns->blksize_shift - 9);
 
-	nvmet_inline_bio_init(req);
-	bio = &req->inline_bio;
+	bio_init(bio, req->inline_bvec, ARRAY_SIZE(req->inline_bvec));
 	bio_set_dev(bio, req->ns->bdev);
 	bio->bi_iter.bi_sector = sector;
 	bio->bi_private = req;
@@ -94,16 +86,14 @@ static void nvmet_execute_rw(struct nvmet_req *req)
 
 	cookie = submit_bio(bio);
 
-	blk_mq_poll(bdev_get_queue(req->ns->bdev), cookie);
+	blk_poll(bdev_get_queue(req->ns->bdev), cookie);
 }
 
 static void nvmet_execute_flush(struct nvmet_req *req)
 {
-	struct bio *bio;
-
-	nvmet_inline_bio_init(req);
-	bio = &req->inline_bio;
+	struct bio *bio = &req->inline_bio;
 
+	bio_init(bio, req->inline_bvec, ARRAY_SIZE(req->inline_bvec));
 	bio_set_dev(bio, req->ns->bdev);
 	bio->bi_private = req;
 	bio->bi_end_io = nvmet_bio_done;
diff --git a/drivers/nvme/target/loop.c b/drivers/nvme/target/loop.c
index 92628c432926..96d390416789 100644
--- a/drivers/nvme/target/loop.c
+++ b/drivers/nvme/target/loop.c
@@ -23,14 +23,6 @@
 
 #define NVME_LOOP_MAX_SEGMENTS		256
 
-/*
- * We handle AEN commands ourselves and don't even let the
- * block layer know about them.
- */
-#define NVME_LOOP_NR_AEN_COMMANDS	1
-#define NVME_LOOP_AQ_BLKMQ_DEPTH	\
-	(NVME_AQ_DEPTH - NVME_LOOP_NR_AEN_COMMANDS)
-
 struct nvme_loop_iod {
 	struct nvme_request	nvme_req;
 	struct nvme_command	cmd;
@@ -53,7 +45,6 @@ struct nvme_loop_ctrl {
 	struct nvme_ctrl	ctrl;
 
 	struct nvmet_ctrl	*target_ctrl;
-	struct work_struct	delete_work;
 };
 
 static inline struct nvme_loop_ctrl *to_loop_ctrl(struct nvme_ctrl *ctrl)
@@ -113,7 +104,7 @@ static void nvme_loop_queue_response(struct nvmet_req *req)
 	 * for them but rather special case them here.
 	 */
 	if (unlikely(nvme_loop_queue_idx(queue) == 0 &&
-			cqe->command_id >= NVME_LOOP_AQ_BLKMQ_DEPTH)) {
+			cqe->command_id >= NVME_AQ_BLK_MQ_DEPTH)) {
 		nvme_complete_async_event(&queue->ctrl->ctrl, cqe->status,
 				&cqe->result);
 	} else {
@@ -136,7 +127,7 @@ static void nvme_loop_execute_work(struct work_struct *work)
 	struct nvme_loop_iod *iod =
 		container_of(work, struct nvme_loop_iod, work);
 
-	iod->req.execute(&iod->req);
+	nvmet_req_execute(&iod->req);
 }
 
 static enum blk_eh_timer_return
@@ -185,6 +176,7 @@ static blk_status_t nvme_loop_queue_rq(struct blk_mq_hw_ctx *hctx,
 
 		iod->req.sg = iod->sg_table.sgl;
 		iod->req.sg_cnt = blk_rq_map_sg(req->q, req, iod->sg_table.sgl);
+		iod->req.transfer_len = blk_rq_bytes(req);
 	}
 
 	blk_mq_start_request(req);
@@ -193,7 +185,7 @@ static blk_status_t nvme_loop_queue_rq(struct blk_mq_hw_ctx *hctx,
 	return BLK_STS_OK;
 }
 
-static void nvme_loop_submit_async_event(struct nvme_ctrl *arg, int aer_idx)
+static void nvme_loop_submit_async_event(struct nvme_ctrl *arg)
 {
 	struct nvme_loop_ctrl *ctrl = to_loop_ctrl(arg);
 	struct nvme_loop_queue *queue = &ctrl->queues[0];
@@ -201,7 +193,7 @@ static void nvme_loop_submit_async_event(struct nvme_ctrl *arg, int aer_idx)
 
 	memset(&iod->cmd, 0, sizeof(iod->cmd));
 	iod->cmd.common.opcode = nvme_admin_async_event;
-	iod->cmd.common.command_id = NVME_LOOP_AQ_BLKMQ_DEPTH;
+	iod->cmd.common.command_id = NVME_AQ_BLK_MQ_DEPTH;
 	iod->cmd.common.flags |= NVME_CMD_SGL_METABUF;
 
 	if (!nvmet_req_init(&iod->req, &queue->nvme_cq, &queue->nvme_sq,
@@ -357,7 +349,7 @@ static int nvme_loop_configure_admin_queue(struct nvme_loop_ctrl *ctrl)
 
 	memset(&ctrl->admin_tag_set, 0, sizeof(ctrl->admin_tag_set));
 	ctrl->admin_tag_set.ops = &nvme_loop_admin_mq_ops;
-	ctrl->admin_tag_set.queue_depth = NVME_LOOP_AQ_BLKMQ_DEPTH;
+	ctrl->admin_tag_set.queue_depth = NVME_AQ_MQ_TAG_DEPTH;
 	ctrl->admin_tag_set.reserved_tags = 2; /* connect + keep-alive */
 	ctrl->admin_tag_set.numa_node = NUMA_NO_NODE;
 	ctrl->admin_tag_set.cmd_size = sizeof(struct nvme_loop_iod) +
@@ -365,6 +357,7 @@ static int nvme_loop_configure_admin_queue(struct nvme_loop_ctrl *ctrl)
 	ctrl->admin_tag_set.driver_data = ctrl;
 	ctrl->admin_tag_set.nr_hw_queues = 1;
 	ctrl->admin_tag_set.timeout = ADMIN_TIMEOUT;
+	ctrl->admin_tag_set.flags = BLK_MQ_F_NO_SCHED;
 
 	ctrl->queues[0].ctrl = ctrl;
 	error = nvmet_sq_init(&ctrl->queues[0].nvme_sq);
@@ -438,41 +431,9 @@ static void nvme_loop_shutdown_ctrl(struct nvme_loop_ctrl *ctrl)
 	nvme_loop_destroy_admin_queue(ctrl);
 }
 
-static void nvme_loop_del_ctrl_work(struct work_struct *work)
+static void nvme_loop_delete_ctrl_host(struct nvme_ctrl *ctrl)
 {
-	struct nvme_loop_ctrl *ctrl = container_of(work,
-				struct nvme_loop_ctrl, delete_work);
-
-	nvme_stop_ctrl(&ctrl->ctrl);
-	nvme_remove_namespaces(&ctrl->ctrl);
-	nvme_loop_shutdown_ctrl(ctrl);
-	nvme_uninit_ctrl(&ctrl->ctrl);
-	nvme_put_ctrl(&ctrl->ctrl);
-}
-
-static int __nvme_loop_del_ctrl(struct nvme_loop_ctrl *ctrl)
-{
-	if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_DELETING))
-		return -EBUSY;
-
-	if (!queue_work(nvme_wq, &ctrl->delete_work))
-		return -EBUSY;
-
-	return 0;
-}
-
-static int nvme_loop_del_ctrl(struct nvme_ctrl *nctrl)
-{
-	struct nvme_loop_ctrl *ctrl = to_loop_ctrl(nctrl);
-	int ret;
-
-	ret = __nvme_loop_del_ctrl(ctrl);
-	if (ret)
-		return ret;
-
-	flush_work(&ctrl->delete_work);
-
-	return 0;
+	nvme_loop_shutdown_ctrl(to_loop_ctrl(ctrl));
 }
 
 static void nvme_loop_delete_ctrl(struct nvmet_ctrl *nctrl)
@@ -482,7 +443,7 @@ static void nvme_loop_delete_ctrl(struct nvmet_ctrl *nctrl)
 	mutex_lock(&nvme_loop_ctrl_mutex);
 	list_for_each_entry(ctrl, &nvme_loop_ctrl_list, list) {
 		if (ctrl->ctrl.cntlid == nctrl->cntlid)
-			__nvme_loop_del_ctrl(ctrl);
+			nvme_delete_ctrl(&ctrl->ctrl);
 	}
 	mutex_unlock(&nvme_loop_ctrl_mutex);
 }
@@ -538,7 +499,7 @@ static const struct nvme_ctrl_ops nvme_loop_ctrl_ops = {
 	.reg_write32		= nvmf_reg_write32,
 	.free_ctrl		= nvme_loop_free_ctrl,
 	.submit_async_event	= nvme_loop_submit_async_event,
-	.delete_ctrl		= nvme_loop_del_ctrl,
+	.delete_ctrl		= nvme_loop_delete_ctrl_host,
 };
 
 static int nvme_loop_create_io_queues(struct nvme_loop_ctrl *ctrl)
@@ -600,7 +561,6 @@ static struct nvme_ctrl *nvme_loop_create_ctrl(struct device *dev,
 	ctrl->ctrl.opts = opts;
 	INIT_LIST_HEAD(&ctrl->list);
 
-	INIT_WORK(&ctrl->delete_work, nvme_loop_del_ctrl_work);
 	INIT_WORK(&ctrl->ctrl.reset_work, nvme_loop_reset_ctrl_work);
 
 	ret = nvme_init_ctrl(&ctrl->ctrl, dev, &nvme_loop_ctrl_ops,
@@ -641,7 +601,7 @@ static struct nvme_ctrl *nvme_loop_create_ctrl(struct device *dev,
 	dev_info(ctrl->ctrl.device,
 		 "new ctrl: \"%s\"\n", ctrl->ctrl.opts->subsysnqn);
 
-	kref_get(&ctrl->ctrl.kref);
+	nvme_get_ctrl(&ctrl->ctrl);
 
 	changed = nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_LIVE);
 	WARN_ON_ONCE(!changed);
@@ -730,7 +690,7 @@ static void __exit nvme_loop_cleanup_module(void)
 
 	mutex_lock(&nvme_loop_ctrl_mutex);
 	list_for_each_entry_safe(ctrl, next, &nvme_loop_ctrl_list, list)
-		__nvme_loop_del_ctrl(ctrl);
+		nvme_delete_ctrl(&ctrl->ctrl);
 	mutex_unlock(&nvme_loop_ctrl_mutex);
 
 	flush_workqueue(nvme_wq);
diff --git a/drivers/nvme/target/nvmet.h b/drivers/nvme/target/nvmet.h
index 87e429bfcd8a..417f6c0331cc 100644
--- a/drivers/nvme/target/nvmet.h
+++ b/drivers/nvme/target/nvmet.h
@@ -223,7 +223,10 @@ struct nvmet_req {
 	struct bio		inline_bio;
 	struct bio_vec		inline_bvec[NVMET_MAX_INLINE_BIOVEC];
 	int			sg_cnt;
+	/* data length as parsed from the command: */
 	size_t			data_len;
+	/* data length as parsed from the SGL descriptor: */
+	size_t			transfer_len;
 
 	struct nvmet_port	*port;
 
@@ -266,6 +269,7 @@ u16 nvmet_parse_fabrics_cmd(struct nvmet_req *req);
 bool nvmet_req_init(struct nvmet_req *req, struct nvmet_cq *cq,
 		struct nvmet_sq *sq, struct nvmet_fabrics_ops *ops);
 void nvmet_req_uninit(struct nvmet_req *req);
+void nvmet_req_execute(struct nvmet_req *req);
 void nvmet_req_complete(struct nvmet_req *req, u16 status);
 
 void nvmet_cq_setup(struct nvmet_ctrl *ctrl, struct nvmet_cq *cq, u16 qid,
@@ -314,7 +318,7 @@ u16 nvmet_copy_from_sgl(struct nvmet_req *req, off_t off, void *buf,
 u32 nvmet_get_log_page_len(struct nvme_command *cmd);
 
 #define NVMET_QUEUE_SIZE	1024
-#define NVMET_NR_QUEUES		64
+#define NVMET_NR_QUEUES		128
 #define NVMET_MAX_CMD		NVMET_QUEUE_SIZE
 #define NVMET_KAS		10
 #define NVMET_DISC_KATO		120
diff --git a/drivers/nvme/target/rdma.c b/drivers/nvme/target/rdma.c
index 76d2bb793afe..49912909c298 100644
--- a/drivers/nvme/target/rdma.c
+++ b/drivers/nvme/target/rdma.c
@@ -148,14 +148,14 @@ static inline u32 get_unaligned_le24(const u8 *p)
 static inline bool nvmet_rdma_need_data_in(struct nvmet_rdma_rsp *rsp)
 {
 	return nvme_is_write(rsp->req.cmd) &&
-		rsp->req.data_len &&
+		rsp->req.transfer_len &&
 		!(rsp->flags & NVMET_RDMA_REQ_INLINE_DATA);
 }
 
 static inline bool nvmet_rdma_need_data_out(struct nvmet_rdma_rsp *rsp)
 {
 	return !nvme_is_write(rsp->req.cmd) &&
-		rsp->req.data_len &&
+		rsp->req.transfer_len &&
 		!rsp->req.rsp->status &&
 		!(rsp->flags & NVMET_RDMA_REQ_INLINE_DATA);
 }
@@ -577,7 +577,7 @@ static void nvmet_rdma_read_data_done(struct ib_cq *cq, struct ib_wc *wc)
 		return;
 	}
 
-	rsp->req.execute(&rsp->req);
+	nvmet_req_execute(&rsp->req);
 }
 
 static void nvmet_rdma_use_inline_sg(struct nvmet_rdma_rsp *rsp, u32 len,
@@ -609,6 +609,7 @@ static u16 nvmet_rdma_map_sgl_inline(struct nvmet_rdma_rsp *rsp)
 
 	nvmet_rdma_use_inline_sg(rsp, len, off);
 	rsp->flags |= NVMET_RDMA_REQ_INLINE_DATA;
+	rsp->req.transfer_len += len;
 	return 0;
 }
 
@@ -636,6 +637,7 @@ static u16 nvmet_rdma_map_sgl_keyed(struct nvmet_rdma_rsp *rsp,
 			nvmet_data_dir(&rsp->req));
 	if (ret < 0)
 		return NVME_SC_INTERNAL;
+	rsp->req.transfer_len += len;
 	rsp->n_rdma += ret;
 
 	if (invalidate) {
@@ -693,7 +695,7 @@ static bool nvmet_rdma_execute_command(struct nvmet_rdma_rsp *rsp)
 				queue->cm_id->port_num, &rsp->read_cqe, NULL))
 			nvmet_req_complete(&rsp->req, NVME_SC_DATA_XFER_ERROR);
 	} else {
-		rsp->req.execute(&rsp->req);
+		nvmet_req_execute(&rsp->req);
 	}
 
 	return true;
@@ -1512,15 +1514,17 @@ static struct nvmet_fabrics_ops nvmet_rdma_ops = {
 
 static void nvmet_rdma_remove_one(struct ib_device *ib_device, void *client_data)
 {
-	struct nvmet_rdma_queue *queue;
+	struct nvmet_rdma_queue *queue, *tmp;
 
 	/* Device is being removed, delete all queues using this device */
 	mutex_lock(&nvmet_rdma_queue_mutex);
-	list_for_each_entry(queue, &nvmet_rdma_queue_list, queue_list) {
+	list_for_each_entry_safe(queue, tmp, &nvmet_rdma_queue_list,
+				 queue_list) {
 		if (queue->dev->device != ib_device)
 			continue;
 
 		pr_info("Removing queue %d\n", queue->idx);
+		list_del_init(&queue->queue_list);
 		__nvmet_rdma_queue_disconnect(queue);
 	}
 	mutex_unlock(&nvmet_rdma_queue_mutex);