Merge tag 'for-linus-20190608' of git://git.kernel.dk/linux-block

Pull block fixes from Jens Axboe:

 - Allow symlink from the bfq.weight cgroup parameter to the general
   weight (Angelo)

 - Damien is new skd maintainer (Bart)

 - NVMe pull request from Sagi, with a few small fixes.

 - Ensure we set DMA segment size properly, dma-debug is now tripping on
   these (Christoph)

 - Remove useless debugfs_create() return check (Greg)

 - Remove redundant unlikely() check on IS_ERR() (Kefeng)

 - Fixup request freeing on exit (Ming)

* tag 'for-linus-20190608' of git://git.kernel.dk/linux-block:
  block, bfq: add weight symlink to the bfq.weight cgroup parameter
  cgroup: let a symlink too be created with a cftype file
  block: free sched's request pool in blk_cleanup_queue
  nvme-rdma: use dynamic dma mapping per command
  nvme: Fix u32 overflow in the number of namespace list calculation
  mmc: also set max_segment_size in the device
  mtip32xx: also set max_segment_size in the device
  rsxx: don't call dma_set_max_seg_size
  nvme-pci: don't limit DMA segement size
  block: Drop unlikely before IS_ERR(_OR_NULL)
  block: aoe: no need to check return value of debugfs_create functions
  nvmet: fix data_len to 0 for bdev-backed write_zeroes
  MAINTAINERS: Hand over skd maintainership
  nvme-tcp: fix queue mapping when queue count is limited
  nvme-rdma: fix queue mapping when queue count is limited

MAINTAINERS

@@ -14995,7 +14995,7 @@ S:	Odd Fixes
 F:	drivers/net/ethernet/adaptec/starfire*
 
 STEC S1220 SKD DRIVER
-M:	Bart Van Assche <bart.vanassche@wdc.com>
+M:	Damien Le Moal <Damien.LeMoal@wdc.com>
 L:	linux-block@vger.kernel.org
 S:	Maintained
 F:	drivers/block/skd*[ch]

block/bfq-cgroup.c

@@ -1046,7 +1046,8 @@ struct blkcg_policy blkcg_policy_bfq = {
 struct cftype bfq_blkcg_legacy_files[] = {
 	{
 		.name = "bfq.weight",
-		.flags = CFTYPE_NOT_ON_ROOT,
+		.link_name = "weight",
+		.flags = CFTYPE_NOT_ON_ROOT | CFTYPE_SYMLINKED,
 		.seq_show = bfq_io_show_weight,
 		.write_u64 = bfq_io_set_weight_legacy,
 	},
@@ -1166,7 +1167,8 @@ struct cftype bfq_blkcg_legacy_files[] = {
 struct cftype bfq_blkg_files[] = {
 	{
 		.name = "bfq.weight",
-		.flags = CFTYPE_NOT_ON_ROOT,
+		.link_name = "weight",
+		.flags = CFTYPE_NOT_ON_ROOT | CFTYPE_SYMLINKED,
 		.seq_show = bfq_io_show_weight,
 		.write = bfq_io_set_weight,
 	},

block/blk-cgroup.c

@@ -881,7 +881,7 @@ int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol,
 			blkg_free(new_blkg);
 		} else {
 			blkg = blkg_create(pos, q, new_blkg);
-			if (unlikely(IS_ERR(blkg))) {
+			if (IS_ERR(blkg)) {
 				ret = PTR_ERR(blkg);
 				goto fail_unlock;
 			}

block/blk-core.c

@@ -320,6 +320,19 @@ void blk_cleanup_queue(struct request_queue *q)
 	if (queue_is_mq(q))
 		blk_mq_exit_queue(q);
 
+	/*
+	 * In theory, request pool of sched_tags belongs to request queue.
+	 * However, the current implementation requires tag_set for freeing
+	 * requests, so free the pool now.
+	 *
+	 * Queue has become frozen, there can't be any in-queue requests, so
+	 * it is safe to free requests now.
+	 */
+	mutex_lock(&q->sysfs_lock);
+	if (q->elevator)
+		blk_mq_sched_free_requests(q);
+	mutex_unlock(&q->sysfs_lock);
+
 	percpu_ref_exit(&q->q_usage_counter);
 
 	/* @q is and will stay empty, shutdown and put */

block/blk-mq-sched.c

@@ -475,14 +475,18 @@ static int blk_mq_sched_alloc_tags(struct request_queue *q,
 	return ret;
 }
 
+/* called in queue's release handler, tagset has gone away */
 static void blk_mq_sched_tags_teardown(struct request_queue *q)
 {
-	struct blk_mq_tag_set *set = q->tag_set;
 	struct blk_mq_hw_ctx *hctx;
 	int i;
 
-	queue_for_each_hw_ctx(q, hctx, i)
-		blk_mq_sched_free_tags(set, hctx, i);
+	queue_for_each_hw_ctx(q, hctx, i) {
+		if (hctx->sched_tags) {
+			blk_mq_free_rq_map(hctx->sched_tags);
+			hctx->sched_tags = NULL;
+		}
+	}
 }
 
 int blk_mq_init_sched(struct request_queue *q, struct elevator_type *e)
@@ -523,6 +527,7 @@ int blk_mq_init_sched(struct request_queue *q, struct elevator_type *e)
 			ret = e->ops.init_hctx(hctx, i);
 			if (ret) {
 				eq = q->elevator;
+				blk_mq_sched_free_requests(q);
 				blk_mq_exit_sched(q, eq);
 				kobject_put(&eq->kobj);
 				return ret;
@@ -534,11 +539,30 @@ int blk_mq_init_sched(struct request_queue *q, struct elevator_type *e)
 	return 0;
 
 err:
+	blk_mq_sched_free_requests(q);
 	blk_mq_sched_tags_teardown(q);
 	q->elevator = NULL;
 	return ret;
 }
 
+/*
+ * called in either blk_queue_cleanup or elevator_switch, tagset
+ * is required for freeing requests
+ */
+void blk_mq_sched_free_requests(struct request_queue *q)
+{
+	struct blk_mq_hw_ctx *hctx;
+	int i;
+
+	lockdep_assert_held(&q->sysfs_lock);
+	WARN_ON(!q->elevator);
+
+	queue_for_each_hw_ctx(q, hctx, i) {
+		if (hctx->sched_tags)
+			blk_mq_free_rqs(q->tag_set, hctx->sched_tags, i);
+	}
+}
+
 void blk_mq_exit_sched(struct request_queue *q, struct elevator_queue *e)
 {
 	struct blk_mq_hw_ctx *hctx;

block/blk-mq-sched.h

@@ -28,6 +28,7 @@ void blk_mq_sched_dispatch_requests(struct blk_mq_hw_ctx *hctx);
 
 int blk_mq_init_sched(struct request_queue *q, struct elevator_type *e);
 void blk_mq_exit_sched(struct request_queue *q, struct elevator_queue *e);
+void blk_mq_sched_free_requests(struct request_queue *q);
 
 static inline bool
 blk_mq_sched_bio_merge(struct request_queue *q, struct bio *bio)

block/blk-sysfs.c

@@ -850,7 +850,7 @@ static void blk_exit_queue(struct request_queue *q)
 	 */
 	if (q->elevator) {
 		ioc_clear_queue(q);
-		elevator_exit(q, q->elevator);
+		__elevator_exit(q, q->elevator);
 		q->elevator = NULL;
 	}
 

block/blk.h

@@ -6,6 +6,7 @@
 #include <linux/blk-mq.h>
 #include <xen/xen.h>
 #include "blk-mq.h"
+#include "blk-mq-sched.h"
 
 /* Max future timer expiry for timeouts */
 #define BLK_MAX_TIMEOUT		(5 * HZ)
@@ -176,10 +177,17 @@ void blk_insert_flush(struct request *rq);
 int elevator_init_mq(struct request_queue *q);
 int elevator_switch_mq(struct request_queue *q,
 			      struct elevator_type *new_e);
-void elevator_exit(struct request_queue *, struct elevator_queue *);
+void __elevator_exit(struct request_queue *, struct elevator_queue *);
 int elv_register_queue(struct request_queue *q);
 void elv_unregister_queue(struct request_queue *q);
 
+static inline void elevator_exit(struct request_queue *q,
+		struct elevator_queue *e)
+{
+	blk_mq_sched_free_requests(q);
+	__elevator_exit(q, e);
+}
+
 struct hd_struct *__disk_get_part(struct gendisk *disk, int partno);
 
 #ifdef CONFIG_FAIL_IO_TIMEOUT

block/elevator.c

@@ -178,7 +178,7 @@ static void elevator_release(struct kobject *kobj)
 	kfree(e);
 }
 
-void elevator_exit(struct request_queue *q, struct elevator_queue *e)
+void __elevator_exit(struct request_queue *q, struct elevator_queue *e)
 {
 	mutex_lock(&e->sysfs_lock);
 	if (e->type->ops.exit_sched)

drivers/block/aoe/aoeblk.c

@@ -196,7 +196,6 @@ static const struct file_operations aoe_debugfs_fops = {
 static void
 aoedisk_add_debugfs(struct aoedev *d)
 {
-	struct dentry *entry;
 	char *p;
 
 	if (aoe_debugfs_dir == NULL)
@@ -207,15 +206,8 @@ aoedisk_add_debugfs(struct aoedev *d)
 	else
 		p++;
 	BUG_ON(*p == '\0');
-	entry = debugfs_create_file(p, 0444, aoe_debugfs_dir, d,
+	d->debugfs = debugfs_create_file(p, 0444, aoe_debugfs_dir, d,
 					 &aoe_debugfs_fops);
-	if (IS_ERR_OR_NULL(entry)) {
-		pr_info("aoe: cannot create debugfs file for %s\n",
-			d->gd->disk_name);
-		return;
-	}
-	BUG_ON(d->debugfs);
-	d->debugfs = entry;
 }
 void
 aoedisk_rm_debugfs(struct aoedev *d)
@@ -472,10 +464,6 @@ aoeblk_init(void)
 	if (buf_pool_cache == NULL)
 		return -ENOMEM;
 	aoe_debugfs_dir = debugfs_create_dir("aoe", NULL);
-	if (IS_ERR_OR_NULL(aoe_debugfs_dir)) {
-		pr_info("aoe: cannot create debugfs directory\n");
-		aoe_debugfs_dir = NULL;
-	}
 	return 0;
 }
 

drivers/block/mtip32xx/mtip32xx.c

@@ -3676,6 +3676,7 @@ static int mtip_block_initialize(struct driver_data *dd)
 	blk_queue_physical_block_size(dd->queue, 4096);
 	blk_queue_max_hw_sectors(dd->queue, 0xffff);
 	blk_queue_max_segment_size(dd->queue, 0x400000);
+	dma_set_max_seg_size(&dd->pdev->dev, 0x400000);
 	blk_queue_io_min(dd->queue, 4096);
 
 	/* Set the capacity of the device in 512 byte sectors. */

drivers/block/rsxx/core.c

@@ -767,7 +767,6 @@ static int rsxx_pci_probe(struct pci_dev *dev,
 		goto failed_enable;
 
 	pci_set_master(dev);
-	dma_set_max_seg_size(&dev->dev, RSXX_HW_BLK_SIZE);
 
 	st = dma_set_mask(&dev->dev, DMA_BIT_MASK(64));
 	if (st) {

drivers/mmc/core/queue.c

@@ -377,6 +377,8 @@ static void mmc_setup_queue(struct mmc_queue *mq, struct mmc_card *card)
 	blk_queue_max_segment_size(mq->queue,
 			round_down(host->max_seg_size, block_size));
 
+	dma_set_max_seg_size(mmc_dev(host), queue_max_segment_size(mq->queue));
+
 	INIT_WORK(&mq->recovery_work, mmc_mq_recovery_handler);
 	INIT_WORK(&mq->complete_work, mmc_blk_mq_complete_work);
 

drivers/nvme/host/core.c

@@ -3400,7 +3400,8 @@ static int nvme_scan_ns_list(struct nvme_ctrl *ctrl, unsigned nn)
 {
 	struct nvme_ns *ns;
 	__le32 *ns_list;
-	unsigned i, j, nsid, prev = 0, num_lists = DIV_ROUND_UP(nn, 1024);
+	unsigned i, j, nsid, prev = 0;
+	unsigned num_lists = DIV_ROUND_UP_ULL((u64)nn, 1024);
 	int ret = 0;
 
 	ns_list = kzalloc(NVME_IDENTIFY_DATA_SIZE, GFP_KERNEL);

drivers/nvme/host/pci.c

@@ -2513,6 +2513,12 @@ static void nvme_reset_work(struct work_struct *work)
 	 */
 	dev->ctrl.max_hw_sectors = NVME_MAX_KB_SZ << 1;
 	dev->ctrl.max_segments = NVME_MAX_SEGS;
+
+	/*
+	 * Don't limit the IOMMU merged segment size.
+	 */
+	dma_set_max_seg_size(dev->dev, 0xffffffff);
+
 	mutex_unlock(&dev->shutdown_lock);
 
 	/*

drivers/nvme/host/rdma.c

@@ -213,6 +213,11 @@ static struct nvme_rdma_qe *nvme_rdma_alloc_ring(struct ib_device *ibdev,
 	if (!ring)
 		return NULL;
 
+	/*
+	 * Bind the CQEs (post recv buffers) DMA mapping to the RDMA queue
+	 * lifetime. It's safe, since any chage in the underlying RDMA device
+	 * will issue error recovery and queue re-creation.
+	 */
 	for (i = 0; i < ib_queue_size; i++) {
 		if (nvme_rdma_alloc_qe(ibdev, &ring[i], capsule_size, dir))
 			goto out_free_ring;
@@ -274,14 +279,9 @@ static int nvme_rdma_create_qp(struct nvme_rdma_queue *queue, const int factor)
 static void nvme_rdma_exit_request(struct blk_mq_tag_set *set,
 		struct request *rq, unsigned int hctx_idx)
 {
-	struct nvme_rdma_ctrl *ctrl = set->driver_data;
 	struct nvme_rdma_request *req = blk_mq_rq_to_pdu(rq);
-	int queue_idx = (set == &ctrl->tag_set) ? hctx_idx + 1 : 0;
-	struct nvme_rdma_queue *queue = &ctrl->queues[queue_idx];
-	struct nvme_rdma_device *dev = queue->device;
 
-	nvme_rdma_free_qe(dev->dev, &req->sqe, sizeof(struct nvme_command),
-			DMA_TO_DEVICE);
+	kfree(req->sqe.data);
 }
 
 static int nvme_rdma_init_request(struct blk_mq_tag_set *set,
@@ -292,15 +292,11 @@ static int nvme_rdma_init_request(struct blk_mq_tag_set *set,
 	struct nvme_rdma_request *req = blk_mq_rq_to_pdu(rq);
 	int queue_idx = (set == &ctrl->tag_set) ? hctx_idx + 1 : 0;
 	struct nvme_rdma_queue *queue = &ctrl->queues[queue_idx];
-	struct nvme_rdma_device *dev = queue->device;
-	struct ib_device *ibdev = dev->dev;
-	int ret;
 
 	nvme_req(rq)->ctrl = &ctrl->ctrl;
-	ret = nvme_rdma_alloc_qe(ibdev, &req->sqe, sizeof(struct nvme_command),
-			DMA_TO_DEVICE);
-	if (ret)
-		return ret;
+	req->sqe.data = kzalloc(sizeof(struct nvme_command), GFP_KERNEL);
+	if (!req->sqe.data)
+		return -ENOMEM;
 
 	req->queue = queue;
 
@@ -641,34 +637,16 @@ static int nvme_rdma_alloc_io_queues(struct nvme_rdma_ctrl *ctrl)
 {
 	struct nvmf_ctrl_options *opts = ctrl->ctrl.opts;
 	struct ib_device *ibdev = ctrl->device->dev;
-	unsigned int nr_io_queues;
+	unsigned int nr_io_queues, nr_default_queues;
+	unsigned int nr_read_queues, nr_poll_queues;
 	int i, ret;
 
-	nr_io_queues = min(opts->nr_io_queues, num_online_cpus());
-
-	/*
-	 * we map queues according to the device irq vectors for
-	 * optimal locality so we don't need more queues than
-	 * completion vectors.
-	 */
-	nr_io_queues = min_t(unsigned int, nr_io_queues,
-				ibdev->num_comp_vectors);
-
-	if (opts->nr_write_queues) {
-		ctrl->io_queues[HCTX_TYPE_DEFAULT] =
-				min(opts->nr_write_queues, nr_io_queues);
-		nr_io_queues += ctrl->io_queues[HCTX_TYPE_DEFAULT];
-	} else {
-		ctrl->io_queues[HCTX_TYPE_DEFAULT] = nr_io_queues;
-	}
-
-	ctrl->io_queues[HCTX_TYPE_READ] = nr_io_queues;
-
-	if (opts->nr_poll_queues) {
-		ctrl->io_queues[HCTX_TYPE_POLL] =
-			min(opts->nr_poll_queues, num_online_cpus());
-		nr_io_queues += ctrl->io_queues[HCTX_TYPE_POLL];
-	}
+	nr_read_queues = min_t(unsigned int, ibdev->num_comp_vectors,
+				min(opts->nr_io_queues, num_online_cpus()));
+	nr_default_queues =  min_t(unsigned int, ibdev->num_comp_vectors,
+				min(opts->nr_write_queues, num_online_cpus()));
+	nr_poll_queues = min(opts->nr_poll_queues, num_online_cpus());
+	nr_io_queues = nr_read_queues + nr_default_queues + nr_poll_queues;
 
 	ret = nvme_set_queue_count(&ctrl->ctrl, &nr_io_queues);
 	if (ret)
@@ -681,6 +659,34 @@ static int nvme_rdma_alloc_io_queues(struct nvme_rdma_ctrl *ctrl)
 	dev_info(ctrl->ctrl.device,
 		"creating %d I/O queues.\n", nr_io_queues);
 
+	if (opts->nr_write_queues && nr_read_queues < nr_io_queues) {
+		/*
+		 * separate read/write queues
+		 * hand out dedicated default queues only after we have
+		 * sufficient read queues.
+		 */
+		ctrl->io_queues[HCTX_TYPE_READ] = nr_read_queues;
+		nr_io_queues -= ctrl->io_queues[HCTX_TYPE_READ];
+		ctrl->io_queues[HCTX_TYPE_DEFAULT] =
+			min(nr_default_queues, nr_io_queues);
+		nr_io_queues -= ctrl->io_queues[HCTX_TYPE_DEFAULT];
+	} else {
+		/*
+		 * shared read/write queues
+		 * either no write queues were requested, or we don't have
+		 * sufficient queue count to have dedicated default queues.
+		 */
+		ctrl->io_queues[HCTX_TYPE_DEFAULT] =
+			min(nr_read_queues, nr_io_queues);
+		nr_io_queues -= ctrl->io_queues[HCTX_TYPE_DEFAULT];
+	}
+
+	if (opts->nr_poll_queues && nr_io_queues) {
+		/* map dedicated poll queues only if we have queues left */
+		ctrl->io_queues[HCTX_TYPE_POLL] =
+			min(nr_poll_queues, nr_io_queues);
+	}
+
 	for (i = 1; i < ctrl->ctrl.queue_count; i++) {
 		ret = nvme_rdma_alloc_queue(ctrl, i,
 				ctrl->ctrl.sqsize + 1);
@@ -769,6 +775,11 @@ static int nvme_rdma_configure_admin_queue(struct nvme_rdma_ctrl *ctrl,
 
 	ctrl->max_fr_pages = nvme_rdma_get_max_fr_pages(ctrl->device->dev);
 
+	/*
+	 * 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
+	 * error recovery and queue re-creation.
+	 */
 	error = nvme_rdma_alloc_qe(ctrl->device->dev, &ctrl->async_event_sqe,
 			sizeof(struct nvme_command), DMA_TO_DEVICE);
 	if (error)
@@ -1709,12 +1720,20 @@ static blk_status_t nvme_rdma_queue_rq(struct blk_mq_hw_ctx *hctx,
 		return nvmf_fail_nonready_command(&queue->ctrl->ctrl, rq);
 
 	dev = queue->device->dev;
+
+	req->sqe.dma = ib_dma_map_single(dev, req->sqe.data,
+					 sizeof(struct nvme_command),
+					 DMA_TO_DEVICE);
+	err = ib_dma_mapping_error(dev, req->sqe.dma);
+	if (unlikely(err))
+		return BLK_STS_RESOURCE;
+
 	ib_dma_sync_single_for_cpu(dev, sqe->dma,
 			sizeof(struct nvme_command), DMA_TO_DEVICE);
 
 	ret = nvme_setup_cmd(ns, rq, c);
 	if (ret)
-		return ret;
+		goto unmap_qe;
 
 	blk_mq_start_request(rq);
 
@@ -1739,10 +1758,16 @@ static blk_status_t nvme_rdma_queue_rq(struct blk_mq_hw_ctx *hctx,
 	}
 
 	return BLK_STS_OK;
+
 err:
 	if (err == -ENOMEM || err == -EAGAIN)
-		return BLK_STS_RESOURCE;
-	return BLK_STS_IOERR;
+		ret = BLK_STS_RESOURCE;
+	else
+		ret = BLK_STS_IOERR;
+unmap_qe:
+	ib_dma_unmap_single(dev, req->sqe.dma, sizeof(struct nvme_command),
+			    DMA_TO_DEVICE);
+	return ret;
 }
 
 static int nvme_rdma_poll(struct blk_mq_hw_ctx *hctx)
@@ -1755,25 +1780,36 @@ static int nvme_rdma_poll(struct blk_mq_hw_ctx *hctx)
 static void nvme_rdma_complete_rq(struct request *rq)
 {
 	struct nvme_rdma_request *req = blk_mq_rq_to_pdu(rq);
+	struct nvme_rdma_queue *queue = req->queue;
+	struct ib_device *ibdev = queue->device->dev;
 
-	nvme_rdma_unmap_data(req->queue, rq);
+	nvme_rdma_unmap_data(queue, rq);
+	ib_dma_unmap_single(ibdev, req->sqe.dma, sizeof(struct nvme_command),
+			    DMA_TO_DEVICE);
 	nvme_complete_rq(rq);
 }
 
 static int nvme_rdma_map_queues(struct blk_mq_tag_set *set)
 {
 	struct nvme_rdma_ctrl *ctrl = set->driver_data;
+	struct nvmf_ctrl_options *opts = ctrl->ctrl.opts;
 
-	set->map[HCTX_TYPE_DEFAULT].queue_offset = 0;
+	if (opts->nr_write_queues && ctrl->io_queues[HCTX_TYPE_READ]) {
+		/* separate read/write queues */
 		set->map[HCTX_TYPE_DEFAULT].nr_queues =
 			ctrl->io_queues[HCTX_TYPE_DEFAULT];
-	set->map[HCTX_TYPE_READ].nr_queues = ctrl->io_queues[HCTX_TYPE_READ];
-	if (ctrl->ctrl.opts->nr_write_queues) {
-		/* separate read/write queues */
+		set->map[HCTX_TYPE_DEFAULT].queue_offset = 0;
+		set->map[HCTX_TYPE_READ].nr_queues =
+			ctrl->io_queues[HCTX_TYPE_READ];
 		set->map[HCTX_TYPE_READ].queue_offset =
 			ctrl->io_queues[HCTX_TYPE_DEFAULT];
 	} else {
-		/* mixed read/write queues */
+		/* shared read/write queues */
+		set->map[HCTX_TYPE_DEFAULT].nr_queues =
+			ctrl->io_queues[HCTX_TYPE_DEFAULT];
+		set->map[HCTX_TYPE_DEFAULT].queue_offset = 0;
+		set->map[HCTX_TYPE_READ].nr_queues =
+			ctrl->io_queues[HCTX_TYPE_DEFAULT];
 		set->map[HCTX_TYPE_READ].queue_offset = 0;
 	}
 	blk_mq_rdma_map_queues(&set->map[HCTX_TYPE_DEFAULT],
@@ -1781,16 +1817,22 @@ static int nvme_rdma_map_queues(struct blk_mq_tag_set *set)
 	blk_mq_rdma_map_queues(&set->map[HCTX_TYPE_READ],
 			ctrl->device->dev, 0);
 
-	if (ctrl->ctrl.opts->nr_poll_queues) {
+	if (opts->nr_poll_queues && ctrl->io_queues[HCTX_TYPE_POLL]) {
+		/* map dedicated poll queues only if we have queues left */
 		set->map[HCTX_TYPE_POLL].nr_queues =
 				ctrl->io_queues[HCTX_TYPE_POLL];
 		set->map[HCTX_TYPE_POLL].queue_offset =
-				ctrl->io_queues[HCTX_TYPE_DEFAULT];
-		if (ctrl->ctrl.opts->nr_write_queues)
-			set->map[HCTX_TYPE_POLL].queue_offset +=
+			ctrl->io_queues[HCTX_TYPE_DEFAULT] +
 			ctrl->io_queues[HCTX_TYPE_READ];
 		blk_mq_map_queues(&set->map[HCTX_TYPE_POLL]);
 	}
+
+	dev_info(ctrl->ctrl.device,
+		"mapped %d/%d/%d default/read/poll queues.\n",
+		ctrl->io_queues[HCTX_TYPE_DEFAULT],
+		ctrl->io_queues[HCTX_TYPE_READ],
+		ctrl->io_queues[HCTX_TYPE_POLL]);
+
 	return 0;
 }
 

drivers/nvme/host/tcp.c

@@ -111,6 +111,7 @@ struct nvme_tcp_ctrl {
 	struct work_struct	err_work;
 	struct delayed_work	connect_work;
 	struct nvme_tcp_request async_req;
+	u32			io_queues[HCTX_MAX_TYPES];
 };
 
 static LIST_HEAD(nvme_tcp_ctrl_list);
@@ -1564,6 +1565,35 @@ static unsigned int nvme_tcp_nr_io_queues(struct nvme_ctrl *ctrl)
 	return nr_io_queues;
 }
 
+static void nvme_tcp_set_io_queues(struct nvme_ctrl *nctrl,
+		unsigned int nr_io_queues)
+{
+	struct nvme_tcp_ctrl *ctrl = to_tcp_ctrl(nctrl);
+	struct nvmf_ctrl_options *opts = nctrl->opts;
+
+	if (opts->nr_write_queues && opts->nr_io_queues < nr_io_queues) {
+		/*
+		 * separate read/write queues
+		 * hand out dedicated default queues only after we have
+		 * sufficient read queues.
+		 */
+		ctrl->io_queues[HCTX_TYPE_READ] = opts->nr_io_queues;
+		nr_io_queues -= ctrl->io_queues[HCTX_TYPE_READ];
+		ctrl->io_queues[HCTX_TYPE_DEFAULT] =
+			min(opts->nr_write_queues, nr_io_queues);
+		nr_io_queues -= ctrl->io_queues[HCTX_TYPE_DEFAULT];
+	} else {
+		/*
+		 * shared read/write queues
+		 * either no write queues were requested, or we don't have
+		 * sufficient queue count to have dedicated default queues.
+		 */
+		ctrl->io_queues[HCTX_TYPE_DEFAULT] =
+			min(opts->nr_io_queues, nr_io_queues);
+		nr_io_queues -= ctrl->io_queues[HCTX_TYPE_DEFAULT];
+	}
+}
+
 static int nvme_tcp_alloc_io_queues(struct nvme_ctrl *ctrl)
 {
 	unsigned int nr_io_queues;
@@ -1581,6 +1611,8 @@ static int nvme_tcp_alloc_io_queues(struct nvme_ctrl *ctrl)
 	dev_info(ctrl->device,
 		"creating %d I/O queues.\n", nr_io_queues);
 
+	nvme_tcp_set_io_queues(ctrl, nr_io_queues);
+
 	return __nvme_tcp_alloc_io_queues(ctrl);
 }
 
@@ -2089,23 +2121,34 @@ static blk_status_t nvme_tcp_queue_rq(struct blk_mq_hw_ctx *hctx,
 static int nvme_tcp_map_queues(struct blk_mq_tag_set *set)
 {
 	struct nvme_tcp_ctrl *ctrl = set->driver_data;
+	struct nvmf_ctrl_options *opts = ctrl->ctrl.opts;
 
-	set->map[HCTX_TYPE_DEFAULT].queue_offset = 0;
-	set->map[HCTX_TYPE_READ].nr_queues = ctrl->ctrl.opts->nr_io_queues;
-	if (ctrl->ctrl.opts->nr_write_queues) {
+	if (opts->nr_write_queues && ctrl->io_queues[HCTX_TYPE_READ]) {
 		/* separate read/write queues */
 		set->map[HCTX_TYPE_DEFAULT].nr_queues =
-				ctrl->ctrl.opts->nr_write_queues;
+			ctrl->io_queues[HCTX_TYPE_DEFAULT];
+		set->map[HCTX_TYPE_DEFAULT].queue_offset = 0;
+		set->map[HCTX_TYPE_READ].nr_queues =
+			ctrl->io_queues[HCTX_TYPE_READ];
 		set->map[HCTX_TYPE_READ].queue_offset =
-				ctrl->ctrl.opts->nr_write_queues;
+			ctrl->io_queues[HCTX_TYPE_DEFAULT];
 	} else {
-		/* mixed read/write queues */
+		/* shared read/write queues */
 		set->map[HCTX_TYPE_DEFAULT].nr_queues =
-				ctrl->ctrl.opts->nr_io_queues;
+			ctrl->io_queues[HCTX_TYPE_DEFAULT];
+		set->map[HCTX_TYPE_DEFAULT].queue_offset = 0;
+		set->map[HCTX_TYPE_READ].nr_queues =
+			ctrl->io_queues[HCTX_TYPE_DEFAULT];
 		set->map[HCTX_TYPE_READ].queue_offset = 0;
 	}
 	blk_mq_map_queues(&set->map[HCTX_TYPE_DEFAULT]);
 	blk_mq_map_queues(&set->map[HCTX_TYPE_READ]);
+
+	dev_info(ctrl->ctrl.device,
+		"mapped %d/%d default/read queues.\n",
+		ctrl->io_queues[HCTX_TYPE_DEFAULT],
+		ctrl->io_queues[HCTX_TYPE_READ]);
+
 	return 0;
 }
 

drivers/nvme/target/io-cmd-bdev.c

@@ -293,6 +293,7 @@ u16 nvmet_bdev_parse_io_cmd(struct nvmet_req *req)
 		return 0;
 	case nvme_cmd_write_zeroes:
 		req->execute = nvmet_bdev_execute_write_zeroes;
+		req->data_len = 0;
 		return 0;
 	default:
 		pr_err("unhandled cmd %d on qid %d\n", cmd->common.opcode,

include/linux/cgroup-defs.h

@@ -106,6 +106,8 @@ enum {
 	CFTYPE_WORLD_WRITABLE	= (1 << 4),	/* (DON'T USE FOR NEW FILES) S_IWUGO */
 	CFTYPE_DEBUG		= (1 << 5),	/* create when cgroup_debug */
 
+	CFTYPE_SYMLINKED	= (1 << 6),	/* pointed to by symlink too */
+
 	/* internal flags, do not use outside cgroup core proper */
 	__CFTYPE_ONLY_ON_DFL	= (1 << 16),	/* only on default hierarchy */
 	__CFTYPE_NOT_ON_DFL	= (1 << 17),	/* not on default hierarchy */
@@ -543,6 +545,7 @@ struct cftype {
 	 * end of cftype array.
 	 */
 	char name[MAX_CFTYPE_NAME];
+	char link_name[MAX_CFTYPE_NAME];
 	unsigned long private;
 
 	/*

kernel/cgroup/cgroup.c

@@ -1460,8 +1460,8 @@ struct cgroup *task_cgroup_from_root(struct task_struct *task,
 
 static struct kernfs_syscall_ops cgroup_kf_syscall_ops;
 
-static char *cgroup_file_name(struct cgroup *cgrp, const struct cftype *cft,
-			      char *buf)
+static char *cgroup_fill_name(struct cgroup *cgrp, const struct cftype *cft,
+			      char *buf, bool write_link_name)
 {
 	struct cgroup_subsys *ss = cft->ss;
 
@@ -1471,13 +1471,26 @@ static char *cgroup_file_name(struct cgroup *cgrp, const struct cftype *cft,
 
 		snprintf(buf, CGROUP_FILE_NAME_MAX, "%s%s.%s",
 			 dbg, cgroup_on_dfl(cgrp) ? ss->name : ss->legacy_name,
-			 cft->name);
+			 write_link_name ? cft->link_name : cft->name);
 	} else {
-		strscpy(buf, cft->name, CGROUP_FILE_NAME_MAX);
+		strscpy(buf, write_link_name ? cft->link_name : cft->name,
+			CGROUP_FILE_NAME_MAX);
 	}
 	return buf;
 }
 
+static char *cgroup_file_name(struct cgroup *cgrp, const struct cftype *cft,
+			      char *buf)
+{
+	return cgroup_fill_name(cgrp, cft, buf, false);
+}
+
+static char *cgroup_link_name(struct cgroup *cgrp, const struct cftype *cft,
+			      char *buf)
+{
+	return cgroup_fill_name(cgrp, cft, buf, true);
+}
+
 /**
  * cgroup_file_mode - deduce file mode of a control file
  * @cft: the control file in question
@@ -1636,6 +1649,9 @@ static void cgroup_rm_file(struct cgroup *cgrp, const struct cftype *cft)
 	}
 
 	kernfs_remove_by_name(cgrp->kn, cgroup_file_name(cgrp, cft, name));
+	if (cft->flags & CFTYPE_SYMLINKED)
+		kernfs_remove_by_name(cgrp->kn,
+				      cgroup_link_name(cgrp, cft, name));
 }
 
 /**
@@ -3821,6 +3837,7 @@ static int cgroup_add_file(struct cgroup_subsys_state *css, struct cgroup *cgrp,
 {
 	char name[CGROUP_FILE_NAME_MAX];
 	struct kernfs_node *kn;
+	struct kernfs_node *kn_link;
 	struct lock_class_key *key = NULL;
 	int ret;
 
@@ -3851,6 +3868,14 @@ static int cgroup_add_file(struct cgroup_subsys_state *css, struct cgroup *cgrp,
 		spin_unlock_irq(&cgroup_file_kn_lock);
 	}
 
+	if (cft->flags & CFTYPE_SYMLINKED) {
+		kn_link = kernfs_create_link(cgrp->kn,
+					     cgroup_link_name(cgrp, cft, name),
+					     kn);
+		if (IS_ERR(kn_link))
+			return PTR_ERR(kn_link);
+	}
+
 	return 0;
 }