Merge tag 'for-6.1/block-2022-10-03' of git://git.kernel.dk/linux

Pull block updates from Jens Axboe:

 - NVMe pull requests via Christoph:
      - handle number of queue changes in the TCP and RDMA drivers
        (Daniel Wagner)
      - allow changing the number of queues in nvmet (Daniel Wagner)
      - also consider host_iface when checking ip options (Daniel
        Wagner)
      - don't map pages which can't come from HIGHMEM (Fabio M. De
        Francesco)
      - avoid unnecessary flush bios in nvmet (Guixin Liu)
      - shrink and better pack the nvme_iod structure (Keith Busch)
      - add comment for unaligned "fake" nqn (Linjun Bao)
      - print actual source IP address through sysfs "address" attr
        (Martin Belanger)
      - various cleanups (Jackie Liu, Wolfram Sang, Genjian Zhang)
      - handle effects after freeing the request (Keith Busch)
      - copy firmware_rev on each init (Keith Busch)
      - restrict management ioctls to admin (Keith Busch)
      - ensure subsystem reset is single threaded (Keith Busch)
      - report the actual number of tagset maps in nvme-pci (Keith
        Busch)
      - small fabrics authentication fixups (Christoph Hellwig)
      - add common code for tagset allocation and freeing (Christoph
        Hellwig)
      - stop using the request_queue in nvmet (Christoph Hellwig)
      - set min_align_mask before calculating max_hw_sectors (Rishabh
        Bhatnagar)
      - send a rediscover uevent when a persistent discovery controller
        reconnects (Sagi Grimberg)
      - misc nvmet-tcp fixes (Varun Prakash, zhenwei pi)

 - MD pull request via Song:
      - Various raid5 fix and clean up, by Logan Gunthorpe and David
        Sloan.
      - Raid10 performance optimization, by Yu Kuai.

 - sbitmap wakeup hang fixes (Hugh, Keith, Jan, Yu)

 - IO scheduler switching quisce fix (Keith)

 - s390/dasd block driver updates (Stefan)

 - support for recovery for the ublk driver (ZiyangZhang)

 - rnbd drivers fixes and updates (Guoqing, Santosh, ye, Christoph)

 - blk-mq and null_blk map fixes (Bart)

 - various bcache fixes (Coly, Jilin, Jules)

 - nbd signal hang fix (Shigeru)

 - block writeback throttling fix (Yu)

 - optimize the passthrough mapping handling (me)

 - prepare block cgroups to being gendisk based (Christoph)

 - get rid of an old PSI hack in the block layer, moving it to the
   callers instead where it belongs (Christoph)

 - blk-throttle fixes and cleanups (Yu)

 - misc fixes and cleanups (Liu Shixin, Liu Song, Miaohe, Pankaj,
   Ping-Xiang, Wolfram, Saurabh, Li Jinlin, Li Lei, Lin, Li zeming,
   Miaohe, Bart, Coly, Gaosheng

* tag 'for-6.1/block-2022-10-03' of git://git.kernel.dk/linux: (162 commits)
  sbitmap: fix lockup while swapping
  block: add rationale for not using blk_mq_plug() when applicable
  block: adapt blk_mq_plug() to not plug for writes that require a zone lock
  s390/dasd: use blk_mq_alloc_disk
  blk-cgroup: don't update the blkg lookup hint in blkg_conf_prep
  nvmet: don't look at the request_queue in nvmet_bdev_set_limits
  nvmet: don't look at the request_queue in nvmet_bdev_zone_mgmt_emulate_all
  blk-mq: use quiesced elevator switch when reinitializing queues
  block: replace blk_queue_nowait with bdev_nowait
  nvme: remove nvme_ctrl_init_connect_q
  nvme-loop: use the tagset alloc/free helpers
  nvme-loop: store the generic nvme_ctrl in set->driver_data
  nvme-loop: initialize sqsize later
  nvme-fc: use the tagset alloc/free helpers
  nvme-fc: store the generic nvme_ctrl in set->driver_data
  nvme-fc: keep ctrl->sqsize in sync with opts->queue_size
  nvme-rdma: use the tagset alloc/free helpers
  nvme-rdma: store the generic nvme_ctrl in set->driver_data
  nvme-tcp: use the tagset alloc/free helpers
  nvme-tcp: store the generic nvme_ctrl in set->driver_data
  ...

1 files changed, 65 insertions, 104 deletions

diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
index d5871fd6f769..93e2e313fa70 100644
--- a/drivers/nvme/host/tcp.c
+++ b/drivers/nvme/host/tcp.c
@@ -133,7 +133,6 @@ struct nvme_tcp_queue {
 	/* send state */
 	struct nvme_tcp_request *request;
 
-	int			queue_size;
 	u32			maxh2cdata;
 	size_t			cmnd_capsule_len;
 	struct nvme_tcp_ctrl	*ctrl;
@@ -463,7 +462,7 @@ static int nvme_tcp_init_request(struct blk_mq_tag_set *set,
 		struct request *rq, unsigned int hctx_idx,
 		unsigned int numa_node)
 {
-	struct nvme_tcp_ctrl *ctrl = set->driver_data;
+	struct nvme_tcp_ctrl *ctrl = to_tcp_ctrl(set->driver_data);
 	struct nvme_tcp_request *req = blk_mq_rq_to_pdu(rq);
 	struct nvme_tcp_cmd_pdu *pdu;
 	int queue_idx = (set == &ctrl->tag_set) ? hctx_idx + 1 : 0;
@@ -487,7 +486,7 @@ static int nvme_tcp_init_request(struct blk_mq_tag_set *set,
 static int nvme_tcp_init_hctx(struct blk_mq_hw_ctx *hctx, void *data,
 		unsigned int hctx_idx)
 {
-	struct nvme_tcp_ctrl *ctrl = data;
+	struct nvme_tcp_ctrl *ctrl = to_tcp_ctrl(data);
 	struct nvme_tcp_queue *queue = &ctrl->queues[hctx_idx + 1];
 
 	hctx->driver_data = queue;
@@ -497,7 +496,7 @@ static int nvme_tcp_init_hctx(struct blk_mq_hw_ctx *hctx, void *data,
 static int nvme_tcp_init_admin_hctx(struct blk_mq_hw_ctx *hctx, void *data,
 		unsigned int hctx_idx)
 {
-	struct nvme_tcp_ctrl *ctrl = data;
+	struct nvme_tcp_ctrl *ctrl = to_tcp_ctrl(data);
 	struct nvme_tcp_queue *queue = &ctrl->queues[0];
 
 	hctx->driver_data = queue;
@@ -1476,8 +1475,7 @@ static void nvme_tcp_set_queue_io_cpu(struct nvme_tcp_queue *queue)
 	queue->io_cpu = cpumask_next_wrap(n - 1, cpu_online_mask, -1, false);
 }
 
-static int nvme_tcp_alloc_queue(struct nvme_ctrl *nctrl,
-		int qid, size_t queue_size)
+static int nvme_tcp_alloc_queue(struct nvme_ctrl *nctrl, int qid)
 {
 	struct nvme_tcp_ctrl *ctrl = to_tcp_ctrl(nctrl);
 	struct nvme_tcp_queue *queue = &ctrl->queues[qid];
@@ -1489,7 +1487,6 @@ static int nvme_tcp_alloc_queue(struct nvme_ctrl *nctrl,
 	INIT_LIST_HEAD(&queue->send_list);
 	mutex_init(&queue->send_mutex);
 	INIT_WORK(&queue->io_work, nvme_tcp_io_work);
-	queue->queue_size = queue_size;
 
 	if (qid > 0)
 		queue->cmnd_capsule_len = nctrl->ioccsz * 16;
@@ -1687,51 +1684,6 @@ static int nvme_tcp_start_queue(struct nvme_ctrl *nctrl, int idx)
 	return ret;
 }
 
-static int nvme_tcp_alloc_admin_tag_set(struct nvme_ctrl *nctrl)
-{
-	struct nvme_tcp_ctrl *ctrl = to_tcp_ctrl(nctrl);
-	struct blk_mq_tag_set *set = &ctrl->admin_tag_set;
-	int ret;
-
-	memset(set, 0, sizeof(*set));
-	set->ops = &nvme_tcp_admin_mq_ops;
-	set->queue_depth = NVME_AQ_MQ_TAG_DEPTH;
-	set->reserved_tags = NVMF_RESERVED_TAGS;
-	set->numa_node = nctrl->numa_node;
-	set->flags = BLK_MQ_F_BLOCKING;
-	set->cmd_size = sizeof(struct nvme_tcp_request);
-	set->driver_data = ctrl;
-	set->nr_hw_queues = 1;
-	set->timeout = NVME_ADMIN_TIMEOUT;
-	ret = blk_mq_alloc_tag_set(set);
-	if (!ret)
-		nctrl->admin_tagset = set;
-	return ret;
-}
-
-static int nvme_tcp_alloc_tag_set(struct nvme_ctrl *nctrl)
-{
-	struct nvme_tcp_ctrl *ctrl = to_tcp_ctrl(nctrl);
-	struct blk_mq_tag_set *set = &ctrl->tag_set;
-	int ret;
-
-	memset(set, 0, sizeof(*set));
-	set->ops = &nvme_tcp_mq_ops;
-	set->queue_depth = nctrl->sqsize + 1;
-	set->reserved_tags = NVMF_RESERVED_TAGS;
-	set->numa_node = nctrl->numa_node;
-	set->flags = BLK_MQ_F_SHOULD_MERGE | BLK_MQ_F_BLOCKING;
-	set->cmd_size = sizeof(struct nvme_tcp_request);
-	set->driver_data = ctrl;
-	set->nr_hw_queues = nctrl->queue_count - 1;
-	set->timeout = NVME_IO_TIMEOUT;
-	set->nr_maps = nctrl->opts->nr_poll_queues ? HCTX_MAX_TYPES : 2;
-	ret = blk_mq_alloc_tag_set(set);
-	if (!ret)
-		nctrl->tagset = set;
-	return ret;
-}
-
 static void nvme_tcp_free_admin_queue(struct nvme_ctrl *ctrl)
 {
 	if (to_tcp_ctrl(ctrl)->async_req.pdu) {
@@ -1759,11 +1711,12 @@ static void nvme_tcp_stop_io_queues(struct nvme_ctrl *ctrl)
 		nvme_tcp_stop_queue(ctrl, i);
 }
 
-static int nvme_tcp_start_io_queues(struct nvme_ctrl *ctrl)
+static int nvme_tcp_start_io_queues(struct nvme_ctrl *ctrl,
+				    int first, int last)
 {
 	int i, ret;
 
-	for (i = 1; i < ctrl->queue_count; i++) {
+	for (i = first; i < last; i++) {
 		ret = nvme_tcp_start_queue(ctrl, i);
 		if (ret)
 			goto out_stop_queues;
@@ -1772,7 +1725,7 @@ static int nvme_tcp_start_io_queues(struct nvme_ctrl *ctrl)
 	return 0;
 
 out_stop_queues:
-	for (i--; i >= 1; i--)
+	for (i--; i >= first; i--)
 		nvme_tcp_stop_queue(ctrl, i);
 	return ret;
 }
@@ -1781,7 +1734,7 @@ static int nvme_tcp_alloc_admin_queue(struct nvme_ctrl *ctrl)
 {
 	int ret;
 
-	ret = nvme_tcp_alloc_queue(ctrl, 0, NVME_AQ_DEPTH);
+	ret = nvme_tcp_alloc_queue(ctrl, 0);
 	if (ret)
 		return ret;
 
@@ -1801,7 +1754,7 @@ static int __nvme_tcp_alloc_io_queues(struct nvme_ctrl *ctrl)
 	int i, ret;
 
 	for (i = 1; i < ctrl->queue_count; i++) {
-		ret = nvme_tcp_alloc_queue(ctrl, i, ctrl->sqsize + 1);
+		ret = nvme_tcp_alloc_queue(ctrl, i);
 		if (ret)
 			goto out_free_queues;
 	}
@@ -1889,32 +1842,35 @@ static int nvme_tcp_alloc_io_queues(struct nvme_ctrl *ctrl)
 static void nvme_tcp_destroy_io_queues(struct nvme_ctrl *ctrl, bool remove)
 {
 	nvme_tcp_stop_io_queues(ctrl);
-	if (remove) {
-		blk_mq_destroy_queue(ctrl->connect_q);
-		blk_mq_free_tag_set(ctrl->tagset);
-	}
+	if (remove)
+		nvme_remove_io_tag_set(ctrl);
 	nvme_tcp_free_io_queues(ctrl);
 }
 
 static int nvme_tcp_configure_io_queues(struct nvme_ctrl *ctrl, bool new)
 {
-	int ret;
+	int ret, nr_queues;
 
 	ret = nvme_tcp_alloc_io_queues(ctrl);
 	if (ret)
 		return ret;
 
 	if (new) {
-		ret = nvme_tcp_alloc_tag_set(ctrl);
+		ret = nvme_alloc_io_tag_set(ctrl, &to_tcp_ctrl(ctrl)->tag_set,
+				&nvme_tcp_mq_ops,
+				BLK_MQ_F_SHOULD_MERGE | BLK_MQ_F_BLOCKING,
+				sizeof(struct nvme_tcp_request));
 		if (ret)
 			goto out_free_io_queues;
-
-		ret = nvme_ctrl_init_connect_q(ctrl);
-		if (ret)
-			goto out_free_tag_set;
 	}
 
-	ret = nvme_tcp_start_io_queues(ctrl);
+	/*
+	 * Only start IO queues for which we have allocated the tagset
+	 * and limitted it to the available queues. On reconnects, the
+	 * queue number might have changed.
+	 */
+	nr_queues = min(ctrl->tagset->nr_hw_queues + 1, ctrl->queue_count);
+	ret = nvme_tcp_start_io_queues(ctrl, 1, nr_queues);
 	if (ret)
 		goto out_cleanup_connect_q;
 
@@ -1934,6 +1890,15 @@ static int nvme_tcp_configure_io_queues(struct nvme_ctrl *ctrl, bool new)
 		nvme_unfreeze(ctrl);
 	}
 
+	/*
+	 * If the number of queues has increased (reconnect case)
+	 * start all new queues now.
+	 */
+	ret = nvme_tcp_start_io_queues(ctrl, nr_queues,
+				       ctrl->tagset->nr_hw_queues + 1);
+	if (ret)
+		goto out_wait_freeze_timed_out;
+
 	return 0;
 
 out_wait_freeze_timed_out:
@@ -1943,10 +1908,7 @@ out_wait_freeze_timed_out:
 out_cleanup_connect_q:
 	nvme_cancel_tagset(ctrl);
 	if (new)
-		blk_mq_destroy_queue(ctrl->connect_q);
-out_free_tag_set:
-	if (new)
-		blk_mq_free_tag_set(ctrl->tagset);
+		nvme_remove_io_tag_set(ctrl);
 out_free_io_queues:
 	nvme_tcp_free_io_queues(ctrl);
 	return ret;
@@ -1955,11 +1917,8 @@ out_free_io_queues:
 static void nvme_tcp_destroy_admin_queue(struct nvme_ctrl *ctrl, bool remove)
 {
 	nvme_tcp_stop_queue(ctrl, 0);
-	if (remove) {
-		blk_mq_destroy_queue(ctrl->admin_q);
-		blk_mq_destroy_queue(ctrl->fabrics_q);
-		blk_mq_free_tag_set(ctrl->admin_tagset);
-	}
+	if (remove)
+		nvme_remove_admin_tag_set(ctrl);
 	nvme_tcp_free_admin_queue(ctrl);
 }
 
@@ -1972,26 +1931,17 @@ static int nvme_tcp_configure_admin_queue(struct nvme_ctrl *ctrl, bool new)
 		return error;
 
 	if (new) {
-		error = nvme_tcp_alloc_admin_tag_set(ctrl);
+		error = nvme_alloc_admin_tag_set(ctrl,
+				&to_tcp_ctrl(ctrl)->admin_tag_set,
+				&nvme_tcp_admin_mq_ops, BLK_MQ_F_BLOCKING,
+				sizeof(struct nvme_tcp_request));
 		if (error)
 			goto out_free_queue;
-
-		ctrl->fabrics_q = blk_mq_init_queue(ctrl->admin_tagset);
-		if (IS_ERR(ctrl->fabrics_q)) {
-			error = PTR_ERR(ctrl->fabrics_q);
-			goto out_free_tagset;
-		}
-
-		ctrl->admin_q = blk_mq_init_queue(ctrl->admin_tagset);
-		if (IS_ERR(ctrl->admin_q)) {
-			error = PTR_ERR(ctrl->admin_q);
-			goto out_cleanup_fabrics_q;
-		}
 	}
 
 	error = nvme_tcp_start_queue(ctrl, 0);
 	if (error)
-		goto out_cleanup_queue;
+		goto out_cleanup_tagset;
 
 	error = nvme_enable_ctrl(ctrl);
 	if (error)
@@ -2011,15 +1961,9 @@ out_quiesce_queue:
 out_stop_queue:
 	nvme_tcp_stop_queue(ctrl, 0);
 	nvme_cancel_admin_tagset(ctrl);
-out_cleanup_queue:
-	if (new)
-		blk_mq_destroy_queue(ctrl->admin_q);
-out_cleanup_fabrics_q:
+out_cleanup_tagset:
 	if (new)
-		blk_mq_destroy_queue(ctrl->fabrics_q);
-out_free_tagset:
-	if (new)
-		blk_mq_free_tag_set(ctrl->admin_tagset);
+		nvme_remove_admin_tag_set(ctrl);
 out_free_queue:
 	nvme_tcp_free_admin_queue(ctrl);
 	return error;
@@ -2468,9 +2412,9 @@ static blk_status_t nvme_tcp_queue_rq(struct blk_mq_hw_ctx *hctx,
 	return BLK_STS_OK;
 }
 
-static int nvme_tcp_map_queues(struct blk_mq_tag_set *set)
+static void nvme_tcp_map_queues(struct blk_mq_tag_set *set)
 {
-	struct nvme_tcp_ctrl *ctrl = set->driver_data;
+	struct nvme_tcp_ctrl *ctrl = to_tcp_ctrl(set->driver_data);
 	struct nvmf_ctrl_options *opts = ctrl->ctrl.opts;
 
 	if (opts->nr_write_queues && ctrl->io_queues[HCTX_TYPE_READ]) {
@@ -2509,8 +2453,6 @@ static int nvme_tcp_map_queues(struct blk_mq_tag_set *set)
 		ctrl->io_queues[HCTX_TYPE_DEFAULT],
 		ctrl->io_queues[HCTX_TYPE_READ],
 		ctrl->io_queues[HCTX_TYPE_POLL]);
-
-	return 0;
 }
 
 static int nvme_tcp_poll(struct blk_mq_hw_ctx *hctx, struct io_comp_batch *iob)
@@ -2529,6 +2471,25 @@ static int nvme_tcp_poll(struct blk_mq_hw_ctx *hctx, struct io_comp_batch *iob)
 	return queue->nr_cqe;
 }
 
+static int nvme_tcp_get_address(struct nvme_ctrl *ctrl, char *buf, int size)
+{
+	struct nvme_tcp_queue *queue = &to_tcp_ctrl(ctrl)->queues[0];
+	struct sockaddr_storage src_addr;
+	int ret, len;
+
+	len = nvmf_get_address(ctrl, buf, size);
+
+	ret = kernel_getsockname(queue->sock, (struct sockaddr *)&src_addr);
+	if (ret > 0) {
+		if (len > 0)
+			len--; /* strip trailing newline */
+		len += scnprintf(buf + len, size - len, "%ssrc_addr=%pISc\n",
+				(len) ? "," : "", &src_addr);
+	}
+
+	return len;
+}
+
 static const struct blk_mq_ops nvme_tcp_mq_ops = {
 	.queue_rq	= nvme_tcp_queue_rq,
 	.commit_rqs	= nvme_tcp_commit_rqs,
@@ -2560,7 +2521,7 @@ static const struct nvme_ctrl_ops nvme_tcp_ctrl_ops = {
 	.free_ctrl		= nvme_tcp_free_ctrl,
 	.submit_async_event	= nvme_tcp_submit_async_event,
 	.delete_ctrl		= nvme_tcp_delete_ctrl,
-	.get_address		= nvmf_get_address,
+	.get_address		= nvme_tcp_get_address,
 	.stop_ctrl		= nvme_tcp_stop_ctrl,
 };