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, 126 insertions, 14 deletions

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 45ef8e8ddc84..64f599a64a7f 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -1111,8 +1111,8 @@ static u32 nvme_passthru_start(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
 	return effects;
 }
 
-static void nvme_passthru_end(struct nvme_ctrl *ctrl, u32 effects,
-			      struct nvme_command *cmd, int status)
+void nvme_passthru_end(struct nvme_ctrl *ctrl, u32 effects,
+		       struct nvme_command *cmd, int status)
 {
 	if (effects & NVME_CMD_EFFECTS_CSE_MASK) {
 		nvme_unfreeze(ctrl);
@@ -1148,21 +1148,16 @@ static void nvme_passthru_end(struct nvme_ctrl *ctrl, u32 effects,
 		break;
 	}
 }
+EXPORT_SYMBOL_NS_GPL(nvme_passthru_end, NVME_TARGET_PASSTHRU);
 
-int nvme_execute_passthru_rq(struct request *rq)
+int nvme_execute_passthru_rq(struct request *rq, u32 *effects)
 {
 	struct nvme_command *cmd = nvme_req(rq)->cmd;
 	struct nvme_ctrl *ctrl = nvme_req(rq)->ctrl;
 	struct nvme_ns *ns = rq->q->queuedata;
-	u32 effects;
-	int  ret;
 
-	effects = nvme_passthru_start(ctrl, ns, cmd->common.opcode);
-	ret = nvme_execute_rq(rq, false);
-	if (effects) /* nothing to be done for zero cmd effects */
-		nvme_passthru_end(ctrl, effects, cmd, ret);
-
-	return ret;
+	*effects = nvme_passthru_start(ctrl, ns, cmd->common.opcode);
+	return nvme_execute_rq(rq, false);
 }
 EXPORT_SYMBOL_NS_GPL(nvme_execute_passthru_rq, NVME_TARGET_PASSTHRU);
 
@@ -2696,7 +2691,7 @@ static void nvme_init_subnqn(struct nvme_subsystem *subsys, struct nvme_ctrl *ct
 	if(!(ctrl->quirks & NVME_QUIRK_IGNORE_DEV_SUBNQN)) {
 		nqnlen = strnlen(id->subnqn, NVMF_NQN_SIZE);
 		if (nqnlen > 0 && nqnlen < NVMF_NQN_SIZE) {
-			strlcpy(subsys->subnqn, id->subnqn, NVMF_NQN_SIZE);
+			strscpy(subsys->subnqn, id->subnqn, NVMF_NQN_SIZE);
 			return;
 		}
 
@@ -2704,7 +2699,11 @@ static void nvme_init_subnqn(struct nvme_subsystem *subsys, struct nvme_ctrl *ct
 			dev_warn(ctrl->device, "missing or invalid SUBNQN field.\n");
 	}
 
-	/* Generate a "fake" NQN per Figure 254 in NVMe 1.3 + ECN 001 */
+	/*
+	 * Generate a "fake" NQN similar to the one in Section 4.5 of the NVMe
+	 * Base Specification 2.0.  It is slightly different from the format
+	 * specified there due to historic reasons, and we can't change it now.
+	 */
 	off = snprintf(subsys->subnqn, NVMF_NQN_SIZE,
 			"nqn.2014.08.org.nvmexpress:%04x%04x",
 			le16_to_cpu(id->vid), le16_to_cpu(id->ssvid));
@@ -2894,7 +2893,6 @@ static int nvme_init_subsystem(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id)
 	nvme_init_subnqn(subsys, ctrl, id);
 	memcpy(subsys->serial, id->sn, sizeof(subsys->serial));
 	memcpy(subsys->model, id->mn, sizeof(subsys->model));
-	memcpy(subsys->firmware_rev, id->fr, sizeof(subsys->firmware_rev));
 	subsys->vendor_id = le16_to_cpu(id->vid);
 	subsys->cmic = id->cmic;
 
@@ -3113,6 +3111,8 @@ static int nvme_init_identify(struct nvme_ctrl *ctrl)
 				ctrl->quirks |= core_quirks[i].quirks;
 		}
 	}
+	memcpy(ctrl->subsys->firmware_rev, id->fr,
+	       sizeof(ctrl->subsys->firmware_rev));
 
 	if (force_apst && (ctrl->quirks & NVME_QUIRK_NO_DEEPEST_PS)) {
 		dev_warn(ctrl->device, "forcibly allowing all power states due to nvme_core.force_apst -- use at your own risk\n");
@@ -4805,6 +4805,108 @@ void nvme_complete_async_event(struct nvme_ctrl *ctrl, __le16 status,
 }
 EXPORT_SYMBOL_GPL(nvme_complete_async_event);
 
+int nvme_alloc_admin_tag_set(struct nvme_ctrl *ctrl, struct blk_mq_tag_set *set,
+		const struct blk_mq_ops *ops, unsigned int flags,
+		unsigned int cmd_size)
+{
+	int ret;
+
+	memset(set, 0, sizeof(*set));
+	set->ops = ops;
+	set->queue_depth = NVME_AQ_MQ_TAG_DEPTH;
+	if (ctrl->ops->flags & NVME_F_FABRICS)
+		set->reserved_tags = NVMF_RESERVED_TAGS;
+	set->numa_node = ctrl->numa_node;
+	set->flags = flags;
+	set->cmd_size = cmd_size;
+	set->driver_data = ctrl;
+	set->nr_hw_queues = 1;
+	set->timeout = NVME_ADMIN_TIMEOUT;
+	ret = blk_mq_alloc_tag_set(set);
+	if (ret)
+		return ret;
+
+	ctrl->admin_q = blk_mq_init_queue(set);
+	if (IS_ERR(ctrl->admin_q)) {
+		ret = PTR_ERR(ctrl->admin_q);
+		goto out_free_tagset;
+	}
+
+	if (ctrl->ops->flags & NVME_F_FABRICS) {
+		ctrl->fabrics_q = blk_mq_init_queue(set);
+		if (IS_ERR(ctrl->fabrics_q)) {
+			ret = PTR_ERR(ctrl->fabrics_q);
+			goto out_cleanup_admin_q;
+		}
+	}
+
+	ctrl->admin_tagset = set;
+	return 0;
+
+out_cleanup_admin_q:
+	blk_mq_destroy_queue(ctrl->fabrics_q);
+out_free_tagset:
+	blk_mq_free_tag_set(ctrl->admin_tagset);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(nvme_alloc_admin_tag_set);
+
+void nvme_remove_admin_tag_set(struct nvme_ctrl *ctrl)
+{
+	blk_mq_destroy_queue(ctrl->admin_q);
+	if (ctrl->ops->flags & NVME_F_FABRICS)
+		blk_mq_destroy_queue(ctrl->fabrics_q);
+	blk_mq_free_tag_set(ctrl->admin_tagset);
+}
+EXPORT_SYMBOL_GPL(nvme_remove_admin_tag_set);
+
+int nvme_alloc_io_tag_set(struct nvme_ctrl *ctrl, struct blk_mq_tag_set *set,
+		const struct blk_mq_ops *ops, unsigned int flags,
+		unsigned int cmd_size)
+{
+	int ret;
+
+	memset(set, 0, sizeof(*set));
+	set->ops = ops;
+	set->queue_depth = ctrl->sqsize + 1;
+	set->reserved_tags = NVMF_RESERVED_TAGS;
+	set->numa_node = ctrl->numa_node;
+	set->flags = flags;
+	set->cmd_size = cmd_size,
+	set->driver_data = ctrl;
+	set->nr_hw_queues = ctrl->queue_count - 1;
+	set->timeout = NVME_IO_TIMEOUT;
+	if (ops->map_queues)
+		set->nr_maps = ctrl->opts->nr_poll_queues ? HCTX_MAX_TYPES : 2;
+	ret = blk_mq_alloc_tag_set(set);
+	if (ret)
+		return ret;
+
+	if (ctrl->ops->flags & NVME_F_FABRICS) {
+		ctrl->connect_q = blk_mq_init_queue(set);
+        	if (IS_ERR(ctrl->connect_q)) {
+			ret = PTR_ERR(ctrl->connect_q);
+			goto out_free_tag_set;
+		}
+	}
+
+	ctrl->tagset = set;
+	return 0;
+
+out_free_tag_set:
+	blk_mq_free_tag_set(set);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(nvme_alloc_io_tag_set);
+
+void nvme_remove_io_tag_set(struct nvme_ctrl *ctrl)
+{
+	if (ctrl->ops->flags & NVME_F_FABRICS)
+		blk_mq_destroy_queue(ctrl->connect_q);
+	blk_mq_free_tag_set(ctrl->tagset);
+}
+EXPORT_SYMBOL_GPL(nvme_remove_io_tag_set);
+
 void nvme_stop_ctrl(struct nvme_ctrl *ctrl)
 {
 	nvme_mpath_stop(ctrl);
@@ -4824,6 +4926,16 @@ void nvme_start_ctrl(struct nvme_ctrl *ctrl)
 
 	nvme_enable_aen(ctrl);
 
+	/*
+	 * persistent discovery controllers need to send indication to userspace
+	 * to re-read the discovery log page to learn about possible changes
+	 * that were missed. We identify persistent discovery controllers by
+	 * checking that they started once before, hence are reconnecting back.
+	 */
+	if (test_and_set_bit(NVME_CTRL_STARTED_ONCE, &ctrl->flags) &&
+	    nvme_discovery_ctrl(ctrl))
+		nvme_change_uevent(ctrl, "NVME_EVENT=rediscover");
+
 	if (ctrl->queue_count > 1) {
 		nvme_queue_scan(ctrl);
 		nvme_start_queues(ctrl);