Merge tag 'for-5.4/block-2019-09-16' of git://git.kernel.dk/linux-block

Pull block updates from Jens Axboe:

 - Two NVMe pull requests:
     - ana log parse fix from Anton
     - nvme quirks support for Apple devices from Ben
     - fix missing bio completion tracing for multipath stack devices
       from Hannes and Mikhail
     - IP TOS settings for nvme rdma and tcp transports from Israel
     - rq_dma_dir cleanups from Israel
     - tracing for Get LBA Status command from Minwoo
     - Some nvme-tcp cleanups from Minwoo, Potnuri and Myself
     - Some consolidation between the fabrics transports for handling
       the CAP register
     - reset race with ns scanning fix for fabrics (move fabrics
       commands to a dedicated request queue with a different lifetime
       from the admin request queue)."
     - controller reset and namespace scan races fixes
     - nvme discovery log change uevent support
     - naming improvements from Keith
     - multiple discovery controllers reject fix from James
     - some regular cleanups from various people

 - Series fixing (and re-fixing) null_blk debug printing and nr_devices
   checks (André)

 - A few pull requests from Song, with fixes from Andy, Guoqing,
   Guilherme, Neil, Nigel, and Yufen.

 - REQ_OP_ZONE_RESET_ALL support (Chaitanya)

 - Bio merge handling unification (Christoph)

 - Pick default elevator correctly for devices with special needs
   (Damien)

 - Block stats fixes (Hou)

 - Timeout and support devices nbd fixes (Mike)

 - Series fixing races around elevator switching and device add/remove
   (Ming)

 - sed-opal cleanups (Revanth)

 - Per device weight support for BFQ (Fam)

 - Support for blk-iocost, a new model that can properly account cost of
   IO workloads. (Tejun)

 - blk-cgroup writeback fixes (Tejun)

 - paride queue init fixes (zhengbin)

 - blk_set_runtime_active() cleanup (Stanley)

 - Block segment mapping optimizations (Bart)

 - lightnvm fixes (Hans/Minwoo/YueHaibing)

 - Various little fixes and cleanups

* tag 'for-5.4/block-2019-09-16' of git://git.kernel.dk/linux-block: (186 commits)
  null_blk: format pr_* logs with pr_fmt
  null_blk: match the type of parameter nr_devices
  null_blk: do not fail the module load with zero devices
  block: also check RQF_STATS in blk_mq_need_time_stamp()
  block: make rq sector size accessible for block stats
  bfq: Fix bfq linkage error
  raid5: use bio_end_sector in r5_next_bio
  raid5: remove STRIPE_OPS_REQ_PENDING
  md: add feature flag MD_FEATURE_RAID0_LAYOUT
  md/raid0: avoid RAID0 data corruption due to layout confusion.
  raid5: don't set STRIPE_HANDLE to stripe which is in batch list
  raid5: don't increment read_errors on EILSEQ return
  nvmet: fix a wrong error status returned in error log page
  nvme: send discovery log page change events to userspace
  nvme: add uevent variables for controller devices
  nvme: enable aen regardless of the presence of I/O queues
  nvme-fabrics: allow discovery subsystems accept a kato
  nvmet: Use PTR_ERR_OR_ZERO() in nvmet_init_discovery()
  nvme: Remove redundant assignment of cq vector
  nvme: Assign subsys instance from first ctrl
  ...

5 files changed, 66 insertions, 32 deletions

diff --git a/drivers/nvme/target/admin-cmd.c b/drivers/nvme/target/admin-cmd.c
index 4dc12ea52f23..831a062d27cb 100644
--- a/drivers/nvme/target/admin-cmd.c
+++ b/drivers/nvme/target/admin-cmd.c
@@ -37,7 +37,6 @@ static void nvmet_execute_get_log_page_noop(struct nvmet_req *req)
 static void nvmet_execute_get_log_page_error(struct nvmet_req *req)
 {
 	struct nvmet_ctrl *ctrl = req->sq->ctrl;
-	u16 status = NVME_SC_SUCCESS;
 	unsigned long flags;
 	off_t offset = 0;
 	u64 slot;
@@ -47,9 +46,8 @@ static void nvmet_execute_get_log_page_error(struct nvmet_req *req)
 	slot = ctrl->err_counter % NVMET_ERROR_LOG_SLOTS;
 
 	for (i = 0; i < NVMET_ERROR_LOG_SLOTS; i++) {
-		status = nvmet_copy_to_sgl(req, offset, &ctrl->slots[slot],
-				sizeof(struct nvme_error_slot));
-		if (status)
+		if (nvmet_copy_to_sgl(req, offset, &ctrl->slots[slot],
+				sizeof(struct nvme_error_slot)))
 			break;
 
 		if (slot == 0)
@@ -59,7 +57,7 @@ static void nvmet_execute_get_log_page_error(struct nvmet_req *req)
 		offset += sizeof(struct nvme_error_slot);
 	}
 	spin_unlock_irqrestore(&ctrl->error_lock, flags);
-	nvmet_req_complete(req, status);
+	nvmet_req_complete(req, 0);
 }
 
 static u16 nvmet_get_smart_log_nsid(struct nvmet_req *req,
@@ -81,9 +79,11 @@ static u16 nvmet_get_smart_log_nsid(struct nvmet_req *req,
 		goto out;
 
 	host_reads = part_stat_read(ns->bdev->bd_part, ios[READ]);
-	data_units_read = part_stat_read(ns->bdev->bd_part, sectors[READ]);
+	data_units_read = DIV_ROUND_UP(part_stat_read(ns->bdev->bd_part,
+		sectors[READ]), 1000);
 	host_writes = part_stat_read(ns->bdev->bd_part, ios[WRITE]);
-	data_units_written = part_stat_read(ns->bdev->bd_part, sectors[WRITE]);
+	data_units_written = DIV_ROUND_UP(part_stat_read(ns->bdev->bd_part,
+		sectors[WRITE]), 1000);
 
 	put_unaligned_le64(host_reads, &slog->host_reads[0]);
 	put_unaligned_le64(data_units_read, &slog->data_units_read[0]);
@@ -111,11 +111,11 @@ static u16 nvmet_get_smart_log_all(struct nvmet_req *req,
 		if (!ns->bdev)
 			continue;
 		host_reads += part_stat_read(ns->bdev->bd_part, ios[READ]);
-		data_units_read +=
-			part_stat_read(ns->bdev->bd_part, sectors[READ]);
+		data_units_read += DIV_ROUND_UP(
+			part_stat_read(ns->bdev->bd_part, sectors[READ]), 1000);
 		host_writes += part_stat_read(ns->bdev->bd_part, ios[WRITE]);
-		data_units_written +=
-			part_stat_read(ns->bdev->bd_part, sectors[WRITE]);
+		data_units_written += DIV_ROUND_UP(
+			part_stat_read(ns->bdev->bd_part, sectors[WRITE]), 1000);
 
 	}
 	rcu_read_unlock();
diff --git a/drivers/nvme/target/discovery.c b/drivers/nvme/target/discovery.c
index 8efca26b4776..3764a8900850 100644
--- a/drivers/nvme/target/discovery.c
+++ b/drivers/nvme/target/discovery.c
@@ -381,9 +381,7 @@ int __init nvmet_init_discovery(void)
 {
 	nvmet_disc_subsys =
 		nvmet_subsys_alloc(NVME_DISC_SUBSYS_NAME, NVME_NQN_DISC);
-	if (IS_ERR(nvmet_disc_subsys))
-		return PTR_ERR(nvmet_disc_subsys);
-	return 0;
+	return PTR_ERR_OR_ZERO(nvmet_disc_subsys);
 }
 
 void nvmet_exit_discovery(void)
diff --git a/drivers/nvme/target/loop.c b/drivers/nvme/target/loop.c
index 0940c5024a34..748a39fca771 100644
--- a/drivers/nvme/target/loop.c
+++ b/drivers/nvme/target/loop.c
@@ -253,6 +253,7 @@ static void nvme_loop_destroy_admin_queue(struct nvme_loop_ctrl *ctrl)
 	clear_bit(NVME_LOOP_Q_LIVE, &ctrl->queues[0].flags);
 	nvmet_sq_destroy(&ctrl->queues[0].nvme_sq);
 	blk_cleanup_queue(ctrl->ctrl.admin_q);
+	blk_cleanup_queue(ctrl->ctrl.fabrics_q);
 	blk_mq_free_tag_set(&ctrl->admin_tag_set);
 }
 
@@ -357,10 +358,16 @@ static int nvme_loop_configure_admin_queue(struct nvme_loop_ctrl *ctrl)
 		goto out_free_sq;
 	ctrl->ctrl.admin_tagset = &ctrl->admin_tag_set;
 
+	ctrl->ctrl.fabrics_q = blk_mq_init_queue(&ctrl->admin_tag_set);
+	if (IS_ERR(ctrl->ctrl.fabrics_q)) {
+		error = PTR_ERR(ctrl->ctrl.fabrics_q);
+		goto out_free_tagset;
+	}
+
 	ctrl->ctrl.admin_q = blk_mq_init_queue(&ctrl->admin_tag_set);
 	if (IS_ERR(ctrl->ctrl.admin_q)) {
 		error = PTR_ERR(ctrl->ctrl.admin_q);
-		goto out_free_tagset;
+		goto out_cleanup_fabrics_q;
 	}
 
 	error = nvmf_connect_admin_queue(&ctrl->ctrl);
@@ -369,23 +376,15 @@ static int nvme_loop_configure_admin_queue(struct nvme_loop_ctrl *ctrl)
 
 	set_bit(NVME_LOOP_Q_LIVE, &ctrl->queues[0].flags);
 
-	error = nvmf_reg_read64(&ctrl->ctrl, NVME_REG_CAP, &ctrl->ctrl.cap);
-	if (error) {
-		dev_err(ctrl->ctrl.device,
-			"prop_get NVME_REG_CAP failed\n");
-		goto out_cleanup_queue;
-	}
-
-	ctrl->ctrl.sqsize =
-		min_t(int, NVME_CAP_MQES(ctrl->ctrl.cap), ctrl->ctrl.sqsize);
-
-	error = nvme_enable_ctrl(&ctrl->ctrl, ctrl->ctrl.cap);
+	error = nvme_enable_ctrl(&ctrl->ctrl);
 	if (error)
 		goto out_cleanup_queue;
 
 	ctrl->ctrl.max_hw_sectors =
 		(NVME_LOOP_MAX_SEGMENTS - 1) << (PAGE_SHIFT - 9);
 
+	blk_mq_unquiesce_queue(ctrl->ctrl.admin_q);
+
 	error = nvme_init_identify(&ctrl->ctrl);
 	if (error)
 		goto out_cleanup_queue;
@@ -394,6 +393,8 @@ static int nvme_loop_configure_admin_queue(struct nvme_loop_ctrl *ctrl)
 
 out_cleanup_queue:
 	blk_cleanup_queue(ctrl->ctrl.admin_q);
+out_cleanup_fabrics_q:
+	blk_cleanup_queue(ctrl->ctrl.fabrics_q);
 out_free_tagset:
 	blk_mq_free_tag_set(&ctrl->admin_tag_set);
 out_free_sq:
@@ -407,16 +408,17 @@ static void nvme_loop_shutdown_ctrl(struct nvme_loop_ctrl *ctrl)
 		nvme_stop_queues(&ctrl->ctrl);
 		blk_mq_tagset_busy_iter(&ctrl->tag_set,
 					nvme_cancel_request, &ctrl->ctrl);
+		blk_mq_tagset_wait_completed_request(&ctrl->tag_set);
 		nvme_loop_destroy_io_queues(ctrl);
 	}
 
+	blk_mq_quiesce_queue(ctrl->ctrl.admin_q);
 	if (ctrl->ctrl.state == NVME_CTRL_LIVE)
 		nvme_shutdown_ctrl(&ctrl->ctrl);
 
-	blk_mq_quiesce_queue(ctrl->ctrl.admin_q);
 	blk_mq_tagset_busy_iter(&ctrl->admin_tag_set,
 				nvme_cancel_request, &ctrl->ctrl);
-	blk_mq_unquiesce_queue(ctrl->ctrl.admin_q);
+	blk_mq_tagset_wait_completed_request(&ctrl->admin_tag_set);
 	nvme_loop_destroy_admin_queue(ctrl);
 }
 
diff --git a/drivers/nvme/target/tcp.c b/drivers/nvme/target/tcp.c
index 69b83fa0c76c..bf4f03474e89 100644
--- a/drivers/nvme/target/tcp.c
+++ b/drivers/nvme/target/tcp.c
@@ -348,7 +348,8 @@ static int nvmet_tcp_map_data(struct nvmet_tcp_cmd *cmd)
 
 	return 0;
 err:
-	sgl_free(cmd->req.sg);
+	if (cmd->req.sg_cnt)
+		sgl_free(cmd->req.sg);
 	return NVME_SC_INTERNAL;
 }
 
@@ -553,7 +554,8 @@ static int nvmet_try_send_data(struct nvmet_tcp_cmd *cmd)
 
 	if (queue->nvme_sq.sqhd_disabled) {
 		kfree(cmd->iov);
-		sgl_free(cmd->req.sg);
+		if (cmd->req.sg_cnt)
+			sgl_free(cmd->req.sg);
 	}
 
 	return 1;
@@ -584,7 +586,8 @@ static int nvmet_try_send_response(struct nvmet_tcp_cmd *cmd,
 		return -EAGAIN;
 
 	kfree(cmd->iov);
-	sgl_free(cmd->req.sg);
+	if (cmd->req.sg_cnt)
+		sgl_free(cmd->req.sg);
 	cmd->queue->snd_cmd = NULL;
 	nvmet_tcp_put_cmd(cmd);
 	return 1;
@@ -1306,7 +1309,9 @@ static void nvmet_tcp_finish_cmd(struct nvmet_tcp_cmd *cmd)
 {
 	nvmet_req_uninit(&cmd->req);
 	nvmet_tcp_unmap_pdu_iovec(cmd);
-	sgl_free(cmd->req.sg);
+	kfree(cmd->iov);
+	if (cmd->req.sg_cnt)
+		sgl_free(cmd->req.sg);
 }
 
 static void nvmet_tcp_uninit_data_in_cmds(struct nvmet_tcp_queue *queue)
@@ -1410,6 +1415,7 @@ done:
 static int nvmet_tcp_set_queue_sock(struct nvmet_tcp_queue *queue)
 {
 	struct socket *sock = queue->sock;
+	struct inet_sock *inet = inet_sk(sock->sk);
 	struct linger sol = { .l_onoff = 1, .l_linger = 0 };
 	int ret;
 
@@ -1433,6 +1439,16 @@ static int nvmet_tcp_set_queue_sock(struct nvmet_tcp_queue *queue)
 	if (ret)
 		return ret;
 
+	/* Set socket type of service */
+	if (inet->rcv_tos > 0) {
+		int tos = inet->rcv_tos;
+
+		ret = kernel_setsockopt(sock, SOL_IP, IP_TOS,
+				(char *)&tos, sizeof(tos));
+		if (ret)
+			return ret;
+	}
+
 	write_lock_bh(&sock->sk->sk_callback_lock);
 	sock->sk->sk_user_data = queue;
 	queue->data_ready = sock->sk->sk_data_ready;
diff --git a/drivers/nvme/target/trace.c b/drivers/nvme/target/trace.c
index 6af11d493271..1373a3c67962 100644
--- a/drivers/nvme/target/trace.c
+++ b/drivers/nvme/target/trace.c
@@ -33,6 +33,22 @@ static const char *nvmet_trace_admin_get_features(struct trace_seq *p,
 	return ret;
 }
 
+static const char *nvmet_trace_get_lba_status(struct trace_seq *p,
+					     u8 *cdw10)
+{
+	const char *ret = trace_seq_buffer_ptr(p);
+	u64 slba = get_unaligned_le64(cdw10);
+	u32 mndw = get_unaligned_le32(cdw10 + 8);
+	u16 rl = get_unaligned_le16(cdw10 + 12);
+	u8 atype = cdw10[15];
+
+	trace_seq_printf(p, "slba=0x%llx, mndw=0x%x, rl=0x%x, atype=%u",
+			slba, mndw, rl, atype);
+	trace_seq_putc(p, 0);
+
+	return ret;
+}
+
 static const char *nvmet_trace_read_write(struct trace_seq *p, u8 *cdw10)
 {
 	const char *ret = trace_seq_buffer_ptr(p);
@@ -80,6 +96,8 @@ const char *nvmet_trace_parse_admin_cmd(struct trace_seq *p,
 		return nvmet_trace_admin_identify(p, cdw10);
 	case nvme_admin_get_features:
 		return nvmet_trace_admin_get_features(p, cdw10);
+	case nvme_admin_get_lba_status:
+		return nvmet_trace_get_lba_status(p, cdw10);
 	default:
 		return nvmet_trace_common(p, cdw10);
 	}