Merge tag 'for-linus-20180413' of git://git.kernel.dk/linux-block

Pull block fixes from Jens Axboe:
 "Followup fixes for this merge window. This contains:

   - Series from Ming, fixing corner cases in our CPU <-> queue mapping.

     This triggered repeated warnings on especially s390, but I also hit
     it in cpu hot plug/unplug testing while doing IO on NVMe on x86-64.

   - Another fix from Ming, ensuring that we always order budget and
     driver tag identically, avoiding a deadlock on QD=1 devices.

   - Loop locking regression fix from this merge window, from Omar.

   - Another loop locking fix, this time missing an unlock, from Tetsuo
     Handa.

   - Fix for racing IO submission with device removal from Bart.

   - sr reference fix from me, fixing a case where disk change or
     getevents can race with device removal.

   - Set of nvme fixes by way of Keith, from various contributors"

* tag 'for-linus-20180413' of git://git.kernel.dk/linux-block: (28 commits)
  nvme: expand nvmf_check_if_ready checks
  nvme: Use admin command effects for admin commands
  nvmet: fix space padding in serial number
  nvme: check return value of init_srcu_struct function
  nvmet: Fix nvmet_execute_write_zeroes sector count
  nvme-pci: Separate IO and admin queue IRQ vectors
  nvme-pci: Remove unused queue parameter
  nvme-pci: Skip queue deletion if there are no queues
  nvme: target: fix buffer overflow
  nvme: don't send keep-alives to the discovery controller
  nvme: unexport nvme_start_keep_alive
  nvme-loop: fix kernel oops in case of unhandled command
  nvme: enforce 64bit offset for nvme_get_log_ext fn
  sr: get/drop reference to device in revalidate and check_events
  blk-mq: Revert "blk-mq: reimplement blk_mq_hw_queue_mapped"
  blk-mq: Avoid that submitting a bio concurrently with device removal triggers a crash
  backing: silence compiler warning using __printf
  blk-mq: remove code for dealing with remapping queue
  blk-mq: reimplement blk_mq_hw_queue_mapped
  blk-mq: don't check queue mapped in __blk_mq_delay_run_hw_queue()
  ...

block/blk-core.c

@@ -2385,8 +2385,20 @@ blk_qc_t generic_make_request(struct bio *bio)
 	 * yet.
 	 */
 	struct bio_list bio_list_on_stack[2];
+	blk_mq_req_flags_t flags = 0;
+	struct request_queue *q = bio->bi_disk->queue;
 	blk_qc_t ret = BLK_QC_T_NONE;
 
+	if (bio->bi_opf & REQ_NOWAIT)
+		flags = BLK_MQ_REQ_NOWAIT;
+	if (blk_queue_enter(q, flags) < 0) {
+		if (!blk_queue_dying(q) && (bio->bi_opf & REQ_NOWAIT))
+			bio_wouldblock_error(bio);
+		else
+			bio_io_error(bio);
+		return ret;
+	}
+
 	if (!generic_make_request_checks(bio))
 		goto out;
 
@@ -2423,11 +2435,22 @@ blk_qc_t generic_make_request(struct bio *bio)
 	bio_list_init(&bio_list_on_stack[0]);
 	current->bio_list = bio_list_on_stack;
 	do {
-		struct request_queue *q = bio->bi_disk->queue;
-		blk_mq_req_flags_t flags = bio->bi_opf & REQ_NOWAIT ?
-			BLK_MQ_REQ_NOWAIT : 0;
+		bool enter_succeeded = true;
 
-		if (likely(blk_queue_enter(q, flags) == 0)) {
+		if (unlikely(q != bio->bi_disk->queue)) {
+			if (q)
+				blk_queue_exit(q);
+			q = bio->bi_disk->queue;
+			flags = 0;
+			if (bio->bi_opf & REQ_NOWAIT)
+				flags = BLK_MQ_REQ_NOWAIT;
+			if (blk_queue_enter(q, flags) < 0) {
+				enter_succeeded = false;
+				q = NULL;
+			}
+		}
+
+		if (enter_succeeded) {
 			struct bio_list lower, same;
 
 			/* Create a fresh bio_list for all subordinate requests */
@@ -2435,8 +2458,6 @@ blk_qc_t generic_make_request(struct bio *bio)
 			bio_list_init(&bio_list_on_stack[0]);
 			ret = q->make_request_fn(q, bio);
 
-			blk_queue_exit(q);
-
 			/* sort new bios into those for a lower level
 			 * and those for the same level
 			 */
@@ -2463,6 +2484,8 @@ blk_qc_t generic_make_request(struct bio *bio)
 	current->bio_list = NULL; /* deactivate */
 
 out:
+	if (q)
+		blk_queue_exit(q);
 	return ret;
 }
 EXPORT_SYMBOL(generic_make_request);

block/blk-mq-cpumap.c

@@ -16,11 +16,6 @@
 
 static int cpu_to_queue_index(unsigned int nr_queues, const int cpu)
 {
-	/*
-	 * Non present CPU will be mapped to queue index 0.
-	 */
-	if (!cpu_present(cpu))
-		return 0;
 	return cpu % nr_queues;
 }
 

block/blk-mq-debugfs.c

@@ -235,7 +235,6 @@ static const char *const hctx_state_name[] = {
 	HCTX_STATE_NAME(STOPPED),
 	HCTX_STATE_NAME(TAG_ACTIVE),
 	HCTX_STATE_NAME(SCHED_RESTART),
-	HCTX_STATE_NAME(START_ON_RUN),
 };
 #undef HCTX_STATE_NAME
 

block/blk-mq.c

@@ -1180,7 +1180,12 @@ bool blk_mq_dispatch_rq_list(struct request_queue *q, struct list_head *list,
 		struct blk_mq_queue_data bd;
 
 		rq = list_first_entry(list, struct request, queuelist);
-		if (!blk_mq_get_driver_tag(rq, &hctx, false)) {
+
+		hctx = blk_mq_map_queue(rq->q, rq->mq_ctx->cpu);
+		if (!got_budget && !blk_mq_get_dispatch_budget(hctx))
+			break;
+
+		if (!blk_mq_get_driver_tag(rq, NULL, false)) {
 			/*
 			 * The initial allocation attempt failed, so we need to
 			 * rerun the hardware queue when a tag is freed. The
@@ -1189,7 +1194,6 @@ bool blk_mq_dispatch_rq_list(struct request_queue *q, struct list_head *list,
 			 * we'll re-run it below.
 			 */
 			if (!blk_mq_mark_tag_wait(&hctx, rq)) {
-				if (got_budget)
 				blk_mq_put_dispatch_budget(hctx);
 				/*
 				 * For non-shared tags, the RESTART check
@@ -1201,11 +1205,6 @@ bool blk_mq_dispatch_rq_list(struct request_queue *q, struct list_head *list,
 			}
 		}
 
-		if (!got_budget && !blk_mq_get_dispatch_budget(hctx)) {
-			blk_mq_put_driver_tag(rq);
-			break;
-		}
-
 		list_del_init(&rq->queuelist);
 
 		bd.rq = rq;
@@ -1336,6 +1335,15 @@ static void __blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx)
 	hctx_unlock(hctx, srcu_idx);
 }
 
+static inline int blk_mq_first_mapped_cpu(struct blk_mq_hw_ctx *hctx)
+{
+	int cpu = cpumask_first_and(hctx->cpumask, cpu_online_mask);
+
+	if (cpu >= nr_cpu_ids)
+		cpu = cpumask_first(hctx->cpumask);
+	return cpu;
+}
+
 /*
  * It'd be great if the workqueue API had a way to pass
  * in a mask and had some smarts for more clever placement.
@@ -1345,26 +1353,17 @@ static void __blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx)
 static int blk_mq_hctx_next_cpu(struct blk_mq_hw_ctx *hctx)
 {
 	bool tried = false;
+	int next_cpu = hctx->next_cpu;
 
 	if (hctx->queue->nr_hw_queues == 1)
 		return WORK_CPU_UNBOUND;
 
 	if (--hctx->next_cpu_batch <= 0) {
-		int next_cpu;
 select_cpu:
-		next_cpu = cpumask_next_and(hctx->next_cpu, hctx->cpumask,
+		next_cpu = cpumask_next_and(next_cpu, hctx->cpumask,
 				cpu_online_mask);
 		if (next_cpu >= nr_cpu_ids)
-			next_cpu = cpumask_first_and(hctx->cpumask,cpu_online_mask);
-
-		/*
-		 * No online CPU is found, so have to make sure hctx->next_cpu
-		 * is set correctly for not breaking workqueue.
-		 */
-		if (next_cpu >= nr_cpu_ids)
-			hctx->next_cpu = cpumask_first(hctx->cpumask);
-		else
-			hctx->next_cpu = next_cpu;
+			next_cpu = blk_mq_first_mapped_cpu(hctx);
 		hctx->next_cpu_batch = BLK_MQ_CPU_WORK_BATCH;
 	}
 
@@ -1372,7 +1371,7 @@ static int blk_mq_hctx_next_cpu(struct blk_mq_hw_ctx *hctx)
 	 * Do unbound schedule if we can't find a online CPU for this hctx,
 	 * and it should only happen in the path of handling CPU DEAD.
 	 */
-	if (!cpu_online(hctx->next_cpu)) {
+	if (!cpu_online(next_cpu)) {
 		if (!tried) {
 			tried = true;
 			goto select_cpu;
@@ -1382,18 +1381,18 @@ static int blk_mq_hctx_next_cpu(struct blk_mq_hw_ctx *hctx)
 		 * Make sure to re-select CPU next time once after CPUs
 		 * in hctx->cpumask become online again.
 		 */
+		hctx->next_cpu = next_cpu;
 		hctx->next_cpu_batch = 1;
 		return WORK_CPU_UNBOUND;
 	}
-	return hctx->next_cpu;
+
+	hctx->next_cpu = next_cpu;
+	return next_cpu;
 }
 
 static void __blk_mq_delay_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async,
 					unsigned long msecs)
 {
-	if (WARN_ON_ONCE(!blk_mq_hw_queue_mapped(hctx)))
-		return;
-
 	if (unlikely(blk_mq_hctx_stopped(hctx)))
 		return;
 
@@ -1560,40 +1559,14 @@ static void blk_mq_run_work_fn(struct work_struct *work)
 	hctx = container_of(work, struct blk_mq_hw_ctx, run_work.work);
 
 	/*
-	 * If we are stopped, don't run the queue. The exception is if
-	 * BLK_MQ_S_START_ON_RUN is set. For that case, we auto-clear
-	 * the STOPPED bit and run it.
+	 * If we are stopped, don't run the queue.
 	 */
-	if (test_bit(BLK_MQ_S_STOPPED, &hctx->state)) {
-		if (!test_bit(BLK_MQ_S_START_ON_RUN, &hctx->state))
-			return;
-
-		clear_bit(BLK_MQ_S_START_ON_RUN, &hctx->state);
+	if (test_bit(BLK_MQ_S_STOPPED, &hctx->state))
 		clear_bit(BLK_MQ_S_STOPPED, &hctx->state);
-	}
 
 	__blk_mq_run_hw_queue(hctx);
 }
 
-
-void blk_mq_delay_queue(struct blk_mq_hw_ctx *hctx, unsigned long msecs)
-{
-	if (WARN_ON_ONCE(!blk_mq_hw_queue_mapped(hctx)))
-		return;
-
-	/*
-	 * Stop the hw queue, then modify currently delayed work.
-	 * This should prevent us from running the queue prematurely.
-	 * Mark the queue as auto-clearing STOPPED when it runs.
-	 */
-	blk_mq_stop_hw_queue(hctx);
-	set_bit(BLK_MQ_S_START_ON_RUN, &hctx->state);
-	kblockd_mod_delayed_work_on(blk_mq_hctx_next_cpu(hctx),
-					&hctx->run_work,
-					msecs_to_jiffies(msecs));
-}
-EXPORT_SYMBOL(blk_mq_delay_queue);
-
 static inline void __blk_mq_insert_req_list(struct blk_mq_hw_ctx *hctx,
 					    struct request *rq,
 					    bool at_head)
@@ -1804,11 +1777,11 @@ static blk_status_t __blk_mq_try_issue_directly(struct blk_mq_hw_ctx *hctx,
 	if (q->elevator && !bypass_insert)
 		goto insert;
 
-	if (!blk_mq_get_driver_tag(rq, NULL, false))
+	if (!blk_mq_get_dispatch_budget(hctx))
 		goto insert;
 
-	if (!blk_mq_get_dispatch_budget(hctx)) {
-		blk_mq_put_driver_tag(rq);
+	if (!blk_mq_get_driver_tag(rq, NULL, false)) {
+		blk_mq_put_dispatch_budget(hctx);
 		goto insert;
 	}
 
@@ -2356,7 +2329,7 @@ static void blk_mq_free_map_and_requests(struct blk_mq_tag_set *set,
 
 static void blk_mq_map_swqueue(struct request_queue *q)
 {
-	unsigned int i, hctx_idx;
+	unsigned int i;
 	struct blk_mq_hw_ctx *hctx;
 	struct blk_mq_ctx *ctx;
 	struct blk_mq_tag_set *set = q->tag_set;
@@ -2373,23 +2346,8 @@ static void blk_mq_map_swqueue(struct request_queue *q)
 
 	/*
 	 * Map software to hardware queues.
-	 *
-	 * If the cpu isn't present, the cpu is mapped to first hctx.
 	 */
 	for_each_possible_cpu(i) {
-		hctx_idx = q->mq_map[i];
-		/* unmapped hw queue can be remapped after CPU topo changed */
-		if (!set->tags[hctx_idx] &&
-		    !__blk_mq_alloc_rq_map(set, hctx_idx)) {
-			/*
-			 * If tags initialization fail for some hctx,
-			 * that hctx won't be brought online.  In this
-			 * case, remap the current ctx to hctx[0] which
-			 * is guaranteed to always have tags allocated
-			 */
-			q->mq_map[i] = 0;
-		}
-
 		ctx = per_cpu_ptr(q->queue_ctx, i);
 		hctx = blk_mq_map_queue(q, i);
 
@@ -2401,21 +2359,8 @@ static void blk_mq_map_swqueue(struct request_queue *q)
 	mutex_unlock(&q->sysfs_lock);
 
 	queue_for_each_hw_ctx(q, hctx, i) {
-		/*
-		 * If no software queues are mapped to this hardware queue,
-		 * disable it and free the request entries.
-		 */
-		if (!hctx->nr_ctx) {
-			/* Never unmap queue 0.  We need it as a
-			 * fallback in case of a new remap fails
-			 * allocation
-			 */
-			if (i && set->tags[i])
-				blk_mq_free_map_and_requests(set, i);
-
-			hctx->tags = NULL;
-			continue;
-		}
+		/* every hctx should get mapped by at least one CPU */
+		WARN_ON(!hctx->nr_ctx);
 
 		hctx->tags = set->tags[i];
 		WARN_ON(!hctx->tags);
@@ -2430,8 +2375,7 @@ static void blk_mq_map_swqueue(struct request_queue *q)
 		/*
 		 * Initialize batch roundrobin counts
 		 */
-		hctx->next_cpu = cpumask_first_and(hctx->cpumask,
-				cpu_online_mask);
+		hctx->next_cpu = blk_mq_first_mapped_cpu(hctx);
 		hctx->next_cpu_batch = BLK_MQ_CPU_WORK_BATCH;
 	}
 }

drivers/block/loop.c

@@ -1103,11 +1103,15 @@ loop_set_status(struct loop_device *lo, const struct loop_info64 *info)
 	if (info->lo_encrypt_type) {
 		unsigned int type = info->lo_encrypt_type;
 
-		if (type >= MAX_LO_CRYPT)
-			return -EINVAL;
+		if (type >= MAX_LO_CRYPT) {
+			err = -EINVAL;
+			goto exit;
+		}
 		xfer = xfer_funcs[type];
-		if (xfer == NULL)
-			return -EINVAL;
+		if (xfer == NULL) {
+			err = -EINVAL;
+			goto exit;
+		}
 	} else
 		xfer = NULL;
 
@@ -1283,11 +1287,12 @@ static int
 loop_get_status_old(struct loop_device *lo, struct loop_info __user *arg) {
 	struct loop_info info;
 	struct loop_info64 info64;
-	int err = 0;
+	int err;
 
-	if (!arg)
-		err = -EINVAL;
-	if (!err)
+	if (!arg) {
+		mutex_unlock(&lo->lo_ctl_mutex);
+		return -EINVAL;
+	}
 	err = loop_get_status(lo, &info64);
 	if (!err)
 		err = loop_info64_to_old(&info64, &info);
@@ -1300,11 +1305,12 @@ loop_get_status_old(struct loop_device *lo, struct loop_info __user *arg) {
 static int
 loop_get_status64(struct loop_device *lo, struct loop_info64 __user *arg) {
 	struct loop_info64 info64;
-	int err = 0;
+	int err;
 
-	if (!arg)
-		err = -EINVAL;
-	if (!err)
+	if (!arg) {
+		mutex_unlock(&lo->lo_ctl_mutex);
+		return -EINVAL;
+	}
 	err = loop_get_status(lo, &info64);
 	if (!err && copy_to_user(arg, &info64, sizeof(info64)))
 		err = -EFAULT;
@@ -1529,11 +1535,12 @@ loop_get_status_compat(struct loop_device *lo,
 		       struct compat_loop_info __user *arg)
 {
 	struct loop_info64 info64;
-	int err = 0;
+	int err;
 
-	if (!arg)
-		err = -EINVAL;
-	if (!err)
+	if (!arg) {
+		mutex_unlock(&lo->lo_ctl_mutex);
+		return -EINVAL;
+	}
 	err = loop_get_status(lo, &info64);
 	if (!err)
 		err = loop_info64_to_compat(&info64, arg);

drivers/nvme/host/core.c

@@ -376,6 +376,15 @@ static void nvme_put_ns(struct nvme_ns *ns)
 	kref_put(&ns->kref, nvme_free_ns);
 }
 
+static inline void nvme_clear_nvme_request(struct request *req)
+{
+	if (!(req->rq_flags & RQF_DONTPREP)) {
+		nvme_req(req)->retries = 0;
+		nvme_req(req)->flags = 0;
+		req->rq_flags |= RQF_DONTPREP;
+	}
+}
+
 struct request *nvme_alloc_request(struct request_queue *q,
 		struct nvme_command *cmd, blk_mq_req_flags_t flags, int qid)
 {
@@ -392,6 +401,7 @@ struct request *nvme_alloc_request(struct request_queue *q,
 		return req;
 
 	req->cmd_flags |= REQ_FAILFAST_DRIVER;
+	nvme_clear_nvme_request(req);
 	nvme_req(req)->cmd = cmd;
 
 	return req;
@@ -608,11 +618,7 @@ blk_status_t nvme_setup_cmd(struct nvme_ns *ns, struct request *req,
 {
 	blk_status_t ret = BLK_STS_OK;
 
-	if (!(req->rq_flags & RQF_DONTPREP)) {
-		nvme_req(req)->retries = 0;
-		nvme_req(req)->flags = 0;
-		req->rq_flags |= RQF_DONTPREP;
-	}
+	nvme_clear_nvme_request(req);
 
 	switch (req_op(req)) {
 	case REQ_OP_DRV_IN:
@@ -742,6 +748,7 @@ static int nvme_submit_user_cmd(struct request_queue *q,
 		return PTR_ERR(req);
 
 	req->timeout = timeout ? timeout : ADMIN_TIMEOUT;
+	nvme_req(req)->flags |= NVME_REQ_USERCMD;
 
 	if (ubuffer && bufflen) {
 		ret = blk_rq_map_user(q, req, NULL, ubuffer, bufflen,
@@ -826,7 +833,7 @@ static void nvme_keep_alive_work(struct work_struct *work)
 	}
 }
 
-void nvme_start_keep_alive(struct nvme_ctrl *ctrl)
+static void nvme_start_keep_alive(struct nvme_ctrl *ctrl)
 {
 	if (unlikely(ctrl->kato == 0))
 		return;
@@ -836,7 +843,6 @@ void nvme_start_keep_alive(struct nvme_ctrl *ctrl)
 	ctrl->ka_cmd.common.opcode = nvme_admin_keep_alive;
 	schedule_delayed_work(&ctrl->ka_work, ctrl->kato * HZ);
 }
-EXPORT_SYMBOL_GPL(nvme_start_keep_alive);
 
 void nvme_stop_keep_alive(struct nvme_ctrl *ctrl)
 {
@@ -1103,7 +1109,7 @@ static u32 nvme_passthru_start(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
 	}
 
 	if (ctrl->effects)
-		effects = le32_to_cpu(ctrl->effects->iocs[opcode]);
+		effects = le32_to_cpu(ctrl->effects->acs[opcode]);
 	else
 		effects = nvme_known_admin_effects(opcode);
 
@@ -2220,7 +2226,7 @@ static int nvme_init_subsystem(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id)
 
 int nvme_get_log_ext(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
 		     u8 log_page, void *log,
-		     size_t size, size_t offset)
+		     size_t size, u64 offset)
 {
 	struct nvme_command c = { };
 	unsigned long dwlen = size / 4 - 1;
@@ -2235,8 +2241,8 @@ int nvme_get_log_ext(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
 	c.get_log_page.lid = log_page;
 	c.get_log_page.numdl = cpu_to_le16(dwlen & ((1 << 16) - 1));
 	c.get_log_page.numdu = cpu_to_le16(dwlen >> 16);
-	c.get_log_page.lpol = cpu_to_le32(offset & ((1ULL << 32) - 1));
-	c.get_log_page.lpou = cpu_to_le32(offset >> 32ULL);
+	c.get_log_page.lpol = cpu_to_le32(lower_32_bits(offset));
+	c.get_log_page.lpou = cpu_to_le32(upper_32_bits(offset));
 
 	return nvme_submit_sync_cmd(ctrl->admin_q, &c, log, size);
 }
@@ -2833,7 +2839,9 @@ static struct nvme_ns_head *nvme_alloc_ns_head(struct nvme_ctrl *ctrl,
 		goto out_free_head;
 	head->instance = ret;
 	INIT_LIST_HEAD(&head->list);
-	init_srcu_struct(&head->srcu);
+	ret = init_srcu_struct(&head->srcu);
+	if (ret)
+		goto out_ida_remove;
 	head->subsys = ctrl->subsys;
 	head->ns_id = nsid;
 	kref_init(&head->ref);
@@ -2855,6 +2863,7 @@ static struct nvme_ns_head *nvme_alloc_ns_head(struct nvme_ctrl *ctrl,
 	return head;
 out_cleanup_srcu:
 	cleanup_srcu_struct(&head->srcu);
+out_ida_remove:
 	ida_simple_remove(&ctrl->subsys->ns_ida, head->instance);
 out_free_head:
 	kfree(head);

drivers/nvme/host/fabrics.c

@@ -536,6 +536,85 @@ static struct nvmf_transport_ops *nvmf_lookup_transport(
 	return NULL;
 }
 
+blk_status_t nvmf_check_if_ready(struct nvme_ctrl *ctrl, struct request *rq,
+		bool queue_live, bool is_connected)
+{
+	struct nvme_command *cmd = nvme_req(rq)->cmd;
+
+	if (likely(ctrl->state == NVME_CTRL_LIVE && is_connected))
+		return BLK_STS_OK;
+
+	switch (ctrl->state) {
+	case NVME_CTRL_DELETING:
+		goto reject_io;
+
+	case NVME_CTRL_NEW:
+	case NVME_CTRL_CONNECTING:
+		if (!is_connected)
+			/*
+			 * This is the case of starting a new
+			 * association but connectivity was lost
+			 * before it was fully created. We need to
+			 * error the commands used to initialize the
+			 * controller so the reconnect can go into a
+			 * retry attempt. The commands should all be
+			 * marked REQ_FAILFAST_DRIVER, which will hit
+			 * the reject path below. Anything else will
+			 * be queued while the state settles.
+			 */
+			goto reject_or_queue_io;
+
+		if ((queue_live &&
+		     !(nvme_req(rq)->flags & NVME_REQ_USERCMD)) ||
+		    (!queue_live && blk_rq_is_passthrough(rq) &&
+		     cmd->common.opcode == nvme_fabrics_command &&
+		     cmd->fabrics.fctype == nvme_fabrics_type_connect))
+			/*
+			 * If queue is live, allow only commands that
+			 * are internally generated pass through. These
+			 * are commands on the admin queue to initialize
+			 * the controller. This will reject any ioctl
+			 * admin cmds received while initializing.
+			 *
+			 * If the queue is not live, allow only a
+			 * connect command. This will reject any ioctl
+			 * admin cmd as well as initialization commands
+			 * if the controller reverted the queue to non-live.
+			 */
+			return BLK_STS_OK;
+
+		/*
+		 * fall-thru to the reject_or_queue_io clause
+		 */
+		break;
+
+	/* these cases fall-thru
+	 * case NVME_CTRL_LIVE:
+	 * case NVME_CTRL_RESETTING:
+	 */
+	default:
+		break;
+	}
+
+reject_or_queue_io:
+	/*
+	 * Any other new io is something we're not in a state to send
+	 * to the device. Default action is to busy it and retry it
+	 * after the controller state is recovered. However, anything
+	 * marked for failfast or nvme multipath is immediately failed.
+	 * Note: commands used to initialize the controller will be
+	 *  marked for failfast.
+	 * Note: nvme cli/ioctl commands are marked for failfast.
+	 */
+	if (!blk_noretry_request(rq) && !(rq->cmd_flags & REQ_NVME_MPATH))
+		return BLK_STS_RESOURCE;
+
+reject_io:
+	nvme_req(rq)->status = NVME_SC_ABORT_REQ;
+	return BLK_STS_IOERR;
+}
+EXPORT_SYMBOL_GPL(nvmf_check_if_ready);
+
 static const match_table_t opt_tokens = {
 	{ NVMF_OPT_TRANSPORT,		"transport=%s"		},
 	{ NVMF_OPT_TRADDR,		"traddr=%s"		},
@@ -608,8 +687,10 @@ static int nvmf_parse_options(struct nvmf_ctrl_options *opts,
 			opts->discovery_nqn =
 				!(strcmp(opts->subsysnqn,
 					 NVME_DISC_SUBSYS_NAME));
-			if (opts->discovery_nqn)
+			if (opts->discovery_nqn) {
+				opts->kato = 0;
 				opts->nr_io_queues = 0;
+			}
 			break;
 		case NVMF_OPT_TRADDR:
 			p = match_strdup(args);

drivers/nvme/host/fabrics.h

@@ -157,36 +157,7 @@ void nvmf_unregister_transport(struct nvmf_transport_ops *ops);
 void nvmf_free_options(struct nvmf_ctrl_options *opts);
 int nvmf_get_address(struct nvme_ctrl *ctrl, char *buf, int size);
 bool nvmf_should_reconnect(struct nvme_ctrl *ctrl);
-
-static inline blk_status_t nvmf_check_init_req(struct nvme_ctrl *ctrl,
-		struct request *rq)
-{
-	struct nvme_command *cmd = nvme_req(rq)->cmd;
-
-	/*
-	 * We cannot accept any other command until the connect command has
-	 * completed, so only allow connect to pass.
-	 */
-	if (!blk_rq_is_passthrough(rq) ||
-	    cmd->common.opcode != nvme_fabrics_command ||
-	    cmd->fabrics.fctype != nvme_fabrics_type_connect) {
-		/*
-		 * Connecting state means transport disruption or initial
-		 * establishment, which can take a long time and even might
-		 * fail permanently, fail fast to give upper layers a chance
-		 * to failover.
-		 * Deleting state means that the ctrl will never accept commands
-		 * again, fail it permanently.
-		 */
-		if (ctrl->state == NVME_CTRL_CONNECTING ||
-		    ctrl->state == NVME_CTRL_DELETING) {
-			nvme_req(rq)->status = NVME_SC_ABORT_REQ;
-			return BLK_STS_IOERR;
-		}
-		return BLK_STS_RESOURCE; /* try again later */
-	}
-
-	return BLK_STS_OK;
-}
+blk_status_t nvmf_check_if_ready(struct nvme_ctrl *ctrl,
+	struct request *rq, bool queue_live, bool is_connected);
 
 #endif /* _NVME_FABRICS_H */

drivers/nvme/host/fc.c

@@ -2277,14 +2277,6 @@ nvme_fc_start_fcp_op(struct nvme_fc_ctrl *ctrl, struct nvme_fc_queue *queue,
 	return BLK_STS_OK;
 }
 
-static inline blk_status_t nvme_fc_is_ready(struct nvme_fc_queue *queue,
-		struct request *rq)
-{
-	if (unlikely(!test_bit(NVME_FC_Q_LIVE, &queue->flags)))
-		return nvmf_check_init_req(&queue->ctrl->ctrl, rq);
-	return BLK_STS_OK;
-}
-
 static blk_status_t
 nvme_fc_queue_rq(struct blk_mq_hw_ctx *hctx,
 			const struct blk_mq_queue_data *bd)
@@ -2300,7 +2292,9 @@ nvme_fc_queue_rq(struct blk_mq_hw_ctx *hctx,
 	u32 data_len;
 	blk_status_t ret;
 
-	ret = nvme_fc_is_ready(queue, rq);
+	ret = nvmf_check_if_ready(&queue->ctrl->ctrl, rq,
+		test_bit(NVME_FC_Q_LIVE, &queue->flags),
+		ctrl->rport->remoteport.port_state == FC_OBJSTATE_ONLINE);
 	if (unlikely(ret))
 		return ret;
 

drivers/nvme/host/nvme.h

@@ -105,6 +105,7 @@ struct nvme_request {
 
 enum {
 	NVME_REQ_CANCELLED		= (1 << 0),
+	NVME_REQ_USERCMD		= (1 << 1),
 };
 
 static inline struct nvme_request *nvme_req(struct request *req)
@@ -422,7 +423,6 @@ int __nvme_submit_sync_cmd(struct request_queue *q, struct nvme_command *cmd,
 		unsigned timeout, int qid, int at_head,
 		blk_mq_req_flags_t flags);
 int nvme_set_queue_count(struct nvme_ctrl *ctrl, int *count);
-void nvme_start_keep_alive(struct nvme_ctrl *ctrl);
 void nvme_stop_keep_alive(struct nvme_ctrl *ctrl);
 int nvme_reset_ctrl(struct nvme_ctrl *ctrl);
 int nvme_reset_ctrl_sync(struct nvme_ctrl *ctrl);
@@ -430,7 +430,7 @@ int nvme_delete_ctrl(struct nvme_ctrl *ctrl);
 int nvme_delete_ctrl_sync(struct nvme_ctrl *ctrl);
 
 int nvme_get_log_ext(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
-		u8 log_page, void *log, size_t size, size_t offset);
+		u8 log_page, void *log, size_t size, u64 offset);
 
 extern const struct attribute_group nvme_ns_id_attr_group;
 extern const struct block_device_operations nvme_ns_head_ops;

drivers/nvme/host/pci.c

@@ -84,6 +84,7 @@ struct nvme_dev {
 	struct dma_pool *prp_small_pool;
 	unsigned online_queues;
 	unsigned max_qid;
+	unsigned int num_vecs;
 	int q_depth;
 	u32 db_stride;
 	void __iomem *bar;
@@ -414,7 +415,8 @@ static int nvme_pci_map_queues(struct blk_mq_tag_set *set)
 {
 	struct nvme_dev *dev = set->driver_data;
 
-	return blk_mq_pci_map_queues(set, to_pci_dev(dev->dev), 0);
+	return blk_mq_pci_map_queues(set, to_pci_dev(dev->dev),
+			dev->num_vecs > 1 ? 1 /* admin queue */ : 0);
 }
 
 /**
@@ -1380,8 +1382,7 @@ static int nvme_alloc_sq_cmds(struct nvme_dev *dev, struct nvme_queue *nvmeq,
 	return 0;
 }
 
-static int nvme_alloc_queue(struct nvme_dev *dev, int qid,
-		int depth, int node)
+static int nvme_alloc_queue(struct nvme_dev *dev, int qid, int depth)
 {
 	struct nvme_queue *nvmeq = &dev->queues[qid];
 
@@ -1457,7 +1458,11 @@ static int nvme_create_queue(struct nvme_queue *nvmeq, int qid)
 		nvmeq->sq_cmds_io = dev->cmb + offset;
 	}
 
-	nvmeq->cq_vector = qid - 1;
+	/*
+	 * A queue's vector matches the queue identifier unless the controller
+	 * has only one vector available.
+	 */
+	nvmeq->cq_vector = dev->num_vecs == 1 ? 0 : qid;
 	result = adapter_alloc_cq(dev, qid, nvmeq);
 	if (result < 0)
 		goto release_vector;
@@ -1596,8 +1601,7 @@ static int nvme_pci_configure_admin_queue(struct nvme_dev *dev)
 	if (result < 0)
 		return result;
 
-	result = nvme_alloc_queue(dev, 0, NVME_AQ_DEPTH,
-			dev_to_node(dev->dev));
+	result = nvme_alloc_queue(dev, 0, NVME_AQ_DEPTH);
 	if (result)
 		return result;
 
@@ -1630,9 +1634,7 @@ static int nvme_create_io_queues(struct nvme_dev *dev)
 	int ret = 0;
 
 	for (i = dev->ctrl.queue_count; i <= dev->max_qid; i++) {
-		/* vector == qid - 1, match nvme_create_queue */
-		if (nvme_alloc_queue(dev, i, dev->q_depth,
-		     pci_irq_get_node(to_pci_dev(dev->dev), i - 1))) {
+		if (nvme_alloc_queue(dev, i, dev->q_depth)) {
 			ret = -ENOMEM;
 			break;
 		}
@@ -1914,6 +1916,10 @@ static int nvme_setup_io_queues(struct nvme_dev *dev)
 	int result, nr_io_queues;
 	unsigned long size;
 
+	struct irq_affinity affd = {
+		.pre_vectors = 1
+	};
+
 	nr_io_queues = num_possible_cpus();
 	result = nvme_set_queue_count(&dev->ctrl, &nr_io_queues);
 	if (result < 0)
@@ -1949,11 +1955,12 @@ static int nvme_setup_io_queues(struct nvme_dev *dev)
 	 * setting up the full range we need.
 	 */
 	pci_free_irq_vectors(pdev);
-	nr_io_queues = pci_alloc_irq_vectors(pdev, 1, nr_io_queues,
-			PCI_IRQ_ALL_TYPES | PCI_IRQ_AFFINITY);
-	if (nr_io_queues <= 0)
+	result = pci_alloc_irq_vectors_affinity(pdev, 1, nr_io_queues + 1,
+			PCI_IRQ_ALL_TYPES | PCI_IRQ_AFFINITY, &affd);
+	if (result <= 0)
 		return -EIO;
-	dev->max_qid = nr_io_queues;
+	dev->num_vecs = result;
+	dev->max_qid = max(result - 1, 1);
 
 	/*
 	 * Should investigate if there's a performance win from allocating
@@ -2201,7 +2208,7 @@ static void nvme_dev_disable(struct nvme_dev *dev, bool shutdown)
 
 	nvme_stop_queues(&dev->ctrl);
 
-	if (!dead) {
+	if (!dead && dev->ctrl.queue_count > 0) {
 		/*
 		 * If the controller is still alive tell it to stop using the
 		 * host memory buffer.  In theory the shutdown / reset should

drivers/nvme/host/rdma.c

@@ -1601,17 +1601,6 @@ nvme_rdma_timeout(struct request *rq, bool reserved)
 	return BLK_EH_HANDLED;
 }
 
-/*
- * We cannot accept any other command until the Connect command has completed.
- */
-static inline blk_status_t
-nvme_rdma_is_ready(struct nvme_rdma_queue *queue, struct request *rq)
-{
-	if (unlikely(!test_bit(NVME_RDMA_Q_LIVE, &queue->flags)))
-		return nvmf_check_init_req(&queue->ctrl->ctrl, rq);
-	return BLK_STS_OK;
-}
-
 static blk_status_t nvme_rdma_queue_rq(struct blk_mq_hw_ctx *hctx,
 		const struct blk_mq_queue_data *bd)
 {
@@ -1627,7 +1616,8 @@ static blk_status_t nvme_rdma_queue_rq(struct blk_mq_hw_ctx *hctx,
 
 	WARN_ON_ONCE(rq->tag < 0);
 
-	ret = nvme_rdma_is_ready(queue, rq);
+	ret = nvmf_check_if_ready(&queue->ctrl->ctrl, rq,
+		test_bit(NVME_RDMA_Q_LIVE, &queue->flags), true);
 	if (unlikely(ret))
 		return ret;
 

drivers/nvme/target/admin-cmd.c

@@ -178,6 +178,7 @@ static void nvmet_execute_identify_ctrl(struct nvmet_req *req)
 	id->vid = 0;
 	id->ssvid = 0;
 
+	memset(id->sn, ' ', sizeof(id->sn));
 	bin2hex(id->sn, &ctrl->subsys->serial,
 		min(sizeof(ctrl->subsys->serial), sizeof(id->sn) / 2));
 	memcpy_and_pad(id->mn, sizeof(id->mn), model, sizeof(model) - 1, ' ');

drivers/nvme/target/discovery.c

@@ -59,7 +59,7 @@ static void nvmet_format_discovery_entry(struct nvmf_disc_rsp_page_hdr *hdr,
 	memcpy(e->trsvcid, port->disc_addr.trsvcid, NVMF_TRSVCID_SIZE);
 	memcpy(e->traddr, traddr, NVMF_TRADDR_SIZE);
 	memcpy(e->tsas.common, port->disc_addr.tsas.common, NVMF_TSAS_SIZE);
-	memcpy(e->subnqn, subsys_nqn, NVMF_NQN_SIZE);
+	strncpy(e->subnqn, subsys_nqn, NVMF_NQN_SIZE);
 }
 
 /*

drivers/nvme/target/io-cmd.c

@@ -173,8 +173,8 @@ static void nvmet_execute_write_zeroes(struct nvmet_req *req)
 
 	sector = le64_to_cpu(write_zeroes->slba) <<
 		(req->ns->blksize_shift - 9);
-	nr_sector = (((sector_t)le16_to_cpu(write_zeroes->length)) <<
-		(req->ns->blksize_shift - 9)) + 1;
+	nr_sector = (((sector_t)le16_to_cpu(write_zeroes->length) + 1) <<
+		(req->ns->blksize_shift - 9));
 
 	if (__blkdev_issue_zeroout(req->ns->bdev, sector, nr_sector,
 				GFP_KERNEL, &bio, 0))

drivers/nvme/target/loop.c

@@ -149,14 +149,6 @@ nvme_loop_timeout(struct request *rq, bool reserved)
 	return BLK_EH_HANDLED;
 }
 
-static inline blk_status_t nvme_loop_is_ready(struct nvme_loop_queue *queue,
-		struct request *rq)
-{
-	if (unlikely(!test_bit(NVME_LOOP_Q_LIVE, &queue->flags)))
-		return nvmf_check_init_req(&queue->ctrl->ctrl, rq);
-	return BLK_STS_OK;
-}
-
 static blk_status_t nvme_loop_queue_rq(struct blk_mq_hw_ctx *hctx,
 		const struct blk_mq_queue_data *bd)
 {
@@ -166,7 +158,8 @@ static blk_status_t nvme_loop_queue_rq(struct blk_mq_hw_ctx *hctx,
 	struct nvme_loop_iod *iod = blk_mq_rq_to_pdu(req);
 	blk_status_t ret;
 
-	ret = nvme_loop_is_ready(queue, req);
+	ret = nvmf_check_if_ready(&queue->ctrl->ctrl, req,
+		test_bit(NVME_LOOP_Q_LIVE, &queue->flags), true);
 	if (unlikely(ret))
 		return ret;
 
@@ -174,15 +167,12 @@ static blk_status_t nvme_loop_queue_rq(struct blk_mq_hw_ctx *hctx,
 	if (ret)
 		return ret;
 
+	blk_mq_start_request(req);
 	iod->cmd.common.flags |= NVME_CMD_SGL_METABUF;
 	iod->req.port = nvmet_loop_port;
 	if (!nvmet_req_init(&iod->req, &queue->nvme_cq,
-			&queue->nvme_sq, &nvme_loop_ops)) {
-		nvme_cleanup_cmd(req);
-		blk_mq_start_request(req);
-		nvme_loop_queue_response(&iod->req);
+			&queue->nvme_sq, &nvme_loop_ops))
 		return BLK_STS_OK;
-	}
 
 	if (blk_rq_payload_bytes(req)) {
 		iod->sg_table.sgl = iod->first_sgl;
@@ -196,8 +186,6 @@ static blk_status_t nvme_loop_queue_rq(struct blk_mq_hw_ctx *hctx,
 		iod->req.transfer_len = blk_rq_payload_bytes(req);
 	}
 
-	blk_mq_start_request(req);
-
 	schedule_work(&iod->work);
 	return BLK_STS_OK;
 }

drivers/scsi/sr.c

@@ -587,18 +587,28 @@ static int sr_block_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd,
 static unsigned int sr_block_check_events(struct gendisk *disk,
 					  unsigned int clearing)
 {
-	struct scsi_cd *cd = scsi_cd(disk);
+	unsigned int ret = 0;
+	struct scsi_cd *cd;
 
-	if (atomic_read(&cd->device->disk_events_disable_depth))
+	cd = scsi_cd_get(disk);
+	if (!cd)
 		return 0;
 
-	return cdrom_check_events(&cd->cdi, clearing);
+	if (!atomic_read(&cd->device->disk_events_disable_depth))
+		ret = cdrom_check_events(&cd->cdi, clearing);
+
+	scsi_cd_put(cd);
+	return ret;
 }
 
 static int sr_block_revalidate_disk(struct gendisk *disk)
 {
-	struct scsi_cd *cd = scsi_cd(disk);
 	struct scsi_sense_hdr sshdr;
+	struct scsi_cd *cd;
+
+	cd = scsi_cd_get(disk);
+	if (!cd)
+		return -ENXIO;
 
 	/* if the unit is not ready, nothing more to do */
 	if (scsi_test_unit_ready(cd->device, SR_TIMEOUT, MAX_RETRIES, &sshdr))
@@ -607,6 +617,7 @@ static int sr_block_revalidate_disk(struct gendisk *disk)
 	sr_cd_check(&cd->cdi);
 	get_sectorsize(cd);
 out:
+	scsi_cd_put(cd);
 	return 0;
 }
 

include/linux/backing-dev.h

@@ -28,6 +28,7 @@ void bdi_put(struct backing_dev_info *bdi);
 
 __printf(2, 3)
 int bdi_register(struct backing_dev_info *bdi, const char *fmt, ...);
+__printf(2, 0)
 int bdi_register_va(struct backing_dev_info *bdi, const char *fmt,
 		    va_list args);
 int bdi_register_owner(struct backing_dev_info *bdi, struct device *owner);

include/linux/blk-mq.h

@@ -183,7 +183,6 @@ enum {
 	BLK_MQ_S_STOPPED	= 0,
 	BLK_MQ_S_TAG_ACTIVE	= 1,
 	BLK_MQ_S_SCHED_RESTART	= 2,
-	BLK_MQ_S_START_ON_RUN	= 3,
 
 	BLK_MQ_MAX_DEPTH	= 10240,
 
@@ -270,7 +269,6 @@ void blk_mq_unquiesce_queue(struct request_queue *q);
 void blk_mq_delay_run_hw_queue(struct blk_mq_hw_ctx *hctx, unsigned long msecs);
 bool blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async);
 void blk_mq_run_hw_queues(struct request_queue *q, bool async);
-void blk_mq_delay_queue(struct blk_mq_hw_ctx *hctx, unsigned long msecs);
 void blk_mq_tagset_busy_iter(struct blk_mq_tag_set *tagset,
 		busy_tag_iter_fn *fn, void *priv);
 void blk_mq_freeze_queue(struct request_queue *q);