Merge tag 'block-5.13-2021-05-14' of git://git.kernel.dk/linux-block

Pull block fixes from Jens Axboe:

 - Fix for shared tag set exit (Bart)

 - Correct ioctl range for zoned ioctls (Damien)

 - Removed dead/unused function (Lin)

 - Fix perf regression for shared tags (Ming)

 - Fix out-of-bounds issue with kyber and preemption (Omar)

 - BFQ merge fix (Paolo)

 - Two error handling fixes for nbd (Sun)

 - Fix weight update in blk-iocost (Tejun)

 - NVMe pull request (Christoph):
      - correct the check for using the inline bio in nvmet (Chaitanya
        Kulkarni)
      - demote unsupported command warnings (Chaitanya Kulkarni)
      - fix corruption due to double initializing ANA state (me, Hou Pu)
      - reset ns->file when open fails (Daniel Wagner)
      - fix a NULL deref when SEND is completed with error in nvmet-rdma
        (Michal Kalderon)

 - Fix kernel-doc warning (Bart)

* tag 'block-5.13-2021-05-14' of git://git.kernel.dk/linux-block:
  block/partitions/efi.c: Fix the efi_partition() kernel-doc header
  blk-mq: Swap two calls in blk_mq_exit_queue()
  blk-mq: plug request for shared sbitmap
  nvmet: use new ana_log_size instead the old one
  nvmet: seset ns->file when open fails
  nbd: share nbd_put and return by goto put_nbd
  nbd: Fix NULL pointer in flush_workqueue
  blkdev.h: remove unused codes blk_account_rq
  block, bfq: avoid circular stable merges
  blk-iocost: fix weight updates of inner active iocgs
  nvmet: demote fabrics cmd parse err msg to debug
  nvmet: use helper to remove the duplicate code
  nvmet: demote discovery cmd parse err msg to debug
  nvmet-rdma: Fix NULL deref when SEND is completed with error
  nvmet: fix inline bio check for passthru
  nvmet: fix inline bio check for bdev-ns
  nvme-multipath: fix double initialization of ANA state
  kyber: fix out of bounds access when preempted
  block: uapi: fix comment about block device ioctl

Author: torvalds

block/bfq-iosched.c

@@ -372,9 +372,38 @@ struct bfq_queue *bic_to_bfqq(struct bfq_io_cq *bic, bool is_sync)
 	return bic->bfqq[is_sync];
 }
 
+static void bfq_put_stable_ref(struct bfq_queue *bfqq);
+
 void bic_set_bfqq(struct bfq_io_cq *bic, struct bfq_queue *bfqq, bool is_sync)
 {
+	/*
+	 * If bfqq != NULL, then a non-stable queue merge between
+	 * bic->bfqq and bfqq is happening here. This causes troubles
+	 * in the following case: bic->bfqq has also been scheduled
+	 * for a possible stable merge with bic->stable_merge_bfqq,
+	 * and bic->stable_merge_bfqq == bfqq happens to
+	 * hold. Troubles occur because bfqq may then undergo a split,
+	 * thereby becoming eligible for a stable merge. Yet, if
+	 * bic->stable_merge_bfqq points exactly to bfqq, then bfqq
+	 * would be stably merged with itself. To avoid this anomaly,
+	 * we cancel the stable merge if
+	 * bic->stable_merge_bfqq == bfqq.
+	 */
 	bic->bfqq[is_sync] = bfqq;
+
+	if (bfqq && bic->stable_merge_bfqq == bfqq) {
+		/*
+		 * Actually, these same instructions are executed also
+		 * in bfq_setup_cooperator, in case of abort or actual
+		 * execution of a stable merge. We could avoid
+		 * repeating these instructions there too, but if we
+		 * did so, we would nest even more complexity in this
+		 * function.
+		 */
+		bfq_put_stable_ref(bic->stable_merge_bfqq);
+
+		bic->stable_merge_bfqq = NULL;
+	}
 }
 
 struct bfq_data *bic_to_bfqd(struct bfq_io_cq *bic)
@@ -2263,10 +2292,9 @@ static void bfq_remove_request(struct request_queue *q,
 
 }
 
-static bool bfq_bio_merge(struct blk_mq_hw_ctx *hctx, struct bio *bio,
+static bool bfq_bio_merge(struct request_queue *q, struct bio *bio,
 		unsigned int nr_segs)
 {
-	struct request_queue *q = hctx->queue;
 	struct bfq_data *bfqd = q->elevator->elevator_data;
 	struct request *free = NULL;
 	/*
@@ -2631,8 +2659,6 @@ static bool bfq_may_be_close_cooperator(struct bfq_queue *bfqq,
 static bool idling_boosts_thr_without_issues(struct bfq_data *bfqd,
 					     struct bfq_queue *bfqq);
 
-static void bfq_put_stable_ref(struct bfq_queue *bfqq);
-
 /*
  * Attempt to schedule a merge of bfqq with the currently in-service
  * queue or with a close queue among the scheduled queues.  Return

block/blk-iocost.c

@@ -1069,7 +1069,17 @@ static void __propagate_weights(struct ioc_gq *iocg, u32 active, u32 inuse,
 
 	lockdep_assert_held(&ioc->lock);
 
-	inuse = clamp_t(u32, inuse, 1, active);
+	/*
+	 * For an active leaf node, its inuse shouldn't be zero or exceed
+	 * @active. An active internal node's inuse is solely determined by the
+	 * inuse to active ratio of its children regardless of @inuse.
+	 */
+	if (list_empty(&iocg->active_list) && iocg->child_active_sum) {
+		inuse = DIV64_U64_ROUND_UP(active * iocg->child_inuse_sum,
+					   iocg->child_active_sum);
+	} else {
+		inuse = clamp_t(u32, inuse, 1, active);
+	}
 
 	iocg->last_inuse = iocg->inuse;
 	if (save)
@@ -1086,7 +1096,7 @@ static void __propagate_weights(struct ioc_gq *iocg, u32 active, u32 inuse,
 		/* update the level sums */
 		parent->child_active_sum += (s32)(active - child->active);
 		parent->child_inuse_sum += (s32)(inuse - child->inuse);
-		/* apply the udpates */
+		/* apply the updates */
 		child->active = active;
 		child->inuse = inuse;
 

block/blk-mq-sched.c

@@ -358,14 +358,16 @@ bool __blk_mq_sched_bio_merge(struct request_queue *q, struct bio *bio,
 		unsigned int nr_segs)
 {
 	struct elevator_queue *e = q->elevator;
-	struct blk_mq_ctx *ctx = blk_mq_get_ctx(q);
-	struct blk_mq_hw_ctx *hctx = blk_mq_map_queue(q, bio->bi_opf, ctx);
+	struct blk_mq_ctx *ctx;
+	struct blk_mq_hw_ctx *hctx;
 	bool ret = false;
 	enum hctx_type type;
 
 	if (e && e->type->ops.bio_merge)
-		return e->type->ops.bio_merge(hctx, bio, nr_segs);
+		return e->type->ops.bio_merge(q, bio, nr_segs);
 
+	ctx = blk_mq_get_ctx(q);
+	hctx = blk_mq_map_queue(q, bio->bi_opf, ctx);
 	type = hctx->type;
 	if (!(hctx->flags & BLK_MQ_F_SHOULD_MERGE) ||
 	    list_empty_careful(&ctx->rq_lists[type]))

block/blk-mq.c

@@ -2232,8 +2232,9 @@ blk_qc_t blk_mq_submit_bio(struct bio *bio)
 		/* Bypass scheduler for flush requests */
 		blk_insert_flush(rq);
 		blk_mq_run_hw_queue(data.hctx, true);
-	} else if (plug && (q->nr_hw_queues == 1 || q->mq_ops->commit_rqs ||
-				!blk_queue_nonrot(q))) {
+	} else if (plug && (q->nr_hw_queues == 1 ||
+		   blk_mq_is_sbitmap_shared(rq->mq_hctx->flags) ||
+		   q->mq_ops->commit_rqs || !blk_queue_nonrot(q))) {
 		/*
 		 * Use plugging if we have a ->commit_rqs() hook as well, as
 		 * we know the driver uses bd->last in a smart fashion.
@@ -3285,10 +3286,12 @@ EXPORT_SYMBOL(blk_mq_init_allocated_queue);
 /* tags can _not_ be used after returning from blk_mq_exit_queue */
 void blk_mq_exit_queue(struct request_queue *q)
 {
-	struct blk_mq_tag_set	*set = q->tag_set;
+	struct blk_mq_tag_set *set = q->tag_set;
 
-	blk_mq_del_queue_tag_set(q);
+	/* Checks hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED. */
 	blk_mq_exit_hw_queues(q, set, set->nr_hw_queues);
+	/* May clear BLK_MQ_F_TAG_QUEUE_SHARED in hctx->flags. */
+	blk_mq_del_queue_tag_set(q);
 }
 
 static int __blk_mq_alloc_rq_maps(struct blk_mq_tag_set *set)

block/kyber-iosched.c

@@ -561,11 +561,12 @@ static void kyber_limit_depth(unsigned int op, struct blk_mq_alloc_data *data)
 	}
 }
 
-static bool kyber_bio_merge(struct blk_mq_hw_ctx *hctx, struct bio *bio,
+static bool kyber_bio_merge(struct request_queue *q, struct bio *bio,
 		unsigned int nr_segs)
 {
+	struct blk_mq_ctx *ctx = blk_mq_get_ctx(q);
+	struct blk_mq_hw_ctx *hctx = blk_mq_map_queue(q, bio->bi_opf, ctx);
 	struct kyber_hctx_data *khd = hctx->sched_data;
-	struct blk_mq_ctx *ctx = blk_mq_get_ctx(hctx->queue);
 	struct kyber_ctx_queue *kcq = &khd->kcqs[ctx->index_hw[hctx->type]];
 	unsigned int sched_domain = kyber_sched_domain(bio->bi_opf);
 	struct list_head *rq_list = &kcq->rq_list[sched_domain];

block/mq-deadline.c

@@ -461,10 +461,9 @@ static int dd_request_merge(struct request_queue *q, struct request **rq,
 	return ELEVATOR_NO_MERGE;
 }
 
-static bool dd_bio_merge(struct blk_mq_hw_ctx *hctx, struct bio *bio,
+static bool dd_bio_merge(struct request_queue *q, struct bio *bio,
 		unsigned int nr_segs)
 {
-	struct request_queue *q = hctx->queue;
 	struct deadline_data *dd = q->elevator->elevator_data;
 	struct request *free = NULL;
 	bool ret;

block/partitions/efi.c

@@ -682,7 +682,7 @@ static void utf16_le_to_7bit(const __le16 *in, unsigned int size, u8 *out)
 }
 
 /**
- * efi_partition(struct parsed_partitions *state)
+ * efi_partition - scan for GPT partitions
  * @state: disk parsed partitions
  *
  * Description: called from check.c, if the disk contains GPT

drivers/block/nbd.c

@@ -1980,7 +1980,8 @@ static void nbd_disconnect_and_put(struct nbd_device *nbd)
 	 * config ref and try to destroy the workqueue from inside the work
 	 * queue.
 	 */
-	flush_workqueue(nbd->recv_workq);
+	if (nbd->recv_workq)
+		flush_workqueue(nbd->recv_workq);
 	if (test_and_clear_bit(NBD_RT_HAS_CONFIG_REF,
 			       &nbd->config->runtime_flags))
 		nbd_config_put(nbd);
@@ -2014,12 +2015,11 @@ static int nbd_genl_disconnect(struct sk_buff *skb, struct genl_info *info)
 		return -EINVAL;
 	}
 	mutex_unlock(&nbd_index_mutex);
-	if (!refcount_inc_not_zero(&nbd->config_refs)) {
-		nbd_put(nbd);
-		return 0;
-	}
+	if (!refcount_inc_not_zero(&nbd->config_refs))
+		goto put_nbd;
 	nbd_disconnect_and_put(nbd);
 	nbd_config_put(nbd);
+put_nbd:
 	nbd_put(nbd);
 	return 0;
 }

drivers/nvme/host/core.c

@@ -2901,7 +2901,7 @@ static int nvme_init_identify(struct nvme_ctrl *ctrl)
 		ctrl->hmmaxd = le16_to_cpu(id->hmmaxd);
 	}
 
-	ret = nvme_mpath_init(ctrl, id);
+	ret = nvme_mpath_init_identify(ctrl, id);
 	if (ret < 0)
 		goto out_free;
 
@@ -4364,6 +4364,7 @@ int nvme_init_ctrl(struct nvme_ctrl *ctrl, struct device *dev,
 		min(default_ps_max_latency_us, (unsigned long)S32_MAX));
 
 	nvme_fault_inject_init(&ctrl->fault_inject, dev_name(ctrl->device));
+	nvme_mpath_init_ctrl(ctrl);
 
 	return 0;
 out_free_name:

drivers/nvme/host/multipath.c

@@ -781,9 +781,18 @@ void nvme_mpath_remove_disk(struct nvme_ns_head *head)
 	put_disk(head->disk);
 }
 
-int nvme_mpath_init(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id)
+void nvme_mpath_init_ctrl(struct nvme_ctrl *ctrl)
 {
-	int error;
+	mutex_init(&ctrl->ana_lock);
+	timer_setup(&ctrl->anatt_timer, nvme_anatt_timeout, 0);
+	INIT_WORK(&ctrl->ana_work, nvme_ana_work);
+}
+
+int nvme_mpath_init_identify(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id)
+{
+	size_t max_transfer_size = ctrl->max_hw_sectors << SECTOR_SHIFT;
+	size_t ana_log_size;
+	int error = 0;
 
 	/* check if multipath is enabled and we have the capability */
 	if (!multipath || !ctrl->subsys ||
@@ -795,37 +804,31 @@ int nvme_mpath_init(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id)
 	ctrl->nanagrpid = le32_to_cpu(id->nanagrpid);
 	ctrl->anagrpmax = le32_to_cpu(id->anagrpmax);
 
-	mutex_init(&ctrl->ana_lock);
-	timer_setup(&ctrl->anatt_timer, nvme_anatt_timeout, 0);
-	ctrl->ana_log_size = sizeof(struct nvme_ana_rsp_hdr) +
-		ctrl->nanagrpid * sizeof(struct nvme_ana_group_desc);
-	ctrl->ana_log_size += ctrl->max_namespaces * sizeof(__le32);
-
-	if (ctrl->ana_log_size > ctrl->max_hw_sectors << SECTOR_SHIFT) {
+	ana_log_size = sizeof(struct nvme_ana_rsp_hdr) +
+		ctrl->nanagrpid * sizeof(struct nvme_ana_group_desc) +
+		ctrl->max_namespaces * sizeof(__le32);
+	if (ana_log_size > max_transfer_size) {
 		dev_err(ctrl->device,
-			"ANA log page size (%zd) larger than MDTS (%d).\n",
-			ctrl->ana_log_size,
-			ctrl->max_hw_sectors << SECTOR_SHIFT);
+			"ANA log page size (%zd) larger than MDTS (%zd).\n",
+			ana_log_size, max_transfer_size);
 		dev_err(ctrl->device, "disabling ANA support.\n");
-		return 0;
+		goto out_uninit;
 	}
-
-	INIT_WORK(&ctrl->ana_work, nvme_ana_work);
-	kfree(ctrl->ana_log_buf);
-	ctrl->ana_log_buf = kmalloc(ctrl->ana_log_size, GFP_KERNEL);
-	if (!ctrl->ana_log_buf) {
-		error = -ENOMEM;
-		goto out;
+	if (ana_log_size > ctrl->ana_log_size) {
+		nvme_mpath_stop(ctrl);
+		kfree(ctrl->ana_log_buf);
+		ctrl->ana_log_buf = kmalloc(ana_log_size, GFP_KERNEL);
+		if (!ctrl->ana_log_buf)
+			return -ENOMEM;
 	}
-
+	ctrl->ana_log_size = ana_log_size;
 	error = nvme_read_ana_log(ctrl);
 	if (error)
-		goto out_free_ana_log_buf;
+		goto out_uninit;
 	return 0;
-out_free_ana_log_buf:
-	kfree(ctrl->ana_log_buf);
-	ctrl->ana_log_buf = NULL;
-out:
+
+out_uninit:
+	nvme_mpath_uninit(ctrl);
 	return error;
 }