Merge tag 'for-6.5/block-2023-06-23' of git://git.kernel.dk/linux

Pull block updates from Jens Axboe:

 - NVMe pull request via Keith:
      - Various cleanups all around (Irvin, Chaitanya, Christophe)
      - Better struct packing (Christophe JAILLET)
      - Reduce controller error logs for optional commands (Keith)
      - Support for >=64KiB block sizes (Daniel Gomez)
      - Fabrics fixes and code organization (Max, Chaitanya, Daniel
        Wagner)

 - bcache updates via Coly:
      - Fix a race at init time (Mingzhe Zou)
      - Misc fixes and cleanups (Andrea, Thomas, Zheng, Ye)

 - use page pinning in the block layer for dio (David)

 - convert old block dio code to page pinning (David, Christoph)

 - cleanups for pktcdvd (Andy)

 - cleanups for rnbd (Guoqing)

 - use the unchecked __bio_add_page() for the initial single page
   additions (Johannes)

 - fix overflows in the Amiga partition handling code (Michael)

 - improve mq-deadline zoned device support (Bart)

 - keep passthrough requests out of the IO schedulers (Christoph, Ming)

 - improve support for flush requests, making them less special to deal
   with (Christoph)

 - add bdev holder ops and shutdown methods (Christoph)

 - fix the name_to_dev_t() situation and use cases (Christoph)

 - decouple the block open flags from fmode_t (Christoph)

 - ublk updates and cleanups, including adding user copy support (Ming)

 - BFQ sanity checking (Bart)

 - convert brd from radix to xarray (Pankaj)

 - constify various structures (Thomas, Ivan)

 - more fine grained persistent reservation ioctl capability checks
   (Jingbo)

 - misc fixes and cleanups (Arnd, Azeem, Demi, Ed, Hengqi, Hou, Jan,
   Jordy, Li, Min, Yu, Zhong, Waiman)

* tag 'for-6.5/block-2023-06-23' of git://git.kernel.dk/linux: (266 commits)
  scsi/sg: don't grab scsi host module reference
  ext4: Fix warning in blkdev_put()
  block: don't return -EINVAL for not found names in devt_from_devname
  cdrom: Fix spectre-v1 gadget
  block: Improve kernel-doc headers
  blk-mq: don't insert passthrough request into sw queue
  bsg: make bsg_class a static const structure
  ublk: make ublk_chr_class a static const structure
  aoe: make aoe_class a static const structure
  block/rnbd: make all 'class' structures const
  block: fix the exclusive open mask in disk_scan_partitions
  block: add overflow checks for Amiga partition support
  block: change all __u32 annotations to __be32 in affs_hardblocks.h
  block: fix signed int overflow in Amiga partition support
  block: add capacity validation in bdev_add_partition()
  block: fine-granular CAP_SYS_ADMIN for Persistent Reservation
  block: disallow Persistent Reservation on partitions
  reiserfs: fix blkdev_put() warning from release_journal_dev()
  block: fix wrong mode for blkdev_get_by_dev() from disk_scan_partitions()
  block: document the holder argument to blkdev_get_by_path
  ...

1 files changed, 73 insertions, 68 deletions

diff --git a/block/blk-mq.c b/block/blk-mq.c
index 850bfb844ed2..decb6ab2d508 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -45,6 +45,8 @@
 static DEFINE_PER_CPU(struct llist_head, blk_cpu_done);
 
 static void blk_mq_insert_request(struct request *rq, blk_insert_t flags);
+static void blk_mq_request_bypass_insert(struct request *rq,
+		blk_insert_t flags);
 static void blk_mq_try_issue_list_directly(struct blk_mq_hw_ctx *hctx,
 		struct list_head *list);
 
@@ -354,12 +356,12 @@ static struct request *blk_mq_rq_ctx_init(struct blk_mq_alloc_data *data,
 		data->rq_flags |= RQF_IO_STAT;
 	rq->rq_flags = data->rq_flags;
 
-	if (!(data->rq_flags & RQF_ELV)) {
-		rq->tag = tag;
-		rq->internal_tag = BLK_MQ_NO_TAG;
-	} else {
+	if (data->rq_flags & RQF_SCHED_TAGS) {
 		rq->tag = BLK_MQ_NO_TAG;
 		rq->internal_tag = tag;
+	} else {
+		rq->tag = tag;
+		rq->internal_tag = BLK_MQ_NO_TAG;
 	}
 	rq->timeout = 0;
 
@@ -386,17 +388,14 @@ static struct request *blk_mq_rq_ctx_init(struct blk_mq_alloc_data *data,
 	WRITE_ONCE(rq->deadline, 0);
 	req_ref_set(rq, 1);
 
-	if (rq->rq_flags & RQF_ELV) {
+	if (rq->rq_flags & RQF_USE_SCHED) {
 		struct elevator_queue *e = data->q->elevator;
 
 		INIT_HLIST_NODE(&rq->hash);
 		RB_CLEAR_NODE(&rq->rb_node);
 
-		if (!op_is_flush(data->cmd_flags) &&
-		    e->type->ops.prepare_request) {
+		if (e->type->ops.prepare_request)
 			e->type->ops.prepare_request(rq);
-			rq->rq_flags |= RQF_ELVPRIV;
-		}
 	}
 
 	return rq;
@@ -449,26 +448,32 @@ static struct request *__blk_mq_alloc_requests(struct blk_mq_alloc_data *data)
 		data->flags |= BLK_MQ_REQ_NOWAIT;
 
 	if (q->elevator) {
-		struct elevator_queue *e = q->elevator;
-
-		data->rq_flags |= RQF_ELV;
+		/*
+		 * All requests use scheduler tags when an I/O scheduler is
+		 * enabled for the queue.
+		 */
+		data->rq_flags |= RQF_SCHED_TAGS;
 
 		/*
 		 * Flush/passthrough requests are special and go directly to the
-		 * dispatch list. Don't include reserved tags in the
-		 * limiting, as it isn't useful.
+		 * dispatch list.
 		 */
-		if (!op_is_flush(data->cmd_flags) &&
-		    !blk_op_is_passthrough(data->cmd_flags) &&
-		    e->type->ops.limit_depth &&
-		    !(data->flags & BLK_MQ_REQ_RESERVED))
-			e->type->ops.limit_depth(data->cmd_flags, data);
+		if ((data->cmd_flags & REQ_OP_MASK) != REQ_OP_FLUSH &&
+		    !blk_op_is_passthrough(data->cmd_flags)) {
+			struct elevator_mq_ops *ops = &q->elevator->type->ops;
+
+			WARN_ON_ONCE(data->flags & BLK_MQ_REQ_RESERVED);
+
+			data->rq_flags |= RQF_USE_SCHED;
+			if (ops->limit_depth)
+				ops->limit_depth(data->cmd_flags, data);
+		}
 	}
 
 retry:
 	data->ctx = blk_mq_get_ctx(q);
 	data->hctx = blk_mq_map_queue(q, data->cmd_flags, data->ctx);
-	if (!(data->rq_flags & RQF_ELV))
+	if (!(data->rq_flags & RQF_SCHED_TAGS))
 		blk_mq_tag_busy(data->hctx);
 
 	if (data->flags & BLK_MQ_REQ_RESERVED)
@@ -648,10 +653,10 @@ struct request *blk_mq_alloc_request_hctx(struct request_queue *q,
 		goto out_queue_exit;
 	data.ctx = __blk_mq_get_ctx(q, cpu);
 
-	if (!q->elevator)
-		blk_mq_tag_busy(data.hctx);
+	if (q->elevator)
+		data.rq_flags |= RQF_SCHED_TAGS;
 	else
-		data.rq_flags |= RQF_ELV;
+		blk_mq_tag_busy(data.hctx);
 
 	if (flags & BLK_MQ_REQ_RESERVED)
 		data.rq_flags |= RQF_RESV;
@@ -699,7 +704,7 @@ void blk_mq_free_request(struct request *rq)
 {
 	struct request_queue *q = rq->q;
 
-	if ((rq->rq_flags & RQF_ELVPRIV) &&
+	if ((rq->rq_flags & RQF_USE_SCHED) &&
 	    q->elevator->type->ops.finish_request)
 		q->elevator->type->ops.finish_request(rq);
 
@@ -957,6 +962,8 @@ EXPORT_SYMBOL_GPL(blk_update_request);
 
 static inline void blk_account_io_done(struct request *req, u64 now)
 {
+	trace_block_io_done(req);
+
 	/*
 	 * Account IO completion.  flush_rq isn't accounted as a
 	 * normal IO on queueing nor completion.  Accounting the
@@ -976,6 +983,8 @@ static inline void blk_account_io_done(struct request *req, u64 now)
 
 static inline void blk_account_io_start(struct request *req)
 {
+	trace_block_io_start(req);
+
 	if (blk_do_io_stat(req)) {
 		/*
 		 * All non-passthrough requests are created from a bio with one
@@ -1176,8 +1185,9 @@ bool blk_mq_complete_request_remote(struct request *rq)
 	 * or a polled request, always complete locally,
 	 * it's pointless to redirect the completion.
 	 */
-	if (rq->mq_hctx->nr_ctx == 1 ||
-		rq->cmd_flags & REQ_POLLED)
+	if ((rq->mq_hctx->nr_ctx == 1 &&
+	     rq->mq_ctx->cpu == raw_smp_processor_id()) ||
+	     rq->cmd_flags & REQ_POLLED)
 		return false;
 
 	if (blk_mq_complete_need_ipi(rq)) {
@@ -1270,7 +1280,7 @@ static void blk_add_rq_to_plug(struct blk_plug *plug, struct request *rq)
 
 	if (!plug->multiple_queues && last && last->q != rq->q)
 		plug->multiple_queues = true;
-	if (!plug->has_elevator && (rq->rq_flags & RQF_ELV))
+	if (!plug->has_elevator && (rq->rq_flags & RQF_USE_SCHED))
 		plug->has_elevator = true;
 	rq->rq_next = NULL;
 	rq_list_add(&plug->mq_list, rq);
@@ -1411,13 +1421,16 @@ static void __blk_mq_requeue_request(struct request *rq)
 void blk_mq_requeue_request(struct request *rq, bool kick_requeue_list)
 {
 	struct request_queue *q = rq->q;
+	unsigned long flags;
 
 	__blk_mq_requeue_request(rq);
 
 	/* this request will be re-inserted to io scheduler queue */
 	blk_mq_sched_requeue_request(rq);
 
-	blk_mq_add_to_requeue_list(rq, BLK_MQ_INSERT_AT_HEAD);
+	spin_lock_irqsave(&q->requeue_lock, flags);
+	list_add_tail(&rq->queuelist, &q->requeue_list);
+	spin_unlock_irqrestore(&q->requeue_lock, flags);
 
 	if (kick_requeue_list)
 		blk_mq_kick_requeue_list(q);
@@ -1429,13 +1442,16 @@ static void blk_mq_requeue_work(struct work_struct *work)
 	struct request_queue *q =
 		container_of(work, struct request_queue, requeue_work.work);
 	LIST_HEAD(rq_list);
-	struct request *rq, *next;
+	LIST_HEAD(flush_list);
+	struct request *rq;
 
 	spin_lock_irq(&q->requeue_lock);
 	list_splice_init(&q->requeue_list, &rq_list);
+	list_splice_init(&q->flush_list, &flush_list);
 	spin_unlock_irq(&q->requeue_lock);
 
-	list_for_each_entry_safe(rq, next, &rq_list, queuelist) {
+	while (!list_empty(&rq_list)) {
+		rq = list_entry(rq_list.next, struct request, queuelist);
 		/*
 		 * If RQF_DONTPREP ist set, the request has been started by the
 		 * driver already and might have driver-specific data allocated
@@ -1443,18 +1459,16 @@ static void blk_mq_requeue_work(struct work_struct *work)
 		 * block layer merges for the request.
 		 */
 		if (rq->rq_flags & RQF_DONTPREP) {
-			rq->rq_flags &= ~RQF_SOFTBARRIER;
 			list_del_init(&rq->queuelist);
 			blk_mq_request_bypass_insert(rq, 0);
-		} else if (rq->rq_flags & RQF_SOFTBARRIER) {
-			rq->rq_flags &= ~RQF_SOFTBARRIER;
+		} else {
 			list_del_init(&rq->queuelist);
 			blk_mq_insert_request(rq, BLK_MQ_INSERT_AT_HEAD);
 		}
 	}
 
-	while (!list_empty(&rq_list)) {
-		rq = list_entry(rq_list.next, struct request, queuelist);
+	while (!list_empty(&flush_list)) {
+		rq = list_entry(flush_list.next, struct request, queuelist);
 		list_del_init(&rq->queuelist);
 		blk_mq_insert_request(rq, 0);
 	}
@@ -1462,27 +1476,6 @@ static void blk_mq_requeue_work(struct work_struct *work)
 	blk_mq_run_hw_queues(q, false);
 }
 
-void blk_mq_add_to_requeue_list(struct request *rq, blk_insert_t insert_flags)
-{
-	struct request_queue *q = rq->q;
-	unsigned long flags;
-
-	/*
-	 * We abuse this flag that is otherwise used by the I/O scheduler to
-	 * request head insertion from the workqueue.
-	 */
-	BUG_ON(rq->rq_flags & RQF_SOFTBARRIER);
-
-	spin_lock_irqsave(&q->requeue_lock, flags);
-	if (insert_flags & BLK_MQ_INSERT_AT_HEAD) {
-		rq->rq_flags |= RQF_SOFTBARRIER;
-		list_add(&rq->queuelist, &q->requeue_list);
-	} else {
-		list_add_tail(&rq->queuelist, &q->requeue_list);
-	}
-	spin_unlock_irqrestore(&q->requeue_lock, flags);
-}
-
 void blk_mq_kick_requeue_list(struct request_queue *q)
 {
 	kblockd_mod_delayed_work_on(WORK_CPU_UNBOUND, &q->requeue_work, 0);
@@ -2427,7 +2420,7 @@ static void blk_mq_run_work_fn(struct work_struct *work)
  * Should only be used carefully, when the caller knows we want to
  * bypass a potential IO scheduler on the target device.
  */
-void blk_mq_request_bypass_insert(struct request *rq, blk_insert_t flags)
+static void blk_mq_request_bypass_insert(struct request *rq, blk_insert_t flags)
 {
 	struct blk_mq_hw_ctx *hctx = rq->mq_hctx;
 
@@ -2492,7 +2485,7 @@ static void blk_mq_insert_request(struct request *rq, blk_insert_t flags)
 		 * dispatch it given we prioritize requests in hctx->dispatch.
 		 */
 		blk_mq_request_bypass_insert(rq, flags);
-	} else if (rq->rq_flags & RQF_FLUSH_SEQ) {
+	} else if (req_op(rq) == REQ_OP_FLUSH) {
 		/*
 		 * Firstly normal IO request is inserted to scheduler queue or
 		 * sw queue, meantime we add flush request to dispatch queue(
@@ -2622,7 +2615,7 @@ static void blk_mq_try_issue_directly(struct blk_mq_hw_ctx *hctx,
 		return;
 	}
 
-	if ((rq->rq_flags & RQF_ELV) || !blk_mq_get_budget_and_tag(rq)) {
+	if ((rq->rq_flags & RQF_USE_SCHED) || !blk_mq_get_budget_and_tag(rq)) {
 		blk_mq_insert_request(rq, 0);
 		blk_mq_run_hw_queue(hctx, false);
 		return;
@@ -2711,6 +2704,7 @@ static void blk_mq_dispatch_plug_list(struct blk_plug *plug, bool from_sched)
 	struct request *requeue_list = NULL;
 	struct request **requeue_lastp = &requeue_list;
 	unsigned int depth = 0;
+	bool is_passthrough = false;
 	LIST_HEAD(list);
 
 	do {
@@ -2719,7 +2713,9 @@ static void blk_mq_dispatch_plug_list(struct blk_plug *plug, bool from_sched)
 		if (!this_hctx) {
 			this_hctx = rq->mq_hctx;
 			this_ctx = rq->mq_ctx;
-		} else if (this_hctx != rq->mq_hctx || this_ctx != rq->mq_ctx) {
+			is_passthrough = blk_rq_is_passthrough(rq);
+		} else if (this_hctx != rq->mq_hctx || this_ctx != rq->mq_ctx ||
+			   is_passthrough != blk_rq_is_passthrough(rq)) {
 			rq_list_add_tail(&requeue_lastp, rq);
 			continue;
 		}
@@ -2731,7 +2727,13 @@ static void blk_mq_dispatch_plug_list(struct blk_plug *plug, bool from_sched)
 	trace_block_unplug(this_hctx->queue, depth, !from_sched);
 
 	percpu_ref_get(&this_hctx->queue->q_usage_counter);
-	if (this_hctx->queue->elevator) {
+	/* passthrough requests should never be issued to the I/O scheduler */
+	if (is_passthrough) {
+		spin_lock(&this_hctx->lock);
+		list_splice_tail_init(&list, &this_hctx->dispatch);
+		spin_unlock(&this_hctx->lock);
+		blk_mq_run_hw_queue(this_hctx, from_sched);
+	} else if (this_hctx->queue->elevator) {
 		this_hctx->queue->elevator->type->ops.insert_requests(this_hctx,
 				&list, 0);
 		blk_mq_run_hw_queue(this_hctx, from_sched);
@@ -2970,10 +2972,8 @@ void blk_mq_submit_bio(struct bio *bio)
 		return;
 	}
 
-	if (op_is_flush(bio->bi_opf)) {
-		blk_insert_flush(rq);
+	if (op_is_flush(bio->bi_opf) && blk_insert_flush(rq))
 		return;
-	}
 
 	if (plug) {
 		blk_add_rq_to_plug(plug, rq);
@@ -2981,7 +2981,7 @@ void blk_mq_submit_bio(struct bio *bio)
 	}
 
 	hctx = rq->mq_hctx;
-	if ((rq->rq_flags & RQF_ELV) ||
+	if ((rq->rq_flags & RQF_USE_SCHED) ||
 	    (hctx->dispatch_busy && (q->nr_hw_queues == 1 || !is_sync))) {
 		blk_mq_insert_request(rq, 0);
 		blk_mq_run_hw_queue(hctx, true);
@@ -4232,6 +4232,7 @@ int blk_mq_init_allocated_queue(struct blk_mq_tag_set *set,
 	blk_mq_update_poll_flag(q);
 
 	INIT_DELAYED_WORK(&q->requeue_work, blk_mq_requeue_work);
+	INIT_LIST_HEAD(&q->flush_list);
 	INIT_LIST_HEAD(&q->requeue_list);
 	spin_lock_init(&q->requeue_lock);
 
@@ -4608,9 +4609,6 @@ static bool blk_mq_elv_switch_none(struct list_head *head,
 {
 	struct blk_mq_qe_pair *qe;
 
-	if (!q->elevator)
-		return true;
-
 	qe = kmalloc(sizeof(*qe), GFP_NOIO | __GFP_NOWARN | __GFP_NORETRY);
 	if (!qe)
 		return false;
@@ -4618,6 +4616,12 @@ static bool blk_mq_elv_switch_none(struct list_head *head,
 	/* q->elevator needs protection from ->sysfs_lock */
 	mutex_lock(&q->sysfs_lock);
 
+	/* the check has to be done with holding sysfs_lock */
+	if (!q->elevator) {
+		kfree(qe);
+		goto unlock;
+	}
+
 	INIT_LIST_HEAD(&qe->node);
 	qe->q = q;
 	qe->type = q->elevator->type;
@@ -4625,6 +4629,7 @@ static bool blk_mq_elv_switch_none(struct list_head *head,
 	__elevator_get(qe->type);
 	list_add(&qe->node, head);
 	elevator_disable(q);
+unlock:
 	mutex_unlock(&q->sysfs_lock);
 
 	return true;