Merge tag 'block-5.14-2021-07-08' of git://git.kernel.dk/linux-block

Pull more block updates from Jens Axboe:
 "A combination of changes that ended up depending on both the driver
  and core branch (and/or the IDE removal), and a few late arriving
  fixes. In detail:

   - Fix io ticks wrap-around issue (Chunguang)

   - nvme-tcp sock locking fix (Maurizio)

   - s390-dasd fixes (Kees, Christoph)

   - blk_execute_rq polling support (Keith)

   - blk-cgroup RCU iteration fix (Yu)

   - nbd backend ID addition (Prasanna)

   - Partition deletion fix (Yufen)

   - Use blk_mq_alloc_disk for mmc, mtip32xx, ubd (Christoph)

   - Removal of now dead block request types due to IDE removal
     (Christoph)

   - Loop probing and control device cleanups (Christoph)

   - Device uevent fix (Christoph)

   - Misc cleanups/fixes (Tetsuo, Christoph)"

* tag 'block-5.14-2021-07-08' of git://git.kernel.dk/linux-block: (34 commits)
  blk-cgroup: prevent rcu_sched detected stalls warnings while iterating blkgs
  block: fix the problem of io_ticks becoming smaller
  nvme-tcp: can't set sk_user_data without write_lock
  loop: remove unused variable in loop_set_status()
  block: remove the bdgrab in blk_drop_partitions
  block: grab a device refcount in disk_uevent
  s390/dasd: Avoid field over-reading memcpy()
  dasd: unexport dasd_set_target_state
  block: check disk exist before trying to add partition
  ubd: remove dead code in ubd_setup_common
  nvme: use return value from blk_execute_rq()
  block: return errors from blk_execute_rq()
  nvme: use blk_execute_rq() for passthrough commands
  block: support polling through blk_execute_rq
  block: remove REQ_OP_SCSI_{IN,OUT}
  block: mark blk_mq_init_queue_data static
  loop: rewrite loop_exit using idr_for_each_entry
  loop: split loop_lookup
  loop: don't allow deleting an unspecified loop device
  loop: move loop_ctl_mutex locking into loop_add
  ...

9 files changed, 63 insertions, 27 deletions

diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index 7b06a5fa3cac..575d7a2e7203 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -56,6 +56,8 @@ static LIST_HEAD(all_blkcgs);		/* protected by blkcg_pol_mutex */
 bool blkcg_debug_stats = false;
 static struct workqueue_struct *blkcg_punt_bio_wq;
 
+#define BLKG_DESTROY_BATCH_SIZE  64
+
 static bool blkcg_policy_enabled(struct request_queue *q,
 				 const struct blkcg_policy *pol)
 {
@@ -422,7 +424,9 @@ static void blkg_destroy(struct blkcg_gq *blkg)
 static void blkg_destroy_all(struct request_queue *q)
 {
 	struct blkcg_gq *blkg, *n;
+	int count = BLKG_DESTROY_BATCH_SIZE;
 
+restart:
 	spin_lock_irq(&q->queue_lock);
 	list_for_each_entry_safe(blkg, n, &q->blkg_list, q_node) {
 		struct blkcg *blkcg = blkg->blkcg;
@@ -430,6 +434,17 @@ static void blkg_destroy_all(struct request_queue *q)
 		spin_lock(&blkcg->lock);
 		blkg_destroy(blkg);
 		spin_unlock(&blkcg->lock);
+
+		/*
+		 * in order to avoid holding the spin lock for too long, release
+		 * it when a batch of blkgs are destroyed.
+		 */
+		if (!(--count)) {
+			count = BLKG_DESTROY_BATCH_SIZE;
+			spin_unlock_irq(&q->queue_lock);
+			cond_resched();
+			goto restart;
+		}
 	}
 
 	q->root_blkg = NULL;
diff --git a/block/blk-core.c b/block/blk-core.c
index 514838ccab2d..04477697ee4b 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -142,8 +142,6 @@ static const char *const blk_op_name[] = {
 	REQ_OP_NAME(ZONE_APPEND),
 	REQ_OP_NAME(WRITE_SAME),
 	REQ_OP_NAME(WRITE_ZEROES),
-	REQ_OP_NAME(SCSI_IN),
-	REQ_OP_NAME(SCSI_OUT),
 	REQ_OP_NAME(DRV_IN),
 	REQ_OP_NAME(DRV_OUT),
 };
@@ -1243,7 +1241,7 @@ static void update_io_ticks(struct block_device *part, unsigned long now,
 	unsigned long stamp;
 again:
 	stamp = READ_ONCE(part->bd_stamp);
-	if (unlikely(stamp != now)) {
+	if (unlikely(time_after(now, stamp))) {
 		if (likely(cmpxchg(&part->bd_stamp, stamp, now) == stamp))
 			__part_stat_add(part, io_ticks, end ? now - stamp : 1);
 	}
diff --git a/block/blk-exec.c b/block/blk-exec.c
index beae70a0e5e5..d6cd501c0d34 100644
--- a/block/blk-exec.c
+++ b/block/blk-exec.c
@@ -21,7 +21,7 @@ static void blk_end_sync_rq(struct request *rq, blk_status_t error)
 {
 	struct completion *waiting = rq->end_io_data;
 
-	rq->end_io_data = NULL;
+	rq->end_io_data = (void *)(uintptr_t)error;
 
 	/*
 	 * complete last, if this is a stack request the process (and thus
@@ -63,6 +63,19 @@ void blk_execute_rq_nowait(struct gendisk *bd_disk, struct request *rq,
 }
 EXPORT_SYMBOL_GPL(blk_execute_rq_nowait);
 
+static bool blk_rq_is_poll(struct request *rq)
+{
+	return rq->mq_hctx && rq->mq_hctx->type == HCTX_TYPE_POLL;
+}
+
+static void blk_rq_poll_completion(struct request *rq, struct completion *wait)
+{
+	do {
+		blk_poll(rq->q, request_to_qc_t(rq->mq_hctx, rq), true);
+		cond_resched();
+	} while (!completion_done(wait));
+}
+
 /**
  * blk_execute_rq - insert a request into queue for execution
  * @bd_disk:	matching gendisk
@@ -72,8 +85,9 @@ EXPORT_SYMBOL_GPL(blk_execute_rq_nowait);
  * Description:
  *    Insert a fully prepared request at the back of the I/O scheduler queue
  *    for execution and wait for completion.
+ * Return: The blk_status_t result provided to blk_mq_end_request().
  */
-void blk_execute_rq(struct gendisk *bd_disk, struct request *rq, int at_head)
+blk_status_t blk_execute_rq(struct gendisk *bd_disk, struct request *rq, int at_head)
 {
 	DECLARE_COMPLETION_ONSTACK(wait);
 	unsigned long hang_check;
@@ -83,9 +97,14 @@ void blk_execute_rq(struct gendisk *bd_disk, struct request *rq, int at_head)
 
 	/* Prevent hang_check timer from firing at us during very long I/O */
 	hang_check = sysctl_hung_task_timeout_secs;
-	if (hang_check)
+
+	if (blk_rq_is_poll(rq))
+		blk_rq_poll_completion(rq, &wait);
+	else if (hang_check)
 		while (!wait_for_completion_io_timeout(&wait, hang_check * (HZ/2)));
 	else
 		wait_for_completion_io(&wait);
+
+	return (blk_status_t)(uintptr_t)rq->end_io_data;
 }
 EXPORT_SYMBOL(blk_execute_rq);
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 2e9fd0ec63d7..2c4ac51e54eb 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -3109,7 +3109,7 @@ void blk_mq_release(struct request_queue *q)
 	blk_mq_sysfs_deinit(q);
 }
 
-struct request_queue *blk_mq_init_queue_data(struct blk_mq_tag_set *set,
+static struct request_queue *blk_mq_init_queue_data(struct blk_mq_tag_set *set,
 		void *queuedata)
 {
 	struct request_queue *q;
@@ -3126,7 +3126,6 @@ struct request_queue *blk_mq_init_queue_data(struct blk_mq_tag_set *set,
 	}
 	return q;
 }
-EXPORT_SYMBOL_GPL(blk_mq_init_queue_data);
 
 struct request_queue *blk_mq_init_queue(struct blk_mq_tag_set *set)
 {
diff --git a/block/bsg-lib.c b/block/bsg-lib.c
index cf1811261722..a89d80102304 100644
--- a/block/bsg-lib.c
+++ b/block/bsg-lib.c
@@ -45,7 +45,7 @@ static int bsg_transport_fill_hdr(struct request *rq, struct sg_io_v4 *hdr,
 		return PTR_ERR(job->request);
 
 	if (hdr->dout_xfer_len && hdr->din_xfer_len) {
-		job->bidi_rq = blk_get_request(rq->q, REQ_OP_SCSI_IN, 0);
+		job->bidi_rq = blk_get_request(rq->q, REQ_OP_DRV_IN, 0);
 		if (IS_ERR(job->bidi_rq)) {
 			ret = PTR_ERR(job->bidi_rq);
 			goto out;
diff --git a/block/bsg.c b/block/bsg.c
index 33e3f82ed03a..1f196563ae6c 100644
--- a/block/bsg.c
+++ b/block/bsg.c
@@ -154,7 +154,7 @@ static int bsg_sg_io(struct request_queue *q, fmode_t mode, void __user *uarg)
 		return ret;
 
 	rq = blk_get_request(q, hdr.dout_xfer_len ?
-			REQ_OP_SCSI_OUT : REQ_OP_SCSI_IN, 0);
+			REQ_OP_DRV_OUT : REQ_OP_DRV_IN, 0);
 	if (IS_ERR(rq))
 		return PTR_ERR(rq);
 
diff --git a/block/genhd.c b/block/genhd.c
index 79aa40b4c39c..af4d2ab4a633 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -365,12 +365,12 @@ void disk_uevent(struct gendisk *disk, enum kobject_action action)
 	xa_for_each(&disk->part_tbl, idx, part) {
 		if (bdev_is_partition(part) && !bdev_nr_sectors(part))
 			continue;
-		if (!bdgrab(part))
+		if (!kobject_get_unless_zero(&part->bd_device.kobj))
 			continue;
 
 		rcu_read_unlock();
 		kobject_uevent(bdev_kobj(part), action);
-		bdput(part);
+		put_device(&part->bd_device);
 		rcu_read_lock();
 	}
 	rcu_read_unlock();
diff --git a/block/partitions/core.c b/block/partitions/core.c
index 347c56a51d87..4230d4f71879 100644
--- a/block/partitions/core.c
+++ b/block/partitions/core.c
@@ -453,17 +453,26 @@ int bdev_add_partition(struct block_device *bdev, int partno,
 		sector_t start, sector_t length)
 {
 	struct block_device *part;
+	struct gendisk *disk = bdev->bd_disk;
+	int ret;
 
-	mutex_lock(&bdev->bd_disk->open_mutex);
-	if (partition_overlaps(bdev->bd_disk, start, length, -1)) {
-		mutex_unlock(&bdev->bd_disk->open_mutex);
-		return -EBUSY;
+	mutex_lock(&disk->open_mutex);
+	if (!(disk->flags & GENHD_FL_UP)) {
+		ret = -ENXIO;
+		goto out;
+	}
+
+	if (partition_overlaps(disk, start, length, -1)) {
+		ret = -EBUSY;
+		goto out;
 	}
 
-	part = add_partition(bdev->bd_disk, partno, start, length,
+	part = add_partition(disk, partno, start, length,
 			ADDPART_FLAG_NONE, NULL);
-	mutex_unlock(&bdev->bd_disk->open_mutex);
-	return PTR_ERR_OR_ZERO(part);
+	ret = PTR_ERR_OR_ZERO(part);
+out:
+	mutex_unlock(&disk->open_mutex);
+	return ret;
 }
 
 int bdev_del_partition(struct block_device *bdev, int partno)
@@ -537,12 +546,8 @@ void blk_drop_partitions(struct gendisk *disk)
 
 	lockdep_assert_held(&disk->open_mutex);
 
-	xa_for_each_start(&disk->part_tbl, idx, part, 1) {
-		if (!bdgrab(part))
-			continue;
+	xa_for_each_start(&disk->part_tbl, idx, part, 1)
 		delete_partition(part);
-		bdput(part);
-	}
 }
 
 static bool blk_add_partition(struct gendisk *disk,
diff --git a/block/scsi_ioctl.c b/block/scsi_ioctl.c
index fa6df11b8bdd..d247431a6853 100644
--- a/block/scsi_ioctl.c
+++ b/block/scsi_ioctl.c
@@ -313,7 +313,7 @@ static int sg_io(struct request_queue *q, struct gendisk *bd_disk,
 		at_head = 1;
 
 	ret = -ENOMEM;
-	rq = blk_get_request(q, writing ? REQ_OP_SCSI_OUT : REQ_OP_SCSI_IN, 0);
+	rq = blk_get_request(q, writing ? REQ_OP_DRV_OUT : REQ_OP_DRV_IN, 0);
 	if (IS_ERR(rq))
 		return PTR_ERR(rq);
 	req = scsi_req(rq);
@@ -435,7 +435,7 @@ int sg_scsi_ioctl(struct request_queue *q, struct gendisk *disk, fmode_t mode,
 
 	}
 
-	rq = blk_get_request(q, in_len ? REQ_OP_SCSI_OUT : REQ_OP_SCSI_IN, 0);
+	rq = blk_get_request(q, in_len ? REQ_OP_DRV_OUT : REQ_OP_DRV_IN, 0);
 	if (IS_ERR(rq)) {
 		err = PTR_ERR(rq);
 		goto error_free_buffer;
@@ -524,7 +524,7 @@ static int __blk_send_generic(struct request_queue *q, struct gendisk *bd_disk,
 	struct request *rq;
 	int err;
 
-	rq = blk_get_request(q, REQ_OP_SCSI_OUT, 0);
+	rq = blk_get_request(q, REQ_OP_DRV_OUT, 0);
 	if (IS_ERR(rq))
 		return PTR_ERR(rq);
 	rq->timeout = BLK_DEFAULT_SG_TIMEOUT;