Merge tag 'block-5.17-2022-01-28' of git://git.kernel.dk/linux-block

Pull block fixes from Jens Axboe:

 - NVMe pull request
      - add the IGNORE_DEV_SUBNQN quirk for Intel P4500/P4600 SSDs (Wu
        Zheng)
      - remove the unneeded ret variable in nvmf_dev_show (Changcheng
        Deng)

 - Fix for a hang regression introduced with a patch in the merge
   window, where low queue depth devices would not always get woken
   correctly (Laibin)

 - Small series fixing an IO accounting issue with bio backed dm devices
   (Mike, Yu)

* tag 'block-5.17-2022-01-28' of git://git.kernel.dk/linux-block:
  dm: properly fix redundant bio-based IO accounting
  dm: revert partial fix for redundant bio-based IO accounting
  block: add bio_start_io_acct_time() to control start_time
  blk-mq: Fix wrong wakeup batch configuration which will cause hang
  nvme-fabrics: remove the unneeded ret variable in nvmf_dev_show
  nvme-pci: add the IGNORE_DEV_SUBNQN quirk for Intel P4500/P4600 SSDs
  blk-mq: fix missing blk_account_io_done() in error path
  block: fix memory leak in disk_register_independent_access_ranges

Author: torvalds

block/blk-core.c

@@ -1061,20 +1061,32 @@ void update_io_ticks(struct block_device *part, unsigned long now, bool end)
 }
 
 static unsigned long __part_start_io_acct(struct block_device *part,
-					  unsigned int sectors, unsigned int op)
+					  unsigned int sectors, unsigned int op,
+					  unsigned long start_time)
 {
 	const int sgrp = op_stat_group(op);
-	unsigned long now = READ_ONCE(jiffies);
 
 	part_stat_lock();
-	update_io_ticks(part, now, false);
+	update_io_ticks(part, start_time, false);
 	part_stat_inc(part, ios[sgrp]);
 	part_stat_add(part, sectors[sgrp], sectors);
 	part_stat_local_inc(part, in_flight[op_is_write(op)]);
 	part_stat_unlock();
 
-	return now;
+	return start_time;
+}
+
+/**
+ * bio_start_io_acct_time - start I/O accounting for bio based drivers
+ * @bio:	bio to start account for
+ * @start_time:	start time that should be passed back to bio_end_io_acct().
+ */
+void bio_start_io_acct_time(struct bio *bio, unsigned long start_time)
+{
+	__part_start_io_acct(bio->bi_bdev, bio_sectors(bio),
+			     bio_op(bio), start_time);
 }
+EXPORT_SYMBOL_GPL(bio_start_io_acct_time);
 
 /**
  * bio_start_io_acct - start I/O accounting for bio based drivers
@@ -1084,14 +1096,15 @@ static unsigned long __part_start_io_acct(struct block_device *part,
  */
 unsigned long bio_start_io_acct(struct bio *bio)
 {
-	return __part_start_io_acct(bio->bi_bdev, bio_sectors(bio), bio_op(bio));
+	return __part_start_io_acct(bio->bi_bdev, bio_sectors(bio),
+				    bio_op(bio), jiffies);
 }
 EXPORT_SYMBOL_GPL(bio_start_io_acct);
 
 unsigned long disk_start_io_acct(struct gendisk *disk, unsigned int sectors,
 				 unsigned int op)
 {
-	return __part_start_io_acct(disk->part0, sectors, op);
+	return __part_start_io_acct(disk->part0, sectors, op, jiffies);
 }
 EXPORT_SYMBOL(disk_start_io_acct);
 

block/blk-ia-ranges.c

@@ -144,7 +144,7 @@ int disk_register_independent_access_ranges(struct gendisk *disk,
 				   &q->kobj, "%s", "independent_access_ranges");
 	if (ret) {
 		q->ia_ranges = NULL;
-		kfree(iars);
+		kobject_put(&iars->kobj);
 		return ret;
 	}
 

block/blk-mq.c

@@ -2922,6 +2922,8 @@ blk_status_t blk_insert_cloned_request(struct request_queue *q, struct request *
 	 */
 	blk_mq_run_dispatch_ops(rq->q,
 			ret = blk_mq_request_issue_directly(rq, true));
+	if (ret)
+		blk_account_io_done(rq, ktime_get_ns());
 	return ret;
 }
 EXPORT_SYMBOL_GPL(blk_insert_cloned_request);

drivers/md/dm.c

@@ -489,7 +489,7 @@ static void start_io_acct(struct dm_io *io)
 	struct mapped_device *md = io->md;
 	struct bio *bio = io->orig_bio;
 
-	io->start_time = bio_start_io_acct(bio);
+	bio_start_io_acct_time(bio, io->start_time);
 	if (unlikely(dm_stats_used(&md->stats)))
 		dm_stats_account_io(&md->stats, bio_data_dir(bio),
 				    bio->bi_iter.bi_sector, bio_sectors(bio),
@@ -535,7 +535,7 @@ static struct dm_io *alloc_io(struct mapped_device *md, struct bio *bio)
 	io->md = md;
 	spin_lock_init(&io->endio_lock);
 
-	start_io_acct(io);
+	io->start_time = jiffies;
 
 	return io;
 }
@@ -1442,9 +1442,6 @@ static void init_clone_info(struct clone_info *ci, struct mapped_device *md,
 	ci->sector = bio->bi_iter.bi_sector;
 }
 
-#define __dm_part_stat_sub(part, field, subnd)	\
-	(part_stat_get(part, field) -= (subnd))
-
 /*
  * Entry point to split a bio into clones and submit them to the targets.
  */
@@ -1480,23 +1477,12 @@ static void __split_and_process_bio(struct mapped_device *md,
 						  GFP_NOIO, &md->queue->bio_split);
 			ci.io->orig_bio = b;
 
-			/*
-			 * Adjust IO stats for each split, otherwise upon queue
-			 * reentry there will be redundant IO accounting.
-			 * NOTE: this is a stop-gap fix, a proper fix involves
-			 * significant refactoring of DM core's bio splitting
-			 * (by eliminating DM's splitting and just using bio_split)
-			 */
-			part_stat_lock();
-			__dm_part_stat_sub(dm_disk(md)->part0,
-					   sectors[op_stat_group(bio_op(bio))], ci.sector_count);
-			part_stat_unlock();
-
 			bio_chain(b, bio);
 			trace_block_split(b, bio->bi_iter.bi_sector);
 			submit_bio_noacct(bio);
 		}
 	}
+	start_io_acct(ci.io);
 
 	/* drop the extra reference count */
 	dm_io_dec_pending(ci.io, errno_to_blk_status(error));

drivers/nvme/host/fabrics.c

@@ -1092,7 +1092,6 @@ static void __nvmf_concat_opt_tokens(struct seq_file *seq_file)
 static int nvmf_dev_show(struct seq_file *seq_file, void *private)
 {
 	struct nvme_ctrl *ctrl;
-	int ret = 0;
 
 	mutex_lock(&nvmf_dev_mutex);
 	ctrl = seq_file->private;
@@ -1106,7 +1105,7 @@ static int nvmf_dev_show(struct seq_file *seq_file, void *private)
 
 out_unlock:
 	mutex_unlock(&nvmf_dev_mutex);
-	return ret;
+	return 0;
 }
 
 static int nvmf_dev_open(struct inode *inode, struct file *file)

drivers/nvme/host/pci.c

@@ -3391,7 +3391,8 @@ static const struct pci_device_id nvme_id_table[] = {
 				NVME_QUIRK_DEALLOCATE_ZEROES, },
 	{ PCI_VDEVICE(INTEL, 0x0a54),	/* Intel P4500/P4600 */
 		.driver_data = NVME_QUIRK_STRIPE_SIZE |
-				NVME_QUIRK_DEALLOCATE_ZEROES, },
+				NVME_QUIRK_DEALLOCATE_ZEROES |
+				NVME_QUIRK_IGNORE_DEV_SUBNQN, },
 	{ PCI_VDEVICE(INTEL, 0x0a55),	/* Dell Express Flash P4600 */
 		.driver_data = NVME_QUIRK_STRIPE_SIZE |
 				NVME_QUIRK_DEALLOCATE_ZEROES, },

include/linux/blkdev.h

@@ -1258,6 +1258,7 @@ unsigned long disk_start_io_acct(struct gendisk *disk, unsigned int sectors,
 void disk_end_io_acct(struct gendisk *disk, unsigned int op,
 		unsigned long start_time);
 
+void bio_start_io_acct_time(struct bio *bio, unsigned long start_time);
 unsigned long bio_start_io_acct(struct bio *bio);
 void bio_end_io_acct_remapped(struct bio *bio, unsigned long start_time,
 		struct block_device *orig_bdev);

lib/sbitmap.c

@@ -488,9 +488,13 @@ void sbitmap_queue_recalculate_wake_batch(struct sbitmap_queue *sbq,
 					    unsigned int users)
 {
 	unsigned int wake_batch;
+	unsigned int min_batch;
+	unsigned int depth = (sbq->sb.depth + users - 1) / users;
 
-	wake_batch = clamp_val((sbq->sb.depth + users - 1) /
-			users, 4, SBQ_WAKE_BATCH);
+	min_batch = sbq->sb.depth >= (4 * SBQ_WAIT_QUEUES) ? 4 : 1;
+
+	wake_batch = clamp_val(depth / SBQ_WAIT_QUEUES,
+			min_batch, SBQ_WAKE_BATCH);
 	__sbitmap_queue_update_wake_batch(sbq, wake_batch);
 }
 EXPORT_SYMBOL_GPL(sbitmap_queue_recalculate_wake_batch);