Merge tag 'for-5.18/block-2022-03-18' of git://git.kernel.dk/linux-block

Pull block updates from Jens Axboe:

 - BFQ cleanups and fixes (Yu, Zhang, Yahu, Paolo)

 - blk-rq-qos completion fix (Tejun)

 - blk-cgroup merge fix (Tejun)

 - Add offline error return value to distinguish it from an IO error on
   the device (Song)

 - IO stats fixes (Zhang, Christoph)

 - blkcg refcount fixes (Ming, Yu)

 - Fix for indefinite dispatch loop softlockup (Shin'ichiro)

 - blk-mq hardware queue management improvements (Ming)

 - sbitmap dead code removal (Ming, John)

 - Plugging merge improvements (me)

 - Show blk-crypto capabilities in sysfs (Eric)

 - Multiple delayed queue run improvement (David)

 - Block throttling fixes (Ming)

 - Start deprecating auto module loading based on dev_t (Christoph)

 - bio allocation improvements (Christoph, Chaitanya)

 - Get rid of bio_devname (Christoph)

 - bio clone improvements (Christoph)

 - Block plugging improvements (Christoph)

 - Get rid of genhd.h header (Christoph)

 - Ensure drivers use appropriate flush helpers (Christoph)

 - Refcounting improvements (Christoph)

 - Queue initialization and teardown improvements (Ming, Christoph)

 - Misc fixes/improvements (Barry, Chaitanya, Colin, Dan, Jiapeng,
   Lukas, Nian, Yang, Eric, Chengming)

* tag 'for-5.18/block-2022-03-18' of git://git.kernel.dk/linux-block: (127 commits)
  block: cancel all throttled bios in del_gendisk()
  block: let blkcg_gq grab request queue's refcnt
  block: avoid use-after-free on throttle data
  block: limit request dispatch loop duration
  block/bfq-iosched: Fix spelling mistake "tenative" -> "tentative"
  sr: simplify the local variable initialization in sr_block_open()
  block: don't merge across cgroup boundaries if blkcg is enabled
  block: fix rq-qos breakage from skipping rq_qos_done_bio()
  block: flush plug based on hardware and software queue order
  block: ensure plug merging checks the correct queue at least once
  block: move rq_qos_exit() into disk_release()
  block: do more work in elevator_exit
  block: move blk_exit_queue into disk_release
  block: move q_usage_counter release into blk_queue_release
  block: don't remove hctx debugfs dir from blk_mq_exit_queue
  block: move blkcg initialization/destroy into disk allocation/release handler
  sr: implement ->free_disk to simplify refcounting
  sd: implement ->free_disk to simplify refcounting
  sd: delay calling free_opal_dev
  sd: call sd_zbc_release_disk before releasing the scsi_device reference
  ...

1 files changed, 62 insertions, 5 deletions

diff --git a/block/genhd.c b/block/genhd.c
index 9eca1f7d35c9..37eb41ee4086 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -8,7 +8,6 @@
 #include <linux/module.h>
 #include <linux/ctype.h>
 #include <linux/fs.h>
-#include <linux/genhd.h>
 #include <linux/kdev_t.h>
 #include <linux/kernel.h>
 #include <linux/blkdev.h>
@@ -26,10 +25,12 @@
 #include <linux/pm_runtime.h>
 #include <linux/badblocks.h>
 #include <linux/part_stat.h>
+#include "blk-throttle.h"
 
 #include "blk.h"
 #include "blk-mq-sched.h"
 #include "blk-rq-qos.h"
+#include "blk-cgroup.h"
 
 static struct kobject *block_depr;
 
@@ -185,7 +186,9 @@ static struct blk_major_name {
 	struct blk_major_name *next;
 	int major;
 	char name[16];
+#ifdef CONFIG_BLOCK_LEGACY_AUTOLOAD
 	void (*probe)(dev_t devt);
+#endif
 } *major_names[BLKDEV_MAJOR_HASH_SIZE];
 static DEFINE_MUTEX(major_names_lock);
 static DEFINE_SPINLOCK(major_names_spinlock);
@@ -275,7 +278,9 @@ int __register_blkdev(unsigned int major, const char *name,
 	}
 
 	p->major = major;
+#ifdef CONFIG_BLOCK_LEGACY_AUTOLOAD
 	p->probe = probe;
+#endif
 	strlcpy(p->name, name, sizeof(p->name));
 	p->next = NULL;
 	index = major_to_index(major);
@@ -523,6 +528,7 @@ int __must_check device_add_disk(struct device *parent, struct gendisk *disk,
 
 	disk_update_readahead(disk);
 	disk_add_events(disk);
+	set_bit(GD_ADDED, &disk->state);
 	return 0;
 
 out_unregister_bdi:
@@ -636,7 +642,8 @@ void del_gendisk(struct gendisk *disk)
 
 	blk_mq_freeze_queue_wait(q);
 
-	rq_qos_exit(q);
+	blk_throtl_cancel_bios(disk->queue);
+
 	blk_sync_queue(q);
 	blk_flush_integrity();
 	/*
@@ -693,6 +700,7 @@ static ssize_t disk_badblocks_store(struct device *dev,
 	return badblocks_store(disk->bb, page, len, 0);
 }
 
+#ifdef CONFIG_BLOCK_LEGACY_AUTOLOAD
 void blk_request_module(dev_t devt)
 {
 	unsigned int major = MAJOR(devt);
@@ -712,6 +720,7 @@ void blk_request_module(dev_t devt)
 		/* Make old-style 2.4 aliases work */
 		request_module("block-major-%d", MAJOR(devt));
 }
+#endif /* CONFIG_BLOCK_LEGACY_AUTOLOAD */
 
 /*
  * print a full list of all partitions - intended for places where the root
@@ -927,12 +936,17 @@ ssize_t part_stat_show(struct device *dev,
 	struct disk_stats stat;
 	unsigned int inflight;
 
-	part_stat_read_all(bdev, &stat);
 	if (queue_is_mq(q))
 		inflight = blk_mq_in_flight(q, bdev);
 	else
 		inflight = part_in_flight(bdev);
 
+	if (inflight) {
+		part_stat_lock();
+		update_io_ticks(bdev, jiffies, true);
+		part_stat_unlock();
+	}
+	part_stat_read_all(bdev, &stat);
 	return sprintf(buf,
 		"%8lu %8lu %8llu %8u "
 		"%8lu %8lu %8llu %8u "
@@ -1100,6 +1114,31 @@ static const struct attribute_group *disk_attr_groups[] = {
 	NULL
 };
 
+static void disk_release_mq(struct request_queue *q)
+{
+	blk_mq_cancel_work_sync(q);
+
+	/*
+	 * There can't be any non non-passthrough bios in flight here, but
+	 * requests stay around longer, including passthrough ones so we
+	 * still need to freeze the queue here.
+	 */
+	blk_mq_freeze_queue(q);
+
+	/*
+	 * Since the I/O scheduler exit code may access cgroup information,
+	 * perform I/O scheduler exit before disassociating from the block
+	 * cgroup controller.
+	 */
+	if (q->elevator) {
+		mutex_lock(&q->sysfs_lock);
+		elevator_exit(q);
+		mutex_unlock(&q->sysfs_lock);
+	}
+	rq_qos_exit(q);
+	__blk_mq_unfreeze_queue(q, true);
+}
+
 /**
  * disk_release - releases all allocated resources of the gendisk
  * @dev: the device representing this disk
@@ -1121,13 +1160,21 @@ static void disk_release(struct device *dev)
 	might_sleep();
 	WARN_ON_ONCE(disk_live(disk));
 
-	blk_mq_cancel_work_sync(disk->queue);
+	if (queue_is_mq(disk->queue))
+		disk_release_mq(disk->queue);
+
+	blkcg_exit_queue(disk->queue);
 
 	disk_release_events(disk);
 	kfree(disk->random);
 	xa_destroy(&disk->part_tbl);
+
 	disk->queue->disk = NULL;
 	blk_put_queue(disk->queue);
+
+	if (test_bit(GD_ADDED, &disk->state) && disk->fops->free_disk)
+		disk->fops->free_disk(disk);
+
 	iput(disk->part0->bd_inode);	/* frees the disk */
 }
 
@@ -1188,12 +1235,17 @@ static int diskstats_show(struct seq_file *seqf, void *v)
 	xa_for_each(&gp->part_tbl, idx, hd) {
 		if (bdev_is_partition(hd) && !bdev_nr_sectors(hd))
 			continue;
-		part_stat_read_all(hd, &stat);
 		if (queue_is_mq(gp->queue))
 			inflight = blk_mq_in_flight(gp->queue, hd);
 		else
 			inflight = part_in_flight(hd);
 
+		if (inflight) {
+			part_stat_lock();
+			update_io_ticks(hd, jiffies, true);
+			part_stat_unlock();
+		}
+		part_stat_read_all(hd, &stat);
 		seq_printf(seqf, "%4d %7d %pg "
 			   "%lu %lu %lu %u "
 			   "%lu %lu %lu %u "
@@ -1322,6 +1374,9 @@ struct gendisk *__alloc_disk_node(struct request_queue *q, int node_id,
 	if (xa_insert(&disk->part_tbl, 0, disk->part0, GFP_KERNEL))
 		goto out_destroy_part_tbl;
 
+	if (blkcg_init_queue(q))
+		goto out_erase_part0;
+
 	rand_initialize_disk(disk);
 	disk_to_dev(disk)->class = &block_class;
 	disk_to_dev(disk)->type = &disk_type;
@@ -1334,6 +1389,8 @@ struct gendisk *__alloc_disk_node(struct request_queue *q, int node_id,
 #endif
 	return disk;
 
+out_erase_part0:
+	xa_erase(&disk->part_tbl, 0);
 out_destroy_part_tbl:
 	xa_destroy(&disk->part_tbl);
 	disk->part0->bd_disk = NULL;