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, 69 insertions, 118 deletions

diff --git a/block/genhd.c b/block/genhd.c
index 1cb489b927d5..3d287b32d50d 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -25,8 +25,9 @@
 #include <linux/pm_runtime.h>
 #include <linux/badblocks.h>
 #include <linux/part_stat.h>
-#include "blk-throttle.h"
+#include <linux/blktrace_api.h>
 
+#include "blk-throttle.h"
 #include "blk.h"
 #include "blk-mq-sched.h"
 #include "blk-rq-qos.h"
@@ -253,7 +254,7 @@ int __register_blkdev(unsigned int major, const char *name,
 #ifdef CONFIG_BLOCK_LEGACY_AUTOLOAD
 	p->probe = probe;
 #endif
-	strlcpy(p->name, name, sizeof(p->name));
+	strscpy(p->name, name, sizeof(p->name));
 	p->next = NULL;
 	index = major_to_index(major);
 
@@ -318,18 +319,6 @@ void blk_free_ext_minor(unsigned int minor)
 	ida_free(&ext_devt_ida, minor);
 }
 
-static char *bdevt_str(dev_t devt, char *buf)
-{
-	if (MAJOR(devt) <= 0xff && MINOR(devt) <= 0xff) {
-		char tbuf[BDEVT_SIZE];
-		snprintf(tbuf, BDEVT_SIZE, "%02x%02x", MAJOR(devt), MINOR(devt));
-		snprintf(buf, BDEVT_SIZE, "%-9s", tbuf);
-	} else
-		snprintf(buf, BDEVT_SIZE, "%03x:%05x", MAJOR(devt), MINOR(devt));
-
-	return buf;
-}
-
 void disk_uevent(struct gendisk *disk, enum kobject_action action)
 {
 	struct block_device *part;
@@ -351,7 +340,7 @@ void disk_uevent(struct gendisk *disk, enum kobject_action action)
 }
 EXPORT_SYMBOL_GPL(disk_uevent);
 
-int disk_scan_partitions(struct gendisk *disk, fmode_t mode)
+int disk_scan_partitions(struct gendisk *disk, blk_mode_t mode)
 {
 	struct block_device *bdev;
 	int ret = 0;
@@ -369,18 +358,20 @@ int disk_scan_partitions(struct gendisk *disk, fmode_t mode)
 	 * synchronize with other exclusive openers and other partition
 	 * scanners.
 	 */
-	if (!(mode & FMODE_EXCL)) {
-		ret = bd_prepare_to_claim(disk->part0, disk_scan_partitions);
+	if (!(mode & BLK_OPEN_EXCL)) {
+		ret = bd_prepare_to_claim(disk->part0, disk_scan_partitions,
+					  NULL);
 		if (ret)
 			return ret;
 	}
 
 	set_bit(GD_NEED_PART_SCAN, &disk->state);
-	bdev = blkdev_get_by_dev(disk_devt(disk), mode & ~FMODE_EXCL, NULL);
+	bdev = blkdev_get_by_dev(disk_devt(disk), mode & ~BLK_OPEN_EXCL, NULL,
+				 NULL);
 	if (IS_ERR(bdev))
 		ret =  PTR_ERR(bdev);
 	else
-		blkdev_put(bdev, mode & ~FMODE_EXCL);
+		blkdev_put(bdev, NULL);
 
 	/*
 	 * If blkdev_get_by_dev() failed early, GD_NEED_PART_SCAN is still set,
@@ -388,7 +379,7 @@ int disk_scan_partitions(struct gendisk *disk, fmode_t mode)
 	 * creat partition for underlying disk.
 	 */
 	clear_bit(GD_NEED_PART_SCAN, &disk->state);
-	if (!(mode & FMODE_EXCL))
+	if (!(mode & BLK_OPEN_EXCL))
 		bd_abort_claiming(disk->part0, disk_scan_partitions);
 	return ret;
 }
@@ -516,7 +507,7 @@ int __must_check device_add_disk(struct device *parent, struct gendisk *disk,
 
 		bdev_add(disk->part0, ddev->devt);
 		if (get_capacity(disk))
-			disk_scan_partitions(disk, FMODE_READ);
+			disk_scan_partitions(disk, BLK_OPEN_READ);
 
 		/*
 		 * Announce the disk and partitions after all partitions are
@@ -563,6 +554,28 @@ out_exit_elevator:
 }
 EXPORT_SYMBOL(device_add_disk);
 
+static void blk_report_disk_dead(struct gendisk *disk)
+{
+	struct block_device *bdev;
+	unsigned long idx;
+
+	rcu_read_lock();
+	xa_for_each(&disk->part_tbl, idx, bdev) {
+		if (!kobject_get_unless_zero(&bdev->bd_device.kobj))
+			continue;
+		rcu_read_unlock();
+
+		mutex_lock(&bdev->bd_holder_lock);
+		if (bdev->bd_holder_ops && bdev->bd_holder_ops->mark_dead)
+			bdev->bd_holder_ops->mark_dead(bdev);
+		mutex_unlock(&bdev->bd_holder_lock);
+
+		put_device(&bdev->bd_device);
+		rcu_read_lock();
+	}
+	rcu_read_unlock();
+}
+
 /**
  * blk_mark_disk_dead - mark a disk as dead
  * @disk: disk to mark as dead
@@ -572,13 +585,26 @@ EXPORT_SYMBOL(device_add_disk);
  */
 void blk_mark_disk_dead(struct gendisk *disk)
 {
-	set_bit(GD_DEAD, &disk->state);
-	blk_queue_start_drain(disk->queue);
+	/*
+	 * Fail any new I/O.
+	 */
+	if (test_and_set_bit(GD_DEAD, &disk->state))
+		return;
+
+	if (test_bit(GD_OWNS_QUEUE, &disk->state))
+		blk_queue_flag_set(QUEUE_FLAG_DYING, disk->queue);
 
 	/*
 	 * Stop buffered writers from dirtying pages that can't be written out.
 	 */
-	set_capacity_and_notify(disk, 0);
+	set_capacity(disk, 0);
+
+	/*
+	 * Prevent new I/O from crossing bio_queue_enter().
+	 */
+	blk_queue_start_drain(disk->queue);
+
+	blk_report_disk_dead(disk);
 }
 EXPORT_SYMBOL_GPL(blk_mark_disk_dead);
 
@@ -604,6 +630,8 @@ EXPORT_SYMBOL_GPL(blk_mark_disk_dead);
 void del_gendisk(struct gendisk *disk)
 {
 	struct request_queue *q = disk->queue;
+	struct block_device *part;
+	unsigned long idx;
 
 	might_sleep();
 
@@ -612,26 +640,27 @@ void del_gendisk(struct gendisk *disk)
 
 	disk_del_events(disk);
 
+	/*
+	 * Prevent new openers by unlinked the bdev inode, and write out
+	 * dirty data before marking the disk dead and stopping all I/O.
+	 */
 	mutex_lock(&disk->open_mutex);
-	remove_inode_hash(disk->part0->bd_inode);
-	blk_drop_partitions(disk);
+	xa_for_each(&disk->part_tbl, idx, part) {
+		remove_inode_hash(part->bd_inode);
+		fsync_bdev(part);
+		__invalidate_device(part, true);
+	}
 	mutex_unlock(&disk->open_mutex);
 
-	fsync_bdev(disk->part0);
-	__invalidate_device(disk->part0, true);
+	blk_mark_disk_dead(disk);
 
 	/*
-	 * Fail any new I/O.
+	 * Drop all partitions now that the disk is marked dead.
 	 */
-	set_bit(GD_DEAD, &disk->state);
-	if (test_bit(GD_OWNS_QUEUE, &disk->state))
-		blk_queue_flag_set(QUEUE_FLAG_DYING, q);
-	set_capacity(disk, 0);
-
-	/*
-	 * Prevent new I/O from crossing bio_queue_enter().
-	 */
-	blk_queue_start_drain(q);
+	mutex_lock(&disk->open_mutex);
+	xa_for_each_start(&disk->part_tbl, idx, part, 1)
+		drop_partition(part);
+	mutex_unlock(&disk->open_mutex);
 
 	if (!(disk->flags & GENHD_FL_HIDDEN)) {
 		sysfs_remove_link(&disk_to_dev(disk)->kobj, "bdi");
@@ -755,57 +784,6 @@ void blk_request_module(dev_t devt)
 }
 #endif /* CONFIG_BLOCK_LEGACY_AUTOLOAD */
 
-/*
- * print a full list of all partitions - intended for places where the root
- * filesystem can't be mounted and thus to give the victim some idea of what
- * went wrong
- */
-void __init printk_all_partitions(void)
-{
-	struct class_dev_iter iter;
-	struct device *dev;
-
-	class_dev_iter_init(&iter, &block_class, NULL, &disk_type);
-	while ((dev = class_dev_iter_next(&iter))) {
-		struct gendisk *disk = dev_to_disk(dev);
-		struct block_device *part;
-		char devt_buf[BDEVT_SIZE];
-		unsigned long idx;
-
-		/*
-		 * Don't show empty devices or things that have been
-		 * suppressed
-		 */
-		if (get_capacity(disk) == 0 || (disk->flags & GENHD_FL_HIDDEN))
-			continue;
-
-		/*
-		 * Note, unlike /proc/partitions, I am showing the numbers in
-		 * hex - the same format as the root= option takes.
-		 */
-		rcu_read_lock();
-		xa_for_each(&disk->part_tbl, idx, part) {
-			if (!bdev_nr_sectors(part))
-				continue;
-			printk("%s%s %10llu %pg %s",
-			       bdev_is_partition(part) ? "  " : "",
-			       bdevt_str(part->bd_dev, devt_buf),
-			       bdev_nr_sectors(part) >> 1, part,
-			       part->bd_meta_info ?
-					part->bd_meta_info->uuid : "");
-			if (bdev_is_partition(part))
-				printk("\n");
-			else if (dev->parent && dev->parent->driver)
-				printk(" driver: %s\n",
-					dev->parent->driver->name);
-			else
-				printk(" (driver?)\n");
-		}
-		rcu_read_unlock();
-	}
-	class_dev_iter_exit(&iter);
-}
-
 #ifdef CONFIG_PROC_FS
 /* iterator */
 static void *disk_seqf_start(struct seq_file *seqf, loff_t *pos)
@@ -1171,6 +1149,8 @@ static void disk_release(struct device *dev)
 	might_sleep();
 	WARN_ON_ONCE(disk_live(disk));
 
+	blk_trace_remove(disk->queue);
+
 	/*
 	 * To undo the all initialization from blk_mq_init_allocated_queue in
 	 * case of a probe failure where add_disk is never called we have to
@@ -1339,35 +1319,6 @@ dev_t part_devt(struct gendisk *disk, u8 partno)
 	return devt;
 }
 
-dev_t blk_lookup_devt(const char *name, int partno)
-{
-	dev_t devt = MKDEV(0, 0);
-	struct class_dev_iter iter;
-	struct device *dev;
-
-	class_dev_iter_init(&iter, &block_class, NULL, &disk_type);
-	while ((dev = class_dev_iter_next(&iter))) {
-		struct gendisk *disk = dev_to_disk(dev);
-
-		if (strcmp(dev_name(dev), name))
-			continue;
-
-		if (partno < disk->minors) {
-			/* We need to return the right devno, even
-			 * if the partition doesn't exist yet.
-			 */
-			devt = MKDEV(MAJOR(dev->devt),
-				     MINOR(dev->devt) + partno);
-		} else {
-			devt = part_devt(disk, partno);
-			if (devt)
-				break;
-		}
-	}
-	class_dev_iter_exit(&iter);
-	return devt;
-}
-
 struct gendisk *__alloc_disk_node(struct request_queue *q, int node_id,
 		struct lock_class_key *lkclass)
 {