Merge tag 'for-6.4/block-2023-05-06' of git://git.kernel.dk/linux

Pull more block updates from Jens Axboe:

 - MD pull request via Song:
      - Improve raid5 sequential IO performance on spinning disks, which
        fixes a regression since v6.0 (Jan Kara)
      - Fix bitmap offset types, which fixes an issue introduced in this
        merge window (Jonathan Derrick)

 - Cleanup of hweight type used for cgroup writeback (Maxim)

 - Fix a regression with the "has_submit_bio" changes across partitions
   (Ming)

 - Cleanup of QUEUE_FLAG_ADD_RANDOM clearing.

   We used to set this flag on queues non blk-mq queues, and hence some
   drivers clear it unconditionally. Since all of these have since been
   converted to true blk-mq drivers, drop the useless clear as the bit
   is not set (Chaitanya)

 - Fix the flags being set in a bio for a flush for drbd (Christoph)

 - Cleanup and deduplication of the code handling setting block device
   capacity (Damien)

 - Fix for ublk handling IO timeouts (Ming)

 - Fix for a regression in blk-cgroup teardown (Tao)

 - NBD documentation and code fixes (Eric)

 - Convert blk-integrity to using device_attributes rather than a second
   kobject to manage lifetimes (Thomas)

* tag 'for-6.4/block-2023-05-06' of git://git.kernel.dk/linux:
  ublk: add timeout handler
  drbd: correctly submit flush bio on barrier
  mailmap: add mailmap entries for Jens Axboe
  block: Skip destroyed blkg when restart in blkg_destroy_all()
  writeback: fix call of incorrect macro
  md: Fix bitmap offset type in sb writer
  md/raid5: Improve performance for sequential IO
  docs nbd: userspace NBD now favors github over sourceforge
  block nbd: use req.cookie instead of req.handle
  uapi nbd: add cookie alias to handle
  uapi nbd: improve doc links to userspace spec
  blk-integrity: register sysfs attributes on struct device
  blk-integrity: convert to struct device_attribute
  blk-integrity: use sysfs_emit
  block/drivers: remove dead clear of random flag
  block: sync part's ->bd_has_submit_bio with disk's
  block: Cleanup set_capacity()/bdev_set_nr_sectors()

Author: torvalds

.mailmap

@@ -213,7 +213,10 @@ Jeff Garzik <jgarzik@pretzel.yyz.us>
 Jeff Layton <jlayton@kernel.org> <jlayton@poochiereds.net>
 Jeff Layton <jlayton@kernel.org> <jlayton@primarydata.com>
 Jeff Layton <jlayton@kernel.org> <jlayton@redhat.com>
-Jens Axboe <axboe@suse.de>
+Jens Axboe <axboe@kernel.dk> <axboe@suse.de>
+Jens Axboe <axboe@kernel.dk> <jens.axboe@oracle.com>
+Jens Axboe <axboe@kernel.dk> <axboe@fb.com>
+Jens Axboe <axboe@kernel.dk> <axboe@meta.com>
 Jens Osterkamp <Jens.Osterkamp@de.ibm.com>
 Jernej Skrabec <jernej.skrabec@gmail.com> <jernej.skrabec@siol.net>
 Jessica Zhang <quic_jesszhan@quicinc.com> <jesszhan@codeaurora.org>

Documentation/admin-guide/blockdev/nbd.rst

@@ -14,7 +14,7 @@ to borrow disk space from another computer.
 Unlike NFS, it is possible to put any filesystem on it, etc.
 
 For more information, or to download the nbd-client and nbd-server
-tools, go to http://nbd.sf.net/.
+tools, go to https://github.com/NetworkBlockDevice/nbd.
 
 The nbd kernel module need only be installed on the client
 system, as the nbd-server is completely in userspace. In fact,

block/bdev.c

@@ -418,8 +418,11 @@ struct block_device *bdev_alloc(struct gendisk *disk, u8 partno)
 	bdev->bd_partno = partno;
 	bdev->bd_inode = inode;
 	bdev->bd_queue = disk->queue;
+	if (partno)
+		bdev->bd_has_submit_bio = disk->part0->bd_has_submit_bio;
+	else
+		bdev->bd_has_submit_bio = false;
 	bdev->bd_stats = alloc_percpu(struct disk_stats);
-	bdev->bd_has_submit_bio = false;
 	if (!bdev->bd_stats) {
 		iput(inode);
 		return NULL;
@@ -428,6 +431,14 @@ struct block_device *bdev_alloc(struct gendisk *disk, u8 partno)
 	return bdev;
 }
 
+void bdev_set_nr_sectors(struct block_device *bdev, sector_t sectors)
+{
+	spin_lock(&bdev->bd_size_lock);
+	i_size_write(bdev->bd_inode, (loff_t)sectors << SECTOR_SHIFT);
+	bdev->bd_nr_sectors = sectors;
+	spin_unlock(&bdev->bd_size_lock);
+}
+
 void bdev_add(struct block_device *bdev, dev_t dev)
 {
 	bdev->bd_dev = dev;

block/blk-cgroup.c

@@ -567,6 +567,9 @@ static void blkg_destroy_all(struct gendisk *disk)
 	list_for_each_entry_safe(blkg, n, &q->blkg_list, q_node) {
 		struct blkcg *blkcg = blkg->blkcg;
 
+		if (hlist_unhashed(&blkg->blkcg_node))
+			continue;
+
 		spin_lock(&blkcg->lock);
 		blkg_destroy(blkg);
 		spin_unlock(&blkcg->lock);

block/blk-integrity.c

@@ -212,61 +212,44 @@ bool blk_integrity_merge_bio(struct request_queue *q, struct request *req,
 	return true;
 }
 
-struct integrity_sysfs_entry {
-	struct attribute attr;
-	ssize_t (*show)(struct blk_integrity *, char *);
-	ssize_t (*store)(struct blk_integrity *, const char *, size_t);
-};
-
-static ssize_t integrity_attr_show(struct kobject *kobj, struct attribute *attr,
-				   char *page)
+static inline struct blk_integrity *dev_to_bi(struct device *dev)
 {
-	struct gendisk *disk = container_of(kobj, struct gendisk, integrity_kobj);
-	struct blk_integrity *bi = &disk->queue->integrity;
-	struct integrity_sysfs_entry *entry =
-		container_of(attr, struct integrity_sysfs_entry, attr);
-
-	return entry->show(bi, page);
+	return &dev_to_disk(dev)->queue->integrity;
 }
 
-static ssize_t integrity_attr_store(struct kobject *kobj,
-				    struct attribute *attr, const char *page,
-				    size_t count)
+static ssize_t format_show(struct device *dev, struct device_attribute *attr,
+			   char *page)
 {
-	struct gendisk *disk = container_of(kobj, struct gendisk, integrity_kobj);
-	struct blk_integrity *bi = &disk->queue->integrity;
-	struct integrity_sysfs_entry *entry =
-		container_of(attr, struct integrity_sysfs_entry, attr);
-	ssize_t ret = 0;
+	struct blk_integrity *bi = dev_to_bi(dev);
 
-	if (entry->store)
-		ret = entry->store(bi, page, count);
-
-	return ret;
-}
-
-static ssize_t integrity_format_show(struct blk_integrity *bi, char *page)
-{
 	if (bi->profile && bi->profile->name)
-		return sprintf(page, "%s\n", bi->profile->name);
-	else
-		return sprintf(page, "none\n");
+		return sysfs_emit(page, "%s\n", bi->profile->name);
+	return sysfs_emit(page, "none\n");
 }
 
-static ssize_t integrity_tag_size_show(struct blk_integrity *bi, char *page)
+static ssize_t tag_size_show(struct device *dev, struct device_attribute *attr,
+			     char *page)
 {
-	return sprintf(page, "%u\n", bi->tag_size);
+	struct blk_integrity *bi = dev_to_bi(dev);
+
+	return sysfs_emit(page, "%u\n", bi->tag_size);
 }
 
-static ssize_t integrity_interval_show(struct blk_integrity *bi, char *page)
+static ssize_t protection_interval_bytes_show(struct device *dev,
+					      struct device_attribute *attr,
+					      char *page)
 {
-	return sprintf(page, "%u\n",
-		       bi->interval_exp ? 1 << bi->interval_exp : 0);
+	struct blk_integrity *bi = dev_to_bi(dev);
+
+	return sysfs_emit(page, "%u\n",
+			  bi->interval_exp ? 1 << bi->interval_exp : 0);
 }
 
-static ssize_t integrity_verify_store(struct blk_integrity *bi,
-				      const char *page, size_t count)
+static ssize_t read_verify_store(struct device *dev,
+				 struct device_attribute *attr,
+				 const char *page, size_t count)
 {
+	struct blk_integrity *bi = dev_to_bi(dev);
 	char *p = (char *) page;
 	unsigned long val = simple_strtoul(p, &p, 10);
 
@@ -278,14 +261,20 @@ static ssize_t integrity_verify_store(struct blk_integrity *bi,
 	return count;
 }
 
-static ssize_t integrity_verify_show(struct blk_integrity *bi, char *page)
+static ssize_t read_verify_show(struct device *dev,
+				struct device_attribute *attr, char *page)
 {
-	return sprintf(page, "%d\n", (bi->flags & BLK_INTEGRITY_VERIFY) != 0);
+	struct blk_integrity *bi = dev_to_bi(dev);
+
+	return sysfs_emit(page, "%d\n", !!(bi->flags & BLK_INTEGRITY_VERIFY));
 }
 
-static ssize_t integrity_generate_store(struct blk_integrity *bi,
-					const char *page, size_t count)
+static ssize_t write_generate_store(struct device *dev,
+				    struct device_attribute *attr,
+				    const char *page, size_t count)
 {
+	struct blk_integrity *bi = dev_to_bi(dev);
+
 	char *p = (char *) page;
 	unsigned long val = simple_strtoul(p, &p, 10);
 
@@ -297,68 +286,44 @@ static ssize_t integrity_generate_store(struct blk_integrity *bi,
 	return count;
 }
 
-static ssize_t integrity_generate_show(struct blk_integrity *bi, char *page)
+static ssize_t write_generate_show(struct device *dev,
+				   struct device_attribute *attr, char *page)
 {
-	return sprintf(page, "%d\n", (bi->flags & BLK_INTEGRITY_GENERATE) != 0);
-}
+	struct blk_integrity *bi = dev_to_bi(dev);
 
-static ssize_t integrity_device_show(struct blk_integrity *bi, char *page)
-{
-	return sprintf(page, "%u\n",
-		       (bi->flags & BLK_INTEGRITY_DEVICE_CAPABLE) != 0);
+	return sysfs_emit(page, "%d\n", !!(bi->flags & BLK_INTEGRITY_GENERATE));
 }
 
-static struct integrity_sysfs_entry integrity_format_entry = {
-	.attr = { .name = "format", .mode = 0444 },
-	.show = integrity_format_show,
-};
-
-static struct integrity_sysfs_entry integrity_tag_size_entry = {
-	.attr = { .name = "tag_size", .mode = 0444 },
-	.show = integrity_tag_size_show,
-};
-
-static struct integrity_sysfs_entry integrity_interval_entry = {
-	.attr = { .name = "protection_interval_bytes", .mode = 0444 },
-	.show = integrity_interval_show,
-};
-
-static struct integrity_sysfs_entry integrity_verify_entry = {
-	.attr = { .name = "read_verify", .mode = 0644 },
-	.show = integrity_verify_show,
-	.store = integrity_verify_store,
-};
+static ssize_t device_is_integrity_capable_show(struct device *dev,
+						struct device_attribute *attr,
+						char *page)
+{
+	struct blk_integrity *bi = dev_to_bi(dev);
 
-static struct integrity_sysfs_entry integrity_generate_entry = {
-	.attr = { .name = "write_generate", .mode = 0644 },
-	.show = integrity_generate_show,
-	.store = integrity_generate_store,
-};
+	return sysfs_emit(page, "%u\n",
+			  !!(bi->flags & BLK_INTEGRITY_DEVICE_CAPABLE));
+}
 
-static struct integrity_sysfs_entry integrity_device_entry = {
-	.attr = { .name = "device_is_integrity_capable", .mode = 0444 },
-	.show = integrity_device_show,
-};
+static DEVICE_ATTR_RO(format);
+static DEVICE_ATTR_RO(tag_size);
+static DEVICE_ATTR_RO(protection_interval_bytes);
+static DEVICE_ATTR_RW(read_verify);
+static DEVICE_ATTR_RW(write_generate);
+static DEVICE_ATTR_RO(device_is_integrity_capable);
 
 static struct attribute *integrity_attrs[] = {
-	&integrity_format_entry.attr,
-	&integrity_tag_size_entry.attr,
-	&integrity_interval_entry.attr,
-	&integrity_verify_entry.attr,
-	&integrity_generate_entry.attr,
-	&integrity_device_entry.attr,
-	NULL,
+	&dev_attr_format.attr,
+	&dev_attr_tag_size.attr,
+	&dev_attr_protection_interval_bytes.attr,
+	&dev_attr_read_verify.attr,
+	&dev_attr_write_generate.attr,
+	&dev_attr_device_is_integrity_capable.attr,
+	NULL
 };
-ATTRIBUTE_GROUPS(integrity);
 
-static const struct sysfs_ops integrity_ops = {
-	.show	= &integrity_attr_show,
-	.store	= &integrity_attr_store,
-};
-
-static const struct kobj_type integrity_ktype = {
-	.default_groups = integrity_groups,
-	.sysfs_ops	= &integrity_ops,
+const struct attribute_group blk_integrity_attr_group = {
+	.name = "integrity",
+	.attrs = integrity_attrs,
 };
 
 static blk_status_t blk_integrity_nop_fn(struct blk_integrity_iter *iter)
@@ -437,21 +402,3 @@ void blk_integrity_unregister(struct gendisk *disk)
 	memset(bi, 0, sizeof(*bi));
 }
 EXPORT_SYMBOL(blk_integrity_unregister);
-
-int blk_integrity_add(struct gendisk *disk)
-{
-	int ret;
-
-	ret = kobject_init_and_add(&disk->integrity_kobj, &integrity_ktype,
-				   &disk_to_dev(disk)->kobj, "%s", "integrity");
-	if (!ret)
-		kobject_uevent(&disk->integrity_kobj, KOBJ_ADD);
-	return ret;
-}
-
-void blk_integrity_del(struct gendisk *disk)
-{
-	kobject_uevent(&disk->integrity_kobj, KOBJ_REMOVE);
-	kobject_del(&disk->integrity_kobj);
-	kobject_put(&disk->integrity_kobj);
-}

block/blk.h

@@ -214,8 +214,7 @@ static inline bool integrity_req_gap_front_merge(struct request *req,
 				bip_next->bip_vec[0].bv_offset);
 }
 
-int blk_integrity_add(struct gendisk *disk);
-void blk_integrity_del(struct gendisk *);
+extern const struct attribute_group blk_integrity_attr_group;
 #else /* CONFIG_BLK_DEV_INTEGRITY */
 static inline bool blk_integrity_merge_rq(struct request_queue *rq,
 		struct request *r1, struct request *r2)
@@ -248,13 +247,6 @@ static inline bool bio_integrity_endio(struct bio *bio)
 static inline void bio_integrity_free(struct bio *bio)
 {
 }
-static inline int blk_integrity_add(struct gendisk *disk)
-{
-	return 0;
-}
-static inline void blk_integrity_del(struct gendisk *disk)
-{
-}
 #endif /* CONFIG_BLK_DEV_INTEGRITY */
 
 unsigned long blk_rq_timeout(unsigned long timeout);
@@ -419,6 +411,8 @@ int bdev_resize_partition(struct gendisk *disk, int partno, sector_t start,
 		sector_t length);
 void blk_drop_partitions(struct gendisk *disk);
 
+void bdev_set_nr_sectors(struct block_device *bdev, sector_t sectors);
+
 struct gendisk *__alloc_disk_node(struct request_queue *q, int node_id,
 		struct lock_class_key *lkclass);
 

block/genhd.c

@@ -57,12 +57,7 @@ static DEFINE_IDA(ext_devt_ida);
 
 void set_capacity(struct gendisk *disk, sector_t sectors)
 {
-	struct block_device *bdev = disk->part0;
-
-	spin_lock(&bdev->bd_size_lock);
-	i_size_write(bdev->bd_inode, (loff_t)sectors << SECTOR_SHIFT);
-	bdev->bd_nr_sectors = sectors;
-	spin_unlock(&bdev->bd_size_lock);
+	bdev_set_nr_sectors(disk->part0, sectors);
 }
 EXPORT_SYMBOL(set_capacity);
 
@@ -487,15 +482,11 @@ int __must_check device_add_disk(struct device *parent, struct gendisk *disk,
 	 */
 	pm_runtime_set_memalloc_noio(ddev, true);
 
-	ret = blk_integrity_add(disk);
-	if (ret)
-		goto out_del_block_link;
-
 	disk->part0->bd_holder_dir =
 		kobject_create_and_add("holders", &ddev->kobj);
 	if (!disk->part0->bd_holder_dir) {
 		ret = -ENOMEM;
-		goto out_del_integrity;
+		goto out_del_block_link;
 	}
 	disk->slave_dir = kobject_create_and_add("slaves", &ddev->kobj);
 	if (!disk->slave_dir) {
@@ -558,8 +549,6 @@ int __must_check device_add_disk(struct device *parent, struct gendisk *disk,
 	disk->slave_dir = NULL;
 out_put_holder_dir:
 	kobject_put(disk->part0->bd_holder_dir);
-out_del_integrity:
-	blk_integrity_del(disk);
 out_del_block_link:
 	sysfs_remove_link(block_depr, dev_name(ddev));
 out_device_del:
@@ -621,7 +610,6 @@ void del_gendisk(struct gendisk *disk)
 	if (WARN_ON_ONCE(!disk_live(disk) && !(disk->flags & GENHD_FL_HIDDEN)))
 		return;
 
-	blk_integrity_del(disk);
 	disk_del_events(disk);
 
 	mutex_lock(&disk->open_mutex);
@@ -1155,6 +1143,9 @@ static const struct attribute_group *disk_attr_groups[] = {
 	&disk_attr_group,
 #ifdef CONFIG_BLK_DEV_IO_TRACE
 	&blk_trace_attr_group,
+#endif
+#ifdef CONFIG_BLK_DEV_INTEGRITY
+	&blk_integrity_attr_group,
 #endif
 	NULL
 };

block/partitions/core.c

@@ -85,14 +85,6 @@ static int (*check_part[])(struct parsed_partitions *) = {
 	NULL
 };
 
-static void bdev_set_nr_sectors(struct block_device *bdev, sector_t sectors)
-{
-	spin_lock(&bdev->bd_size_lock);
-	i_size_write(bdev->bd_inode, (loff_t)sectors << SECTOR_SHIFT);
-	bdev->bd_nr_sectors = sectors;
-	spin_unlock(&bdev->bd_size_lock);
-}
-
 static struct parsed_partitions *allocate_partitions(struct gendisk *hd)
 {
 	struct parsed_partitions *state;