Merge tag 'for-5.15/block-2021-08-30' of git://git.kernel.dk/linux-block

Pull block updates from Jens Axboe:
 "Nothing major in here - lots of good cleanups and tech debt handling,
  which is also evident in the diffstats. In particular:

   - Add disk sequence numbers (Matteo)

   - Discard merge fix (Ming)

   - Relax disk zoned reporting restrictions (Niklas)

   - Bio error handling zoned leak fix (Pavel)

   - Start of proper add_disk() error handling (Luis, Christoph)

   - blk crypto fix (Eric)

   - Non-standard GPT location support (Dmitry)

   - IO priority improvements and cleanups (Damien)o

   - blk-throtl improvements (Chunguang)

   - diskstats_show() stack reduction (Abd-Alrhman)

   - Loop scheduler selection (Bart)

   - Switch block layer to use kmap_local_page() (Christoph)

   - Remove obsolete disk_name helper (Christoph)

   - block_device refcounting improvements (Christoph)

   - Ensure gendisk always has a request queue reference (Christoph)

   - Misc fixes/cleanups (Shaokun, Oliver, Guoqing)"

* tag 'for-5.15/block-2021-08-30' of git://git.kernel.dk/linux-block: (129 commits)
  sg: pass the device name to blk_trace_setup
  block, bfq: cleanup the repeated declaration
  blk-crypto: fix check for too-large dun_bytes
  blk-zoned: allow BLKREPORTZONE without CAP_SYS_ADMIN
  blk-zoned: allow zone management send operations without CAP_SYS_ADMIN
  block: mark blkdev_fsync static
  block: refine the disk_live check in del_gendisk
  mmc: sdhci-tegra: Enable MMC_CAP2_ALT_GPT_TEGRA
  mmc: block: Support alternative_gpt_sector() operation
  partitions/efi: Support non-standard GPT location
  block: Add alternative_gpt_sector() operation
  bio: fix page leak bio_add_hw_page failure
  block: remove CONFIG_DEBUG_BLOCK_EXT_DEVT
  block: remove a pointless call to MINOR() in device_add_disk
  null_blk: add error handling support for add_disk()
  virtio_blk: add error handling support for add_disk()
  block: add error handling for device_add_disk / add_disk
  block: return errors from disk_alloc_events
  block: return errors from blk_integrity_add
  block: call blk_register_queue earlier in device_add_disk
  ...

12 files changed, 49 insertions, 234 deletions

diff --git a/fs/block_dev.c b/fs/block_dev.c
index 9ef4f1fc2cb0..1f21ac984253 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -35,6 +35,7 @@
 #include <linux/uaccess.h>
 #include <linux/suspend.h>
 #include "internal.h"
+#include "../block/blk.h"
 
 struct bdev_inode {
 	struct block_device bdev;
@@ -686,7 +687,8 @@ static loff_t block_llseek(struct file *file, loff_t offset, int whence)
 	return retval;
 }
 	
-int blkdev_fsync(struct file *filp, loff_t start, loff_t end, int datasync)
+static int blkdev_fsync(struct file *filp, loff_t start, loff_t end,
+		int datasync)
 {
 	struct inode *bd_inode = bdev_file_inode(filp);
 	struct block_device *bdev = I_BDEV(bd_inode);
@@ -707,7 +709,6 @@ int blkdev_fsync(struct file *filp, loff_t start, loff_t end, int datasync)
 
 	return error;
 }
-EXPORT_SYMBOL(blkdev_fsync);
 
 /**
  * bdev_read_page() - Start reading a page from a block device
@@ -801,7 +802,6 @@ static struct inode *bdev_alloc_inode(struct super_block *sb)
 	if (!ei)
 		return NULL;
 	memset(&ei->bdev, 0, sizeof(ei->bdev));
-	ei->bdev.bd_bdi = &noop_backing_dev_info;
 	return &ei->vfs_inode;
 }
 
@@ -812,8 +812,15 @@ static void bdev_free_inode(struct inode *inode)
 	free_percpu(bdev->bd_stats);
 	kfree(bdev->bd_meta_info);
 
-	if (!bdev_is_partition(bdev))
+	if (!bdev_is_partition(bdev)) {
+		if (bdev->bd_disk && bdev->bd_disk->bdi)
+			bdi_put(bdev->bd_disk->bdi);
 		kfree(bdev->bd_disk);
+	}
+
+	if (MAJOR(bdev->bd_dev) == BLOCK_EXT_MAJOR)
+		blk_free_ext_minor(MINOR(bdev->bd_dev));
+
 	kmem_cache_free(bdev_cachep, BDEV_I(inode));
 }
 
@@ -826,16 +833,9 @@ static void init_once(void *data)
 
 static void bdev_evict_inode(struct inode *inode)
 {
-	struct block_device *bdev = &BDEV_I(inode)->bdev;
 	truncate_inode_pages_final(&inode->i_data);
 	invalidate_inode_buffers(inode); /* is it needed here? */
 	clear_inode(inode);
-	/* Detach inode from wb early as bdi_put() may free bdi->wb */
-	inode_detach_wb(inode);
-	if (bdev->bd_bdi != &noop_backing_dev_info) {
-		bdi_put(bdev->bd_bdi);
-		bdev->bd_bdi = &noop_backing_dev_info;
-	}
 }
 
 static const struct super_operations bdev_sops = {
@@ -902,9 +902,6 @@ struct block_device *bdev_alloc(struct gendisk *disk, u8 partno)
 	bdev->bd_disk = disk;
 	bdev->bd_partno = partno;
 	bdev->bd_inode = inode;
-#ifdef CONFIG_SYSFS
-	INIT_LIST_HEAD(&bdev->bd_holder_disks);
-#endif
 	bdev->bd_stats = alloc_percpu(struct disk_stats);
 	if (!bdev->bd_stats) {
 		iput(inode);
@@ -921,31 +918,6 @@ void bdev_add(struct block_device *bdev, dev_t dev)
 	insert_inode_hash(bdev->bd_inode);
 }
 
-static struct block_device *bdget(dev_t dev)
-{
-	struct inode *inode;
-
-	inode = ilookup(blockdev_superblock, dev);
-	if (!inode)
-		return NULL;
-	return &BDEV_I(inode)->bdev;
-}
-
-/**
- * bdgrab -- Grab a reference to an already referenced block device
- * @bdev:	Block device to grab a reference to.
- *
- * Returns the block_device with an additional reference when successful,
- * or NULL if the inode is already beeing freed.
- */
-struct block_device *bdgrab(struct block_device *bdev)
-{
-	if (!igrab(bdev->bd_inode))
-		return NULL;
-	return bdev;
-}
-EXPORT_SYMBOL(bdgrab);
-
 long nr_blockdev_pages(void)
 {
 	struct inode *inode;
@@ -959,12 +931,6 @@ long nr_blockdev_pages(void)
 	return ret;
 }
 
-void bdput(struct block_device *bdev)
-{
-	iput(bdev->bd_inode);
-}
-EXPORT_SYMBOL(bdput);
- 
 /**
  * bd_may_claim - test whether a block device can be claimed
  * @bdev: block device of interest
@@ -1094,148 +1060,6 @@ void bd_abort_claiming(struct block_device *bdev, void *holder)
 }
 EXPORT_SYMBOL(bd_abort_claiming);
 
-#ifdef CONFIG_SYSFS
-struct bd_holder_disk {
-	struct list_head	list;
-	struct gendisk		*disk;
-	int			refcnt;
-};
-
-static struct bd_holder_disk *bd_find_holder_disk(struct block_device *bdev,
-						  struct gendisk *disk)
-{
-	struct bd_holder_disk *holder;
-
-	list_for_each_entry(holder, &bdev->bd_holder_disks, list)
-		if (holder->disk == disk)
-			return holder;
-	return NULL;
-}
-
-static int add_symlink(struct kobject *from, struct kobject *to)
-{
-	return sysfs_create_link(from, to, kobject_name(to));
-}
-
-static void del_symlink(struct kobject *from, struct kobject *to)
-{
-	sysfs_remove_link(from, kobject_name(to));
-}
-
-/**
- * bd_link_disk_holder - create symlinks between holding disk and slave bdev
- * @bdev: the claimed slave bdev
- * @disk: the holding disk
- *
- * DON'T USE THIS UNLESS YOU'RE ALREADY USING IT.
- *
- * This functions creates the following sysfs symlinks.
- *
- * - from "slaves" directory of the holder @disk to the claimed @bdev
- * - from "holders" directory of the @bdev to the holder @disk
- *
- * For example, if /dev/dm-0 maps to /dev/sda and disk for dm-0 is
- * passed to bd_link_disk_holder(), then:
- *
- *   /sys/block/dm-0/slaves/sda --> /sys/block/sda
- *   /sys/block/sda/holders/dm-0 --> /sys/block/dm-0
- *
- * The caller must have claimed @bdev before calling this function and
- * ensure that both @bdev and @disk are valid during the creation and
- * lifetime of these symlinks.
- *
- * CONTEXT:
- * Might sleep.
- *
- * RETURNS:
- * 0 on success, -errno on failure.
- */
-int bd_link_disk_holder(struct block_device *bdev, struct gendisk *disk)
-{
-	struct bd_holder_disk *holder;
-	int ret = 0;
-
-	mutex_lock(&bdev->bd_disk->open_mutex);
-
-	WARN_ON_ONCE(!bdev->bd_holder);
-
-	/* FIXME: remove the following once add_disk() handles errors */
-	if (WARN_ON(!disk->slave_dir || !bdev->bd_holder_dir))
-		goto out_unlock;
-
-	holder = bd_find_holder_disk(bdev, disk);
-	if (holder) {
-		holder->refcnt++;
-		goto out_unlock;
-	}
-
-	holder = kzalloc(sizeof(*holder), GFP_KERNEL);
-	if (!holder) {
-		ret = -ENOMEM;
-		goto out_unlock;
-	}
-
-	INIT_LIST_HEAD(&holder->list);
-	holder->disk = disk;
-	holder->refcnt = 1;
-
-	ret = add_symlink(disk->slave_dir, bdev_kobj(bdev));
-	if (ret)
-		goto out_free;
-
-	ret = add_symlink(bdev->bd_holder_dir, &disk_to_dev(disk)->kobj);
-	if (ret)
-		goto out_del;
-	/*
-	 * bdev could be deleted beneath us which would implicitly destroy
-	 * the holder directory.  Hold on to it.
-	 */
-	kobject_get(bdev->bd_holder_dir);
-
-	list_add(&holder->list, &bdev->bd_holder_disks);
-	goto out_unlock;
-
-out_del:
-	del_symlink(disk->slave_dir, bdev_kobj(bdev));
-out_free:
-	kfree(holder);
-out_unlock:
-	mutex_unlock(&bdev->bd_disk->open_mutex);
-	return ret;
-}
-EXPORT_SYMBOL_GPL(bd_link_disk_holder);
-
-/**
- * bd_unlink_disk_holder - destroy symlinks created by bd_link_disk_holder()
- * @bdev: the calimed slave bdev
- * @disk: the holding disk
- *
- * DON'T USE THIS UNLESS YOU'RE ALREADY USING IT.
- *
- * CONTEXT:
- * Might sleep.
- */
-void bd_unlink_disk_holder(struct block_device *bdev, struct gendisk *disk)
-{
-	struct bd_holder_disk *holder;
-
-	mutex_lock(&bdev->bd_disk->open_mutex);
-
-	holder = bd_find_holder_disk(bdev, disk);
-
-	if (!WARN_ON_ONCE(holder == NULL) && !--holder->refcnt) {
-		del_symlink(disk->slave_dir, bdev_kobj(bdev));
-		del_symlink(bdev->bd_holder_dir, &disk_to_dev(disk)->kobj);
-		kobject_put(bdev->bd_holder_dir);
-		list_del_init(&holder->list);
-		kfree(holder);
-	}
-
-	mutex_unlock(&bdev->bd_disk->open_mutex);
-}
-EXPORT_SYMBOL_GPL(bd_unlink_disk_holder);
-#endif
-
 static void blkdev_flush_mapping(struct block_device *bdev)
 {
 	WARN_ON_ONCE(bdev->bd_holders);
@@ -1260,11 +1084,8 @@ static int blkdev_get_whole(struct block_device *bdev, fmode_t mode)
 		}
 	}
 
-	if (!bdev->bd_openers) {
+	if (!bdev->bd_openers)
 		set_init_blocksize(bdev);
-		if (bdev->bd_bdi == &noop_backing_dev_info)
-			bdev->bd_bdi = bdi_get(disk->queue->backing_dev_info);
-	}
 	if (test_bit(GD_NEED_PART_SCAN, &disk->state))
 		bdev_disk_changed(disk, false);
 	bdev->bd_openers++;
@@ -1282,16 +1103,14 @@ static void blkdev_put_whole(struct block_device *bdev, fmode_t mode)
 static int blkdev_get_part(struct block_device *part, fmode_t mode)
 {
 	struct gendisk *disk = part->bd_disk;
-	struct block_device *whole;
 	int ret;
 
 	if (part->bd_openers)
 		goto done;
 
-	whole = bdgrab(disk->part0);
-	ret = blkdev_get_whole(whole, mode);
+	ret = blkdev_get_whole(bdev_whole(part), mode);
 	if (ret)
-		goto out_put_whole;
+		return ret;
 
 	ret = -ENXIO;
 	if (!bdev_nr_sectors(part))
@@ -1299,16 +1118,12 @@ static int blkdev_get_part(struct block_device *part, fmode_t mode)
 
 	disk->open_partitions++;
 	set_init_blocksize(part);
-	if (part->bd_bdi == &noop_backing_dev_info)
-		part->bd_bdi = bdi_get(disk->queue->backing_dev_info);
 done:
 	part->bd_openers++;
 	return 0;
 
 out_blkdev_put:
-	blkdev_put_whole(whole, mode);
-out_put_whole:
-	bdput(whole);
+	blkdev_put_whole(bdev_whole(part), mode);
 	return ret;
 }
 
@@ -1321,42 +1136,42 @@ static void blkdev_put_part(struct block_device *part, fmode_t mode)
 	blkdev_flush_mapping(part);
 	whole->bd_disk->open_partitions--;
 	blkdev_put_whole(whole, mode);
-	bdput(whole);
 }
 
 struct block_device *blkdev_get_no_open(dev_t dev)
 {
 	struct block_device *bdev;
-	struct gendisk *disk;
+	struct inode *inode;
 
-	bdev = bdget(dev);
-	if (!bdev) {
+	inode = ilookup(blockdev_superblock, dev);
+	if (!inode) {
 		blk_request_module(dev);
-		bdev = bdget(dev);
-		if (!bdev)
+		inode = ilookup(blockdev_superblock, dev);
+		if (!inode)
 			return NULL;
 	}
 
-	disk = bdev->bd_disk;
-	if (!kobject_get_unless_zero(&disk_to_dev(disk)->kobj))
-		goto bdput;
-	if ((disk->flags & (GENHD_FL_UP | GENHD_FL_HIDDEN)) != GENHD_FL_UP)
-		goto put_disk;
-	if (!try_module_get(bdev->bd_disk->fops->owner))
-		goto put_disk;
+	/* switch from the inode reference to a device mode one: */
+	bdev = &BDEV_I(inode)->bdev;
+	if (!kobject_get_unless_zero(&bdev->bd_device.kobj))
+		bdev = NULL;
+	iput(inode);
+
+	if (!bdev)
+		return NULL;
+	if ((bdev->bd_disk->flags & GENHD_FL_HIDDEN) ||
+	    !try_module_get(bdev->bd_disk->fops->owner)) {
+		put_device(&bdev->bd_device);
+		return NULL;
+	}
+
 	return bdev;
-put_disk:
-	put_disk(disk);
-bdput:
-	bdput(bdev);
-	return NULL;
 }
 
 void blkdev_put_no_open(struct block_device *bdev)
 {
 	module_put(bdev->bd_disk->fops->owner);
-	put_disk(bdev->bd_disk);
-	bdput(bdev);
+	put_device(&bdev->bd_device);
 }
 
 /**
@@ -1409,7 +1224,7 @@ struct block_device *blkdev_get_by_dev(dev_t dev, fmode_t mode, void *holder)
 
 	mutex_lock(&disk->open_mutex);
 	ret = -ENXIO;
-	if (!(disk->flags & GENHD_FL_UP))
+	if (!disk_live(disk))
 		goto abort_claiming;
 	if (bdev_is_partition(bdev))
 		ret = blkdev_get_part(bdev, mode);
diff --git a/fs/f2fs/sysfs.c b/fs/f2fs/sysfs.c
index 6642246206bd..daad532a4e2b 100644
--- a/fs/f2fs/sysfs.c
+++ b/fs/f2fs/sysfs.c
@@ -378,7 +378,7 @@ out:
 		ret = kstrtol(name, 10, &data);
 		if (ret)
 			return ret;
-		if (data >= IOPRIO_BE_NR || data < 0)
+		if (data >= IOPRIO_NR_LEVELS || data < 0)
 			return -EINVAL;
 
 		cprc->ckpt_thread_ioprio = IOPRIO_PRIO_VALUE(class, data);
diff --git a/fs/fat/fatent.c b/fs/fat/fatent.c
index 860e884e56e8..978ac6751aeb 100644
--- a/fs/fat/fatent.c
+++ b/fs/fat/fatent.c
@@ -5,6 +5,7 @@
 
 #include <linux/blkdev.h>
 #include <linux/sched/signal.h>
+#include <linux/backing-dev-defs.h>
 #include "fat.h"
 
 struct fatent_operations {
diff --git a/fs/nilfs2/super.c b/fs/nilfs2/super.c
index 4abd928b0bc8..f6b2d280aab5 100644
--- a/fs/nilfs2/super.c
+++ b/fs/nilfs2/super.c
@@ -1053,7 +1053,7 @@ nilfs_fill_super(struct super_block *sb, void *data, int silent)
 	sb->s_time_gran = 1;
 	sb->s_max_links = NILFS_LINK_MAX;
 
-	sb->s_bdi = bdi_get(sb->s_bdev->bd_bdi);
+	sb->s_bdi = bdi_get(sb->s_bdev->bd_disk->bdi);
 
 	err = load_nilfs(nilfs, sb);
 	if (err)
diff --git a/fs/squashfs/block.c b/fs/squashfs/block.c
index 855f0e87066d..2db8bcf7ff85 100644
--- a/fs/squashfs/block.c
+++ b/fs/squashfs/block.c
@@ -49,8 +49,7 @@ static int copy_bio_to_actor(struct bio *bio,
 
 		bytes_to_copy = min_t(int, bytes_to_copy,
 				      req_length - copied_bytes);
-		memcpy(actor_addr + actor_offset,
-		       page_address(bvec->bv_page) + bvec->bv_offset + offset,
+		memcpy(actor_addr + actor_offset, bvec_virt(bvec) + offset,
 		       bytes_to_copy);
 
 		actor_offset += bytes_to_copy;
@@ -177,7 +176,7 @@ int squashfs_read_data(struct super_block *sb, u64 index, int length,
 			goto out_free_bio;
 		}
 		/* Extract the length of the metadata block */
-		data = page_address(bvec->bv_page) + bvec->bv_offset;
+		data = bvec_virt(bvec);
 		length = data[offset];
 		if (offset < bvec->bv_len - 1) {
 			length |= data[offset + 1] << 8;
@@ -186,7 +185,7 @@ int squashfs_read_data(struct super_block *sb, u64 index, int length,
 				res = -EIO;
 				goto out_free_bio;
 			}
-			data = page_address(bvec->bv_page) + bvec->bv_offset;
+			data = bvec_virt(bvec);
 			length |= data[0] << 8;
 		}
 		bio_free_pages(bio);
diff --git a/fs/squashfs/lz4_wrapper.c b/fs/squashfs/lz4_wrapper.c
index 233d5582fbee..b685b6238316 100644
--- a/fs/squashfs/lz4_wrapper.c
+++ b/fs/squashfs/lz4_wrapper.c
@@ -101,7 +101,7 @@ static int lz4_uncompress(struct squashfs_sb_info *msblk, void *strm,
 	while (bio_next_segment(bio, &iter_all)) {
 		int avail = min(bytes, ((int)bvec->bv_len) - offset);
 
-		data = page_address(bvec->bv_page) + bvec->bv_offset;
+		data = bvec_virt(bvec);
 		memcpy(buff, data + offset, avail);
 		buff += avail;
 		bytes -= avail;
diff --git a/fs/squashfs/lzo_wrapper.c b/fs/squashfs/lzo_wrapper.c
index 97bb7d92ddcd..cb510a631968 100644
--- a/fs/squashfs/lzo_wrapper.c
+++ b/fs/squashfs/lzo_wrapper.c
@@ -76,7 +76,7 @@ static int lzo_uncompress(struct squashfs_sb_info *msblk, void *strm,
 	while (bio_next_segment(bio, &iter_all)) {
 		int avail = min(bytes, ((int)bvec->bv_len) - offset);
 
-		data = page_address(bvec->bv_page) + bvec->bv_offset;
+		data = bvec_virt(bvec);
 		memcpy(buff, data + offset, avail);
 		buff += avail;
 		bytes -= avail;
diff --git a/fs/squashfs/xz_wrapper.c b/fs/squashfs/xz_wrapper.c
index e80419aed862..68f6d09bb3a2 100644
--- a/fs/squashfs/xz_wrapper.c
+++ b/fs/squashfs/xz_wrapper.c
@@ -146,7 +146,7 @@ static int squashfs_xz_uncompress(struct squashfs_sb_info *msblk, void *strm,
 			}
 
 			avail = min(length, ((int)bvec->bv_len) - offset);
-			data = page_address(bvec->bv_page) + bvec->bv_offset;
+			data = bvec_virt(bvec);
 			length -= avail;
 			stream->buf.in = data + offset;
 			stream->buf.in_size = avail;
diff --git a/fs/squashfs/zlib_wrapper.c b/fs/squashfs/zlib_wrapper.c
index bcb881ec47f2..a20e9042146b 100644
--- a/fs/squashfs/zlib_wrapper.c
+++ b/fs/squashfs/zlib_wrapper.c
@@ -76,7 +76,7 @@ static int zlib_uncompress(struct squashfs_sb_info *msblk, void *strm,
 			}
 
 			avail = min(length, ((int)bvec->bv_len) - offset);
-			data = page_address(bvec->bv_page) + bvec->bv_offset;
+			data = bvec_virt(bvec);
 			length -= avail;
 			stream->next_in = data + offset;
 			stream->avail_in = avail;
diff --git a/fs/squashfs/zstd_wrapper.c b/fs/squashfs/zstd_wrapper.c
index b7cb1faa652d..0015cf8b5582 100644
--- a/fs/squashfs/zstd_wrapper.c
+++ b/fs/squashfs/zstd_wrapper.c
@@ -94,7 +94,7 @@ static int zstd_uncompress(struct squashfs_sb_info *msblk, void *strm,
 			}
 
 			avail = min(length, ((int)bvec->bv_len) - offset);
-			data = page_address(bvec->bv_page) + bvec->bv_offset;
+			data = bvec_virt(bvec);
 			length -= avail;
 			in_buf.src = data + offset;
 			in_buf.size = avail;
diff --git a/fs/super.c b/fs/super.c
index 91b7f156735b..bcef3a6f4c4b 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -1203,7 +1203,7 @@ static int set_bdev_super(struct super_block *s, void *data)
 {
 	s->s_bdev = data;
 	s->s_dev = s->s_bdev->bd_dev;
-	s->s_bdi = bdi_get(s->s_bdev->bd_bdi);
+	s->s_bdi = bdi_get(s->s_bdev->bd_disk->bdi);
 
 	if (blk_queue_stable_writes(s->s_bdev->bd_disk->queue))
 		s->s_iflags |= SB_I_STABLE_WRITES;
diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c
index 8ff42b3585e0..3ab73567a0f5 100644
--- a/fs/xfs/xfs_buf.c
+++ b/fs/xfs/xfs_buf.c
@@ -844,7 +844,7 @@ xfs_buf_readahead_map(
 {
 	struct xfs_buf		*bp;
 
-	if (bdi_read_congested(target->bt_bdev->bd_bdi))
+	if (bdi_read_congested(target->bt_bdev->bd_disk->bdi))
 		return;
 
 	xfs_buf_read_map(target, map, nmaps,