From 210a03c9d51aa0e6e6f06980116e3256da8d4c48 Mon Sep 17 00:00:00 2001
From: Christian Brauner <brauner@kernel.org>
Date: Thu, 28 Mar 2024 13:27:24 +0100
Subject: fs: claw back a few FMODE_* bits

There's a bunch of flags that are purely based on what the file
operations support while also never being conditionally set or unset.
IOW, they're not subject to change for individual files. Imho, such
flags don't need to live in f_mode they might as well live in the fops
structs itself. And the fops struct already has that lonely
mmap_supported_flags member. We might as well turn that into a generic
fop_flags member and move a few flags from FMODE_* space into FOP_*
space. That gets us four FMODE_* bits back and the ability for new
static flags that are about file ops to not have to live in FMODE_*
space but in their own FOP_* space. It's not the most beautiful thing
ever but it gets the job done. Yes, there'll be an additional pointer
chase but hopefully that won't matter for these flags.

I suspect there's a few more we can move into there and that we can also
redirect a bunch of new flag suggestions that follow this pattern into
the fop_flags field instead of f_mode.

Link: https://lore.kernel.org/r/20240328-gewendet-spargel-aa60a030ef74@brauner
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Jan Kara <jack@suse.cz>
Reviewed-by: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 block/bdev.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'block/bdev.c')

diff --git a/block/bdev.c b/block/bdev.c
index 7a5f611c3d2e..1322dfe32c5d 100644
--- a/block/bdev.c
+++ b/block/bdev.c
@@ -904,7 +904,7 @@ int bdev_open(struct block_device *bdev, blk_mode_t mode, void *holder,
 		disk_unblock_events(disk);
 
 	bdev_file->f_flags |= O_LARGEFILE;
-	bdev_file->f_mode |= FMODE_BUF_RASYNC | FMODE_CAN_ODIRECT;
+	bdev_file->f_mode |= FMODE_CAN_ODIRECT;
 	if (bdev_nowait(bdev))
 		bdev_file->f_mode |= FMODE_NOWAIT;
 	bdev_file->f_mapping = bdev->bd_inode->i_mapping;
-- 
cgit v1.2.3


From ead083aeeed9df44fab9227e47688f7305c3a233 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Thu, 18 Apr 2024 00:34:31 -0400
Subject: set_blocksize(): switch to passing struct file *

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 block/bdev.c            | 11 +++++++----
 block/ioctl.c           | 21 ++++++++++++---------
 drivers/block/pktcdvd.c |  2 +-
 fs/btrfs/dev-replace.c  |  2 +-
 fs/btrfs/volumes.c      |  4 ++--
 fs/ext4/super.c         |  2 +-
 fs/reiserfs/journal.c   |  5 ++---
 fs/xfs/xfs_buf.c        |  2 +-
 include/linux/blkdev.h  |  2 +-
 9 files changed, 28 insertions(+), 23 deletions(-)

(limited to 'block/bdev.c')

diff --git a/block/bdev.c b/block/bdev.c
index b8e32d933a63..a329ff9be11d 100644
--- a/block/bdev.c
+++ b/block/bdev.c
@@ -144,8 +144,11 @@ static void set_init_blocksize(struct block_device *bdev)
 	bdev->bd_inode->i_blkbits = blksize_bits(bsize);
 }
 
-int set_blocksize(struct block_device *bdev, int size)
+int set_blocksize(struct file *file, int size)
 {
+	struct inode *inode = file->f_mapping->host;
+	struct block_device *bdev = I_BDEV(inode);
+
 	/* Size must be a power of two, and between 512 and PAGE_SIZE */
 	if (size > PAGE_SIZE || size < 512 || !is_power_of_2(size))
 		return -EINVAL;
@@ -155,9 +158,9 @@ int set_blocksize(struct block_device *bdev, int size)
 		return -EINVAL;
 
 	/* Don't change the size if it is same as current */
-	if (bdev->bd_inode->i_blkbits != blksize_bits(size)) {
+	if (inode->i_blkbits != blksize_bits(size)) {
 		sync_blockdev(bdev);
-		bdev->bd_inode->i_blkbits = blksize_bits(size);
+		inode->i_blkbits = blksize_bits(size);
 		kill_bdev(bdev);
 	}
 	return 0;
@@ -167,7 +170,7 @@ EXPORT_SYMBOL(set_blocksize);
 
 int sb_set_blocksize(struct super_block *sb, int size)
 {
-	if (set_blocksize(sb->s_bdev, size))
+	if (set_blocksize(sb->s_bdev_file, size))
 		return 0;
 	/* If we get here, we know size is power of two
 	 * and it's value is between 512 and PAGE_SIZE */
diff --git a/block/ioctl.c b/block/ioctl.c
index a9028a2c2db5..1c800364bc70 100644
--- a/block/ioctl.c
+++ b/block/ioctl.c
@@ -473,11 +473,14 @@ static int compat_hdio_getgeo(struct block_device *bdev,
 #endif
 
 /* set the logical block size */
-static int blkdev_bszset(struct block_device *bdev, blk_mode_t mode,
+static int blkdev_bszset(struct file *file, blk_mode_t mode,
 		int __user *argp)
 {
+	// this one might be file_inode(file)->i_rdev - a rare valid
+	// use of file_inode() for those.
+	dev_t dev = I_BDEV(file->f_mapping->host)->bd_dev;
+	struct file *excl_file;
 	int ret, n;
-	struct file *file;
 
 	if (!capable(CAP_SYS_ADMIN))
 		return -EACCES;
@@ -487,13 +490,13 @@ static int blkdev_bszset(struct block_device *bdev, blk_mode_t mode,
 		return -EFAULT;
 
 	if (mode & BLK_OPEN_EXCL)
-		return set_blocksize(bdev, n);
+		return set_blocksize(file, n);
 
-	file = bdev_file_open_by_dev(bdev->bd_dev, mode, &bdev, NULL);
-	if (IS_ERR(file))
+	excl_file = bdev_file_open_by_dev(dev, mode, &dev, NULL);
+	if (IS_ERR(excl_file))
 		return -EBUSY;
-	ret = set_blocksize(bdev, n);
-	fput(file);
+	ret = set_blocksize(excl_file, n);
+	fput(excl_file);
 	return ret;
 }
 
@@ -621,7 +624,7 @@ long blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg)
 	case BLKBSZGET: /* get block device soft block size (cf. BLKSSZGET) */
 		return put_int(argp, block_size(bdev));
 	case BLKBSZSET:
-		return blkdev_bszset(bdev, mode, argp);
+		return blkdev_bszset(file, mode, argp);
 	case BLKGETSIZE64:
 		return put_u64(argp, bdev_nr_bytes(bdev));
 
@@ -681,7 +684,7 @@ long compat_blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg)
 	case BLKBSZGET_32: /* get the logical block size (cf. BLKSSZGET) */
 		return put_int(argp, bdev_logical_block_size(bdev));
 	case BLKBSZSET_32:
-		return blkdev_bszset(bdev, mode, argp);
+		return blkdev_bszset(file, mode, argp);
 	case BLKGETSIZE64_32:
 		return put_u64(argp, bdev_nr_bytes(bdev));
 
diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c
index 05933f25b397..8a2ce8070010 100644
--- a/drivers/block/pktcdvd.c
+++ b/drivers/block/pktcdvd.c
@@ -2215,7 +2215,7 @@ static int pkt_open_dev(struct pktcdvd_device *pd, bool write)
 		}
 		dev_info(ddev, "%lukB available on disc\n", lba << 1);
 	}
-	set_blocksize(file_bdev(bdev_file), CD_FRAMESIZE);
+	set_blocksize(bdev_file, CD_FRAMESIZE);
 
 	return 0;
 
diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c
index 7696beec4c21..7130040d92ab 100644
--- a/fs/btrfs/dev-replace.c
+++ b/fs/btrfs/dev-replace.c
@@ -316,7 +316,7 @@ static int btrfs_init_dev_replace_tgtdev(struct btrfs_fs_info *fs_info,
 	set_bit(BTRFS_DEV_STATE_IN_FS_METADATA, &device->dev_state);
 	set_bit(BTRFS_DEV_STATE_REPLACE_TGT, &device->dev_state);
 	device->dev_stats_valid = 1;
-	set_blocksize(device->bdev, BTRFS_BDEV_BLOCKSIZE);
+	set_blocksize(bdev_file, BTRFS_BDEV_BLOCKSIZE);
 	device->fs_devices = fs_devices;
 
 	ret = btrfs_get_dev_zone_info(device, false);
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 43af5a9fb547..65c03ddecc59 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -483,7 +483,7 @@ btrfs_get_bdev_and_sb(const char *device_path, blk_mode_t flags, void *holder,
 	if (flush)
 		sync_blockdev(bdev);
 	if (holder) {
-		ret = set_blocksize(bdev, BTRFS_BDEV_BLOCKSIZE);
+		ret = set_blocksize(*bdev_file, BTRFS_BDEV_BLOCKSIZE);
 		if (ret) {
 			fput(*bdev_file);
 			goto error;
@@ -2717,7 +2717,7 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path
 	set_bit(BTRFS_DEV_STATE_IN_FS_METADATA, &device->dev_state);
 	clear_bit(BTRFS_DEV_STATE_REPLACE_TGT, &device->dev_state);
 	device->dev_stats_valid = 1;
-	set_blocksize(device->bdev, BTRFS_BDEV_BLOCKSIZE);
+	set_blocksize(device->bdev_file, BTRFS_BDEV_BLOCKSIZE);
 
 	if (seeding_dev) {
 		btrfs_clear_sb_rdonly(sb);
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 044135796f2b..9988b3a40b42 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -5873,7 +5873,7 @@ static struct file *ext4_get_journal_blkdev(struct super_block *sb,
 
 	sb_block = EXT4_MIN_BLOCK_SIZE / blocksize;
 	offset = EXT4_MIN_BLOCK_SIZE % blocksize;
-	set_blocksize(bdev, blocksize);
+	set_blocksize(bdev_file, blocksize);
 	bh = __bread(bdev, sb_block, blocksize);
 	if (!bh) {
 		ext4_msg(sb, KERN_ERR, "couldn't read superblock of "
diff --git a/fs/reiserfs/journal.c b/fs/reiserfs/journal.c
index e539ccd39e1e..e477ee0ff35d 100644
--- a/fs/reiserfs/journal.c
+++ b/fs/reiserfs/journal.c
@@ -2626,8 +2626,7 @@ static int journal_init_dev(struct super_block *super,
 					 MAJOR(jdev), MINOR(jdev), result);
 			return result;
 		} else if (jdev != super->s_dev)
-			set_blocksize(file_bdev(journal->j_bdev_file),
-				      super->s_blocksize);
+			set_blocksize(journal->j_bdev_file, super->s_blocksize);
 
 		return 0;
 	}
@@ -2643,7 +2642,7 @@ static int journal_init_dev(struct super_block *super,
 		return result;
 	}
 
-	set_blocksize(file_bdev(journal->j_bdev_file), super->s_blocksize);
+	set_blocksize(journal->j_bdev_file, super->s_blocksize);
 	reiserfs_info(super,
 		      "journal_init_dev: journal device: %pg\n",
 		      file_bdev(journal->j_bdev_file));
diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c
index f0fa02264eda..2dc0eacb0999 100644
--- a/fs/xfs/xfs_buf.c
+++ b/fs/xfs/xfs_buf.c
@@ -2043,7 +2043,7 @@ xfs_setsize_buftarg(
 	btp->bt_meta_sectorsize = sectorsize;
 	btp->bt_meta_sectormask = sectorsize - 1;
 
-	if (set_blocksize(btp->bt_bdev, sectorsize)) {
+	if (set_blocksize(btp->bt_bdev_file, sectorsize)) {
 		xfs_warn(btp->bt_mount,
 			"Cannot set_blocksize to %u on device %pg",
 			sectorsize, btp->bt_bdev);
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 172c91879999..20c749b2ebc2 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1474,7 +1474,7 @@ static inline void bio_end_io_acct(struct bio *bio, unsigned long start_time)
 }
 
 int bdev_read_only(struct block_device *bdev);
-int set_blocksize(struct block_device *bdev, int size);
+int set_blocksize(struct file *file, int size);
 
 int lookup_bdev(const char *pathname, dev_t *dev);
 
-- 
cgit v1.2.3


From d18a8679581e8d1166b68e211d16c5349ae8c38c Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Thu, 2 May 2024 17:36:32 -0400
Subject: make set_blocksize() fail unless block device is opened exclusive

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 Documentation/filesystems/porting.rst | 7 +++++++
 block/bdev.c                          | 3 +++
 2 files changed, 10 insertions(+)

(limited to 'block/bdev.c')

diff --git a/Documentation/filesystems/porting.rst b/Documentation/filesystems/porting.rst
index 1be76ef117b3..5503d5c614a7 100644
--- a/Documentation/filesystems/porting.rst
+++ b/Documentation/filesystems/porting.rst
@@ -1134,3 +1134,10 @@ superblock of the main block device, i.e., the one stored in sb->s_bdev. Block
 device freezing now works for any block device owned by a given superblock, not
 just the main block device. The get_active_super() helper and bd_fsfreeze_sb
 pointer are gone.
+
+---
+
+**mandatory**
+
+set_blocksize() takes opened struct file instead of struct block_device now
+and it *must* be opened exclusive.
diff --git a/block/bdev.c b/block/bdev.c
index a329ff9be11d..a89bce368b64 100644
--- a/block/bdev.c
+++ b/block/bdev.c
@@ -157,6 +157,9 @@ int set_blocksize(struct file *file, int size)
 	if (size < bdev_logical_block_size(bdev))
 		return -EINVAL;
 
+	if (!file->private_data)
+		return -EINVAL;
+
 	/* Don't change the size if it is same as current */
 	if (inode->i_blkbits != blksize_bits(size)) {
 		sync_blockdev(bdev);
-- 
cgit v1.2.3


From 1116b9fa15c09748ae05d2365a305fa22671eb1e Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Fri, 12 Apr 2024 01:07:29 -0400
Subject: bdev: infrastructure for flags

Replace bd_partno with a 32bit field (__bd_flags).  The lower 8 bits
contain the partition number, the upper 24 are for flags.

Helpers: bdev_{test,set,clear}_flag(bdev, flag), with atomic_or()
and atomic_andnot() used to set/clear.

NOTE: this commit does not actually move any flags over there - they
are still bool fields.  As the result, it shifts the fields wrt
cacheline boundaries; that's going to be restored once the first
3 flags are dealt with.

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 block/bdev.c              |  2 +-
 include/linux/blk_types.h |  3 ++-
 include/linux/blkdev.h    | 17 ++++++++++++++++-
 3 files changed, 19 insertions(+), 3 deletions(-)

(limited to 'block/bdev.c')

diff --git a/block/bdev.c b/block/bdev.c
index 7a5f611c3d2e..2ec223315500 100644
--- a/block/bdev.c
+++ b/block/bdev.c
@@ -411,7 +411,7 @@ struct block_device *bdev_alloc(struct gendisk *disk, u8 partno)
 	mutex_init(&bdev->bd_fsfreeze_mutex);
 	spin_lock_init(&bdev->bd_size_lock);
 	mutex_init(&bdev->bd_holder_lock);
-	bdev->bd_partno = partno;
+	atomic_set(&bdev->__bd_flags, partno);
 	bdev->bd_inode = inode;
 	bdev->bd_queue = disk->queue;
 	if (partno)
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index cb1526ec44b5..04f92737ab08 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -45,8 +45,9 @@ struct block_device {
 	struct request_queue *	bd_queue;
 	struct disk_stats __percpu *bd_stats;
 	unsigned long		bd_stamp;
+	atomic_t		__bd_flags;	// partition number + flags
+#define BD_PARTNO		255	// lower 8 bits; assign-once
 	bool			bd_read_only;	/* read-only policy */
-	u8			bd_partno;
 	bool			bd_write_holder;
 	bool			bd_has_submit_bio;
 	dev_t			bd_dev;
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 32549d675955..99917e5860fd 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -722,7 +722,22 @@ void disk_uevent(struct gendisk *disk, enum kobject_action action);
 
 static inline u8 bdev_partno(const struct block_device *bdev)
 {
-	return bdev->bd_partno;
+	return atomic_read(&bdev->__bd_flags) & BD_PARTNO;
+}
+
+static inline bool bdev_test_flag(const struct block_device *bdev, unsigned flag)
+{
+	return atomic_read(&bdev->__bd_flags) & flag;
+}
+
+static inline void bdev_set_flag(struct block_device *bdev, unsigned flag)
+{
+	atomic_or(flag, &bdev->__bd_flags);
+}
+
+static inline void bdev_clear_flag(struct block_device *bdev, unsigned flag)
+{
+	atomic_andnot(flag, &bdev->__bd_flags);
 }
 
 static inline int get_disk_ro(struct gendisk *disk)
-- 
cgit v1.2.3


From 4c80105e3909b3aff634a40daa9c29059ce03d6a Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Fri, 12 Apr 2024 01:18:24 -0400
Subject: bdev: move ->bd_write_holder into ->__bd_flags

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 block/bdev.c              | 9 +++++----
 include/linux/blk_types.h | 2 +-
 2 files changed, 6 insertions(+), 5 deletions(-)

(limited to 'block/bdev.c')

diff --git a/block/bdev.c b/block/bdev.c
index 2ec223315500..9df9a59f0900 100644
--- a/block/bdev.c
+++ b/block/bdev.c
@@ -624,7 +624,7 @@ static void bd_end_claim(struct block_device *bdev, void *holder)
 		bdev->bd_holder = NULL;
 		bdev->bd_holder_ops = NULL;
 		mutex_unlock(&bdev->bd_holder_lock);
-		if (bdev->bd_write_holder)
+		if (bdev_test_flag(bdev, BD_WRITE_HOLDER))
 			unblock = true;
 	}
 	if (!whole->bd_holders)
@@ -640,7 +640,7 @@ static void bd_end_claim(struct block_device *bdev, void *holder)
 	 */
 	if (unblock) {
 		disk_unblock_events(bdev->bd_disk);
-		bdev->bd_write_holder = false;
+		bdev_clear_flag(bdev, BD_WRITE_HOLDER);
 	}
 }
 
@@ -892,9 +892,10 @@ int bdev_open(struct block_device *bdev, blk_mode_t mode, void *holder,
 		 * writeable reference is too fragile given the way @mode is
 		 * used in blkdev_get/put().
 		 */
-		if ((mode & BLK_OPEN_WRITE) && !bdev->bd_write_holder &&
+		if ((mode & BLK_OPEN_WRITE) &&
+		    !bdev_test_flag(bdev, BD_WRITE_HOLDER) &&
 		    (disk->event_flags & DISK_EVENT_FLAG_BLOCK_ON_EXCL_WRITE)) {
-			bdev->bd_write_holder = true;
+			bdev_set_flag(bdev, BD_WRITE_HOLDER);
 			unblock_events = false;
 		}
 	}
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index f70dd31cbcd1..e45a490d488e 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -48,7 +48,7 @@ struct block_device {
 	atomic_t		__bd_flags;	// partition number + flags
 #define BD_PARTNO		255	// lower 8 bits; assign-once
 #define BD_READ_ONLY		(1u<<8) // read-only policy
-	bool			bd_write_holder;
+#define BD_WRITE_HOLDER		(1u<<9)
 	bool			bd_has_submit_bio;
 	dev_t			bd_dev;
 	struct inode		*bd_inode;	/* will die */
-- 
cgit v1.2.3


From ac2b6f9dee8f41d5e9162959a8bbd2c8047ee382 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Fri, 12 Apr 2024 01:21:45 -0400
Subject: bdev: move ->bd_has_subit_bio to ->__bd_flags

In bdev_alloc() we have all flags initialized to false, so
assignment to ->bh_has_submit_bio n there is a no-op unless
we have partno != 0 and flag already set on entire device.

In device_add_disk() we have just allocated the block_device
in question and it had been a full-device one, so the flag
is guaranteed to be still clear when we get to assignment.

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 block/bdev.c              | 6 ++----
 block/blk-core.c          | 4 ++--
 block/genhd.c             | 3 ++-
 include/linux/blk_types.h | 2 +-
 4 files changed, 7 insertions(+), 8 deletions(-)

(limited to 'block/bdev.c')

diff --git a/block/bdev.c b/block/bdev.c
index 9df9a59f0900..fae30eae7741 100644
--- a/block/bdev.c
+++ b/block/bdev.c
@@ -414,10 +414,8 @@ struct block_device *bdev_alloc(struct gendisk *disk, u8 partno)
 	atomic_set(&bdev->__bd_flags, 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;
+	if (partno && bdev_test_flag(disk->part0, BD_HAS_SUBMIT_BIO))
+		bdev_set_flag(bdev, BD_HAS_SUBMIT_BIO);
 	bdev->bd_stats = alloc_percpu(struct disk_stats);
 	if (!bdev->bd_stats) {
 		iput(inode);
diff --git a/block/blk-core.c b/block/blk-core.c
index 20322abc6082..f61460b65408 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -615,7 +615,7 @@ static void __submit_bio(struct bio *bio)
 	if (unlikely(!blk_crypto_bio_prep(&bio)))
 		return;
 
-	if (!bio->bi_bdev->bd_has_submit_bio) {
+	if (!bdev_test_flag(bio->bi_bdev, BD_HAS_SUBMIT_BIO)) {
 		blk_mq_submit_bio(bio);
 	} else if (likely(bio_queue_enter(bio) == 0)) {
 		struct gendisk *disk = bio->bi_bdev->bd_disk;
@@ -723,7 +723,7 @@ void submit_bio_noacct_nocheck(struct bio *bio)
 	 */
 	if (current->bio_list)
 		bio_list_add(&current->bio_list[0], bio);
-	else if (!bio->bi_bdev->bd_has_submit_bio)
+	else if (!bdev_test_flag(bio->bi_bdev, BD_HAS_SUBMIT_BIO))
 		__submit_bio_noacct_mq(bio);
 	else
 		__submit_bio_noacct(bio);
diff --git a/block/genhd.c b/block/genhd.c
index bb29a68e1d67..19cd1a31fa80 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -413,7 +413,8 @@ int __must_check device_add_disk(struct device *parent, struct gendisk *disk,
 	elevator_init_mq(disk->queue);
 
 	/* Mark bdev as having a submit_bio, if needed */
-	disk->part0->bd_has_submit_bio = disk->fops->submit_bio != NULL;
+	if (disk->fops->submit_bio)
+		bdev_set_flag(disk->part0, BD_HAS_SUBMIT_BIO);
 
 	/*
 	 * If the driver provides an explicit major number it also must provide
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index e45a490d488e..11b9e8eeb79f 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -49,7 +49,7 @@ struct block_device {
 #define BD_PARTNO		255	// lower 8 bits; assign-once
 #define BD_READ_ONLY		(1u<<8) // read-only policy
 #define BD_WRITE_HOLDER		(1u<<9)
-	bool			bd_has_submit_bio;
+#define BD_HAS_SUBMIT_BIO	(1u<<10)
 	dev_t			bd_dev;
 	struct inode		*bd_inode;	/* will die */
 
-- 
cgit v1.2.3


From 186ddac2072a8134798d72635d1ed0f29889369d Mon Sep 17 00:00:00 2001
From: Yu Kuai <yukuai3@huawei.com>
Date: Thu, 11 Apr 2024 15:53:43 +0100
Subject: block: move two helpers into bdev.c

disk_live() and block_size() access bd_inode directly, prepare to remove
the field bd_inode from block_device, and only access bd_inode in block
layer.

Signed-off-by: Yu Kuai <yukuai3@huawei.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Jan Kara <jack@suse.cz>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Link: https://lore.kernel.org/r/20240411145346.2516848-8-viro@zeniv.linux.org.uk
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 block/bdev.c           | 12 ++++++++++++
 include/linux/blkdev.h | 12 ++----------
 2 files changed, 14 insertions(+), 10 deletions(-)

(limited to 'block/bdev.c')

diff --git a/block/bdev.c b/block/bdev.c
index a89bce368b64..536233ac3e99 100644
--- a/block/bdev.c
+++ b/block/bdev.c
@@ -1257,6 +1257,18 @@ void bdev_statx_dioalign(struct inode *inode, struct kstat *stat)
 	blkdev_put_no_open(bdev);
 }
 
+bool disk_live(struct gendisk *disk)
+{
+	return !inode_unhashed(disk->part0->bd_inode);
+}
+EXPORT_SYMBOL_GPL(disk_live);
+
+unsigned int block_size(struct block_device *bdev)
+{
+	return 1 << bdev->bd_inode->i_blkbits;
+}
+EXPORT_SYMBOL_GPL(block_size);
+
 static int __init setup_bdev_allow_write_mounted(char *str)
 {
 	if (kstrtobool(str, &bdev_allow_write_mounted))
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 20c749b2ebc2..99ac98ed9548 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -211,11 +211,6 @@ struct gendisk {
 	struct blk_independent_access_ranges *ia_ranges;
 };
 
-static inline bool disk_live(struct gendisk *disk)
-{
-	return !inode_unhashed(disk->part0->bd_inode);
-}
-
 /**
  * disk_openers - returns how many openers are there for a disk
  * @disk: disk to check
@@ -1364,11 +1359,6 @@ static inline unsigned int blksize_bits(unsigned int size)
 	return order_base_2(size >> SECTOR_SHIFT) + SECTOR_SHIFT;
 }
 
-static inline unsigned int block_size(struct block_device *bdev)
-{
-	return 1 << bdev->bd_inode->i_blkbits;
-}
-
 int kblockd_schedule_work(struct work_struct *work);
 int kblockd_mod_delayed_work_on(int cpu, struct delayed_work *dwork, unsigned long delay);
 
@@ -1536,6 +1526,8 @@ void blkdev_put_no_open(struct block_device *bdev);
 
 struct block_device *I_BDEV(struct inode *inode);
 struct block_device *file_bdev(struct file *bdev_file);
+bool disk_live(struct gendisk *disk);
+unsigned int block_size(struct block_device *bdev);
 
 #ifdef CONFIG_BLOCK
 void invalidate_bdev(struct block_device *bdev);
-- 
cgit v1.2.3


From 2638c20876734f986fd91cfbe196483835ed7095 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Sun, 28 Apr 2024 19:01:39 -0400
Subject: missing helpers: bdev_unhash(), bdev_drop()

bdev_unhash(): make block device invisible to lookups by device number
bdev_drop(): drop reference to associated inode.

Both are internal, for use by genhd and partition-related code - similar
to bdev_add().  The logics in there (especially the lifetime-related
parts of it) ought to be cleaned up, but that's a separate story; here
we just encapsulate getting to associated inode.

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 block/bdev.c            | 10 ++++++++++
 block/blk.h             |  2 ++
 block/genhd.c           |  6 +++---
 block/partitions/core.c |  6 +++---
 4 files changed, 18 insertions(+), 6 deletions(-)

(limited to 'block/bdev.c')

diff --git a/block/bdev.c b/block/bdev.c
index 536233ac3e99..28e6f0423857 100644
--- a/block/bdev.c
+++ b/block/bdev.c
@@ -451,6 +451,16 @@ void bdev_add(struct block_device *bdev, dev_t dev)
 	insert_inode_hash(bdev->bd_inode);
 }
 
+void bdev_unhash(struct block_device *bdev)
+{
+	remove_inode_hash(bdev->bd_inode);
+}
+
+void bdev_drop(struct block_device *bdev)
+{
+	iput(bdev->bd_inode);
+}
+
 long nr_blockdev_pages(void)
 {
 	struct inode *inode;
diff --git a/block/blk.h b/block/blk.h
index d9f584984bc4..e3347e1030d5 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -428,6 +428,8 @@ static inline int blkdev_zone_mgmt_ioctl(struct block_device *bdev,
 
 struct block_device *bdev_alloc(struct gendisk *disk, u8 partno);
 void bdev_add(struct block_device *bdev, dev_t dev);
+void bdev_unhash(struct block_device *bdev);
+void bdev_drop(struct block_device *bdev);
 
 int blk_alloc_ext_minor(void);
 void blk_free_ext_minor(unsigned int minor);
diff --git a/block/genhd.c b/block/genhd.c
index bb29a68e1d67..93f5118b7d41 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -656,7 +656,7 @@ void del_gendisk(struct gendisk *disk)
 	 */
 	mutex_lock(&disk->open_mutex);
 	xa_for_each(&disk->part_tbl, idx, part)
-		remove_inode_hash(part->bd_inode);
+		bdev_unhash(part);
 	mutex_unlock(&disk->open_mutex);
 
 	/*
@@ -1191,7 +1191,7 @@ static void disk_release(struct device *dev)
 	if (test_bit(GD_ADDED, &disk->state) && disk->fops->free_disk)
 		disk->fops->free_disk(disk);
 
-	iput(disk->part0->bd_inode);	/* frees the disk */
+	bdev_drop(disk->part0);	/* frees the disk */
 }
 
 static int block_uevent(const struct device *dev, struct kobj_uevent_env *env)
@@ -1381,7 +1381,7 @@ out_erase_part0:
 out_destroy_part_tbl:
 	xa_destroy(&disk->part_tbl);
 	disk->part0->bd_disk = NULL;
-	iput(disk->part0->bd_inode);
+	bdev_drop(disk->part0);
 out_free_bdi:
 	bdi_put(disk->bdi);
 out_free_bioset:
diff --git a/block/partitions/core.c b/block/partitions/core.c
index b11e88c82c8c..2b75e325c63b 100644
--- a/block/partitions/core.c
+++ b/block/partitions/core.c
@@ -243,7 +243,7 @@ static const struct attribute_group *part_attr_groups[] = {
 static void part_release(struct device *dev)
 {
 	put_disk(dev_to_bdev(dev)->bd_disk);
-	iput(dev_to_bdev(dev)->bd_inode);
+	bdev_drop(dev_to_bdev(dev));
 }
 
 static int part_uevent(const struct device *dev, struct kobj_uevent_env *env)
@@ -469,7 +469,7 @@ int bdev_del_partition(struct gendisk *disk, int partno)
 	 * Just delete the partition and invalidate it.
 	 */
 
-	remove_inode_hash(part->bd_inode);
+	bdev_unhash(part);
 	invalidate_bdev(part);
 	drop_partition(part);
 	ret = 0;
@@ -655,7 +655,7 @@ rescan:
 		 * it cannot be looked up any more even when openers
 		 * still hold references.
 		 */
-		remove_inode_hash(part->bd_inode);
+		bdev_unhash(part);
 
 		/*
 		 * If @disk->open_partitions isn't elevated but there's
-- 
cgit v1.2.3


From e33aef2c58577f51ec22736843a652576ce0ef7a Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Thu, 11 Apr 2024 15:53:36 +0100
Subject: block_device: add a pointer to struct address_space (page cache of
 bdev)

points to ->i_data of coallocated inode.

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Link: https://lore.kernel.org/r/20240411145346.2516848-1-viro@zeniv.linux.org.uk
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 block/bdev.c              | 1 +
 include/linux/blk_types.h | 1 +
 2 files changed, 2 insertions(+)

(limited to 'block/bdev.c')

diff --git a/block/bdev.c b/block/bdev.c
index 28e6f0423857..8e19101cbbb0 100644
--- a/block/bdev.c
+++ b/block/bdev.c
@@ -419,6 +419,7 @@ struct block_device *bdev_alloc(struct gendisk *disk, u8 partno)
 	mutex_init(&bdev->bd_holder_lock);
 	bdev->bd_partno = partno;
 	bdev->bd_inode = inode;
+	bdev->bd_mapping = &inode->i_data;
 	bdev->bd_queue = disk->queue;
 	if (partno)
 		bdev->bd_has_submit_bio = disk->part0->bd_has_submit_bio;
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index cb1526ec44b5..6438c75cbb35 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -51,6 +51,7 @@ struct block_device {
 	bool			bd_has_submit_bio;
 	dev_t			bd_dev;
 	struct inode		*bd_inode;	/* will die */
+	struct address_space	*bd_mapping;	/* page cache */
 
 	atomic_t		bd_openers;
 	spinlock_t		bd_size_lock; /* for bd_inode->i_size updates */
-- 
cgit v1.2.3


From 224941e8379a0de8652ffec768cc8394f0b1cb95 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Thu, 11 Apr 2024 15:53:37 +0100
Subject: use ->bd_mapping instead of ->bd_inode->i_mapping

Just the low-hanging fruit...

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Link: https://lore.kernel.org/r/20240411145346.2516848-2-viro@zeniv.linux.org.uk
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 block/bdev.c                | 18 +++++++++---------
 block/blk-zoned.c           |  4 ++--
 block/genhd.c               |  2 +-
 block/ioctl.c               |  4 ++--
 block/partitions/core.c     |  2 +-
 drivers/md/bcache/super.c   |  2 +-
 drivers/scsi/scsicam.c      |  2 +-
 fs/btrfs/disk-io.c          |  6 +++---
 fs/btrfs/volumes.c          |  2 +-
 fs/btrfs/zoned.c            |  2 +-
 fs/buffer.c                 |  2 +-
 fs/cramfs/inode.c           |  2 +-
 fs/erofs/data.c             |  2 +-
 fs/ext4/dir.c               |  2 +-
 fs/ext4/ext4_jbd2.c         |  2 +-
 fs/ext4/super.c             |  6 +++---
 fs/jbd2/journal.c           |  2 +-
 include/linux/buffer_head.h |  4 ++--
 include/linux/jbd2.h        |  4 ++--
 19 files changed, 35 insertions(+), 35 deletions(-)

(limited to 'block/bdev.c')

diff --git a/block/bdev.c b/block/bdev.c
index 8e19101cbbb0..00017af92a51 100644
--- a/block/bdev.c
+++ b/block/bdev.c
@@ -76,7 +76,7 @@ static void bdev_write_inode(struct block_device *bdev)
 /* Kill _all_ buffers and pagecache , dirty or not.. */
 static void kill_bdev(struct block_device *bdev)
 {
-	struct address_space *mapping = bdev->bd_inode->i_mapping;
+	struct address_space *mapping = bdev->bd_mapping;
 
 	if (mapping_empty(mapping))
 		return;
@@ -88,7 +88,7 @@ static void kill_bdev(struct block_device *bdev)
 /* Invalidate clean unused buffers and pagecache. */
 void invalidate_bdev(struct block_device *bdev)
 {
-	struct address_space *mapping = bdev->bd_inode->i_mapping;
+	struct address_space *mapping = bdev->bd_mapping;
 
 	if (mapping->nrpages) {
 		invalidate_bh_lrus();
@@ -116,7 +116,7 @@ int truncate_bdev_range(struct block_device *bdev, blk_mode_t mode,
 			goto invalidate;
 	}
 
-	truncate_inode_pages_range(bdev->bd_inode->i_mapping, lstart, lend);
+	truncate_inode_pages_range(bdev->bd_mapping, lstart, lend);
 	if (!(mode & BLK_OPEN_EXCL))
 		bd_abort_claiming(bdev, truncate_bdev_range);
 	return 0;
@@ -126,7 +126,7 @@ invalidate:
 	 * Someone else has handle exclusively open. Try invalidating instead.
 	 * The 'end' argument is inclusive so the rounding is safe.
 	 */
-	return invalidate_inode_pages2_range(bdev->bd_inode->i_mapping,
+	return invalidate_inode_pages2_range(bdev->bd_mapping,
 					     lstart >> PAGE_SHIFT,
 					     lend >> PAGE_SHIFT);
 }
@@ -198,7 +198,7 @@ int sync_blockdev_nowait(struct block_device *bdev)
 {
 	if (!bdev)
 		return 0;
-	return filemap_flush(bdev->bd_inode->i_mapping);
+	return filemap_flush(bdev->bd_mapping);
 }
 EXPORT_SYMBOL_GPL(sync_blockdev_nowait);
 
@@ -210,13 +210,13 @@ int sync_blockdev(struct block_device *bdev)
 {
 	if (!bdev)
 		return 0;
-	return filemap_write_and_wait(bdev->bd_inode->i_mapping);
+	return filemap_write_and_wait(bdev->bd_mapping);
 }
 EXPORT_SYMBOL(sync_blockdev);
 
 int sync_blockdev_range(struct block_device *bdev, loff_t lstart, loff_t lend)
 {
-	return filemap_write_and_wait_range(bdev->bd_inode->i_mapping,
+	return filemap_write_and_wait_range(bdev->bd_mapping,
 			lstart, lend);
 }
 EXPORT_SYMBOL(sync_blockdev_range);
@@ -445,7 +445,7 @@ void bdev_set_nr_sectors(struct block_device *bdev, sector_t sectors)
 void bdev_add(struct block_device *bdev, dev_t dev)
 {
 	if (bdev_stable_writes(bdev))
-		mapping_set_stable_writes(bdev->bd_inode->i_mapping);
+		mapping_set_stable_writes(bdev->bd_mapping);
 	bdev->bd_dev = dev;
 	bdev->bd_inode->i_rdev = dev;
 	bdev->bd_inode->i_ino = dev;
@@ -925,7 +925,7 @@ int bdev_open(struct block_device *bdev, blk_mode_t mode, void *holder,
 		bdev_file->f_mode |= FMODE_NOWAIT;
 	if (mode & BLK_OPEN_RESTRICT_WRITES)
 		bdev_file->f_mode |= FMODE_WRITE_RESTRICTED;
-	bdev_file->f_mapping = bdev->bd_inode->i_mapping;
+	bdev_file->f_mapping = bdev->bd_mapping;
 	bdev_file->f_wb_err = filemap_sample_wb_err(bdev_file->f_mapping);
 	bdev_file->private_data = holder;
 
diff --git a/block/blk-zoned.c b/block/blk-zoned.c
index da0f4b2a8fa0..b008bcd4889c 100644
--- a/block/blk-zoned.c
+++ b/block/blk-zoned.c
@@ -398,7 +398,7 @@ int blkdev_zone_mgmt_ioctl(struct block_device *bdev, blk_mode_t mode,
 		op = REQ_OP_ZONE_RESET;
 
 		/* Invalidate the page cache, including dirty pages. */
-		filemap_invalidate_lock(bdev->bd_inode->i_mapping);
+		filemap_invalidate_lock(bdev->bd_mapping);
 		ret = blkdev_truncate_zone_range(bdev, mode, &zrange);
 		if (ret)
 			goto fail;
@@ -420,7 +420,7 @@ int blkdev_zone_mgmt_ioctl(struct block_device *bdev, blk_mode_t mode,
 
 fail:
 	if (cmd == BLKRESETZONE)
-		filemap_invalidate_unlock(bdev->bd_inode->i_mapping);
+		filemap_invalidate_unlock(bdev->bd_mapping);
 
 	return ret;
 }
diff --git a/block/genhd.c b/block/genhd.c
index 93f5118b7d41..2bf05bd0f071 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -745,7 +745,7 @@ void invalidate_disk(struct gendisk *disk)
 	struct block_device *bdev = disk->part0;
 
 	invalidate_bdev(bdev);
-	bdev->bd_inode->i_mapping->wb_err = 0;
+	bdev->bd_mapping->wb_err = 0;
 	set_capacity(disk, 0);
 }
 EXPORT_SYMBOL(invalidate_disk);
diff --git a/block/ioctl.c b/block/ioctl.c
index 1c800364bc70..7c13d8bed453 100644
--- a/block/ioctl.c
+++ b/block/ioctl.c
@@ -152,12 +152,12 @@ static int blk_ioctl_secure_erase(struct block_device *bdev, blk_mode_t mode,
 	if (start + len > bdev_nr_bytes(bdev))
 		return -EINVAL;
 
-	filemap_invalidate_lock(bdev->bd_inode->i_mapping);
+	filemap_invalidate_lock(bdev->bd_mapping);
 	err = truncate_bdev_range(bdev, mode, start, start + len - 1);
 	if (!err)
 		err = blkdev_issue_secure_erase(bdev, start >> 9, len >> 9,
 						GFP_KERNEL);
-	filemap_invalidate_unlock(bdev->bd_inode->i_mapping);
+	filemap_invalidate_unlock(bdev->bd_mapping);
 	return err;
 }
 
diff --git a/block/partitions/core.c b/block/partitions/core.c
index 2b75e325c63b..63ee317dfff0 100644
--- a/block/partitions/core.c
+++ b/block/partitions/core.c
@@ -704,7 +704,7 @@ EXPORT_SYMBOL_GPL(bdev_disk_changed);
 
 void *read_part_sector(struct parsed_partitions *state, sector_t n, Sector *p)
 {
-	struct address_space *mapping = state->disk->part0->bd_inode->i_mapping;
+	struct address_space *mapping = state->disk->part0->bd_mapping;
 	struct folio *folio;
 
 	if (n >= get_capacity(state->disk)) {
diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c
index 0ee5e17ae2dd..277ad958cf53 100644
--- a/drivers/md/bcache/super.c
+++ b/drivers/md/bcache/super.c
@@ -171,7 +171,7 @@ static const char *read_super(struct cache_sb *sb, struct block_device *bdev,
 	struct page *page;
 	unsigned int i;
 
-	page = read_cache_page_gfp(bdev->bd_inode->i_mapping,
+	page = read_cache_page_gfp(bdev->bd_mapping,
 				   SB_OFFSET >> PAGE_SHIFT, GFP_KERNEL);
 	if (IS_ERR(page))
 		return "IO error";
diff --git a/drivers/scsi/scsicam.c b/drivers/scsi/scsicam.c
index e2c7d8ef205f..dd69342bbe78 100644
--- a/drivers/scsi/scsicam.c
+++ b/drivers/scsi/scsicam.c
@@ -32,7 +32,7 @@
  */
 unsigned char *scsi_bios_ptable(struct block_device *dev)
 {
-	struct address_space *mapping = bdev_whole(dev)->bd_inode->i_mapping;
+	struct address_space *mapping = bdev_whole(dev)->bd_mapping;
 	unsigned char *res = NULL;
 	struct folio *folio;
 
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 3df5477d48a8..f10e894b0bf5 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -3651,7 +3651,7 @@ struct btrfs_super_block *btrfs_read_dev_one_super(struct block_device *bdev,
 	struct btrfs_super_block *super;
 	struct page *page;
 	u64 bytenr, bytenr_orig;
-	struct address_space *mapping = bdev->bd_inode->i_mapping;
+	struct address_space *mapping = bdev->bd_mapping;
 	int ret;
 
 	bytenr_orig = btrfs_sb_offset(copy_num);
@@ -3738,7 +3738,7 @@ static int write_dev_supers(struct btrfs_device *device,
 			    struct btrfs_super_block *sb, int max_mirrors)
 {
 	struct btrfs_fs_info *fs_info = device->fs_info;
-	struct address_space *mapping = device->bdev->bd_inode->i_mapping;
+	struct address_space *mapping = device->bdev->bd_mapping;
 	SHASH_DESC_ON_STACK(shash, fs_info->csum_shash);
 	int i;
 	int errors = 0;
@@ -3855,7 +3855,7 @@ static int wait_dev_supers(struct btrfs_device *device, int max_mirrors)
 		    device->commit_total_bytes)
 			break;
 
-		page = find_get_page(device->bdev->bd_inode->i_mapping,
+		page = find_get_page(device->bdev->bd_mapping,
 				     bytenr >> PAGE_SHIFT);
 		if (!page) {
 			errors++;
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 65c03ddecc59..33d357e5f9c5 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -1290,7 +1290,7 @@ static struct btrfs_super_block *btrfs_read_disk_super(struct block_device *bdev
 		return ERR_PTR(-EINVAL);
 
 	/* pull in the page with our super */
-	page = read_cache_page_gfp(bdev->bd_inode->i_mapping, index, GFP_KERNEL);
+	page = read_cache_page_gfp(bdev->bd_mapping, index, GFP_KERNEL);
 
 	if (IS_ERR(page))
 		return ERR_CAST(page);
diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c
index 4cba80b34387..9b43fa493219 100644
--- a/fs/btrfs/zoned.c
+++ b/fs/btrfs/zoned.c
@@ -118,7 +118,7 @@ static int sb_write_pointer(struct block_device *bdev, struct blk_zone *zones,
 		return -ENOENT;
 	} else if (full[0] && full[1]) {
 		/* Compare two super blocks */
-		struct address_space *mapping = bdev->bd_inode->i_mapping;
+		struct address_space *mapping = bdev->bd_mapping;
 		struct page *page[BTRFS_NR_SB_LOG_ZONES];
 		struct btrfs_super_block *super[BTRFS_NR_SB_LOG_ZONES];
 		int i;
diff --git a/fs/buffer.c b/fs/buffer.c
index 4f73d23c2c46..d5a0932ae68d 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -1463,7 +1463,7 @@ __bread_gfp(struct block_device *bdev, sector_t block,
 {
 	struct buffer_head *bh;
 
-	gfp |= mapping_gfp_constraint(bdev->bd_inode->i_mapping, ~__GFP_FS);
+	gfp |= mapping_gfp_constraint(bdev->bd_mapping, ~__GFP_FS);
 
 	/*
 	 * Prefer looping in the allocator rather than here, at least that
diff --git a/fs/cramfs/inode.c b/fs/cramfs/inode.c
index 9901057a15ba..460690ca0174 100644
--- a/fs/cramfs/inode.c
+++ b/fs/cramfs/inode.c
@@ -183,7 +183,7 @@ static int next_buffer;
 static void *cramfs_blkdev_read(struct super_block *sb, unsigned int offset,
 				unsigned int len)
 {
-	struct address_space *mapping = sb->s_bdev->bd_inode->i_mapping;
+	struct address_space *mapping = sb->s_bdev->bd_mapping;
 	struct file_ra_state ra = {};
 	struct page *pages[BLKS_PER_BUF];
 	unsigned i, blocknr, buffer;
diff --git a/fs/erofs/data.c b/fs/erofs/data.c
index e1a170e45c70..5fc03c1e2757 100644
--- a/fs/erofs/data.c
+++ b/fs/erofs/data.c
@@ -68,7 +68,7 @@ void erofs_init_metabuf(struct erofs_buf *buf, struct super_block *sb)
 	if (erofs_is_fscache_mode(sb))
 		buf->mapping = EROFS_SB(sb)->s_fscache->inode->i_mapping;
 	else
-		buf->mapping = sb->s_bdev->bd_inode->i_mapping;
+		buf->mapping = sb->s_bdev->bd_mapping;
 }
 
 void *erofs_read_metabuf(struct erofs_buf *buf, struct super_block *sb,
diff --git a/fs/ext4/dir.c b/fs/ext4/dir.c
index 3985f8c33f95..ff4514e4626b 100644
--- a/fs/ext4/dir.c
+++ b/fs/ext4/dir.c
@@ -192,7 +192,7 @@ static int ext4_readdir(struct file *file, struct dir_context *ctx)
 					(PAGE_SHIFT - inode->i_blkbits);
 			if (!ra_has_index(&file->f_ra, index))
 				page_cache_sync_readahead(
-					sb->s_bdev->bd_inode->i_mapping,
+					sb->s_bdev->bd_mapping,
 					&file->f_ra, file,
 					index, 1);
 			file->f_ra.prev_pos = (loff_t)index << PAGE_SHIFT;
diff --git a/fs/ext4/ext4_jbd2.c b/fs/ext4/ext4_jbd2.c
index 5d8055161acd..da4a82456383 100644
--- a/fs/ext4/ext4_jbd2.c
+++ b/fs/ext4/ext4_jbd2.c
@@ -206,7 +206,7 @@ static void ext4_journal_abort_handle(const char *caller, unsigned int line,
 
 static void ext4_check_bdev_write_error(struct super_block *sb)
 {
-	struct address_space *mapping = sb->s_bdev->bd_inode->i_mapping;
+	struct address_space *mapping = sb->s_bdev->bd_mapping;
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
 	int err;
 
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index b255f798f449..02042eb91806 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -244,7 +244,7 @@ static struct buffer_head *__ext4_sb_bread_gfp(struct super_block *sb,
 struct buffer_head *ext4_sb_bread(struct super_block *sb, sector_t block,
 				   blk_opf_t op_flags)
 {
-	gfp_t gfp = mapping_gfp_constraint(sb->s_bdev->bd_inode->i_mapping,
+	gfp_t gfp = mapping_gfp_constraint(sb->s_bdev->bd_mapping,
 			~__GFP_FS) | __GFP_MOVABLE;
 
 	return __ext4_sb_bread_gfp(sb, block, op_flags, gfp);
@@ -253,7 +253,7 @@ struct buffer_head *ext4_sb_bread(struct super_block *sb, sector_t block,
 struct buffer_head *ext4_sb_bread_unmovable(struct super_block *sb,
 					    sector_t block)
 {
-	gfp_t gfp = mapping_gfp_constraint(sb->s_bdev->bd_inode->i_mapping,
+	gfp_t gfp = mapping_gfp_constraint(sb->s_bdev->bd_mapping,
 			~__GFP_FS);
 
 	return __ext4_sb_bread_gfp(sb, block, 0, gfp);
@@ -5556,7 +5556,7 @@ static int __ext4_fill_super(struct fs_context *fc, struct super_block *sb)
 	 * used to detect the metadata async write error.
 	 */
 	spin_lock_init(&sbi->s_bdev_wb_lock);
-	errseq_check_and_advance(&sb->s_bdev->bd_inode->i_mapping->wb_err,
+	errseq_check_and_advance(&sb->s_bdev->bd_mapping->wb_err,
 				 &sbi->s_bdev_wb_err);
 	EXT4_SB(sb)->s_mount_state |= EXT4_ORPHAN_FS;
 	ext4_orphan_cleanup(sb, es);
diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
index b6c114c11b97..03c4b9214f56 100644
--- a/fs/jbd2/journal.c
+++ b/fs/jbd2/journal.c
@@ -2009,7 +2009,7 @@ static int __jbd2_journal_erase(journal_t *journal, unsigned int flags)
 		byte_count = (block_stop - block_start + 1) *
 				journal->j_blocksize;
 
-		truncate_inode_pages_range(journal->j_dev->bd_inode->i_mapping,
+		truncate_inode_pages_range(journal->j_dev->bd_mapping,
 				byte_start, byte_stop);
 
 		if (flags & JBD2_JOURNAL_FLUSH_DISCARD) {
diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h
index d78454a4dd1f..e58a0d63409a 100644
--- a/include/linux/buffer_head.h
+++ b/include/linux/buffer_head.h
@@ -338,7 +338,7 @@ static inline struct buffer_head *getblk_unmovable(struct block_device *bdev,
 {
 	gfp_t gfp;
 
-	gfp = mapping_gfp_constraint(bdev->bd_inode->i_mapping, ~__GFP_FS);
+	gfp = mapping_gfp_constraint(bdev->bd_mapping, ~__GFP_FS);
 	gfp |= __GFP_NOFAIL;
 
 	return bdev_getblk(bdev, block, size, gfp);
@@ -349,7 +349,7 @@ static inline struct buffer_head *__getblk(struct block_device *bdev,
 {
 	gfp_t gfp;
 
-	gfp = mapping_gfp_constraint(bdev->bd_inode->i_mapping, ~__GFP_FS);
+	gfp = mapping_gfp_constraint(bdev->bd_mapping, ~__GFP_FS);
 	gfp |= __GFP_MOVABLE | __GFP_NOFAIL;
 
 	return bdev_getblk(bdev, block, size, gfp);
diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h
index 971f3e826e15..ac31c37816f7 100644
--- a/include/linux/jbd2.h
+++ b/include/linux/jbd2.h
@@ -1696,7 +1696,7 @@ static inline void jbd2_journal_abort_handle(handle_t *handle)
 
 static inline void jbd2_init_fs_dev_write_error(journal_t *journal)
 {
-	struct address_space *mapping = journal->j_fs_dev->bd_inode->i_mapping;
+	struct address_space *mapping = journal->j_fs_dev->bd_mapping;
 
 	/*
 	 * Save the original wb_err value of client fs's bdev mapping which
@@ -1707,7 +1707,7 @@ static inline void jbd2_init_fs_dev_write_error(journal_t *journal)
 
 static inline int jbd2_check_fs_dev_write_error(journal_t *journal)
 {
-	struct address_space *mapping = journal->j_fs_dev->bd_inode->i_mapping;
+	struct address_space *mapping = journal->j_fs_dev->bd_mapping;
 
 	return errseq_check(&mapping->wb_err,
 			    READ_ONCE(journal->j_fs_dev_wb_err));
-- 
cgit v1.2.3


From df65f1660b6141f0b051d2439cc99222a6ae865b Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Sun, 28 Apr 2024 19:09:12 -0400
Subject: block/bdev.c: use the knowledge of inode/bdev coallocation

Here we know that bdevfs inodes are coallocated with struct block_device
and we can get to ->bd_inode value without any dereferencing.  Introduce
an inlined helper (static, *not* exported, purely internal for bdev.c)
that gets an associated inode by block_device - BD_INODE(bdev).

NOTE: leave it static; nobody outside of block/bdev.c has any business
playing with that.

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 block/bdev.c | 32 +++++++++++++++++++-------------
 1 file changed, 19 insertions(+), 13 deletions(-)

(limited to 'block/bdev.c')

diff --git a/block/bdev.c b/block/bdev.c
index 00017af92a51..a8c66cc1d6b8 100644
--- a/block/bdev.c
+++ b/block/bdev.c
@@ -43,6 +43,11 @@ static inline struct bdev_inode *BDEV_I(struct inode *inode)
 	return container_of(inode, struct bdev_inode, vfs_inode);
 }
 
+static inline struct inode *BD_INODE(struct block_device *bdev)
+{
+	return &container_of(bdev, struct bdev_inode, bdev)->vfs_inode;
+}
+
 struct block_device *I_BDEV(struct inode *inode)
 {
 	return &BDEV_I(inode)->bdev;
@@ -57,7 +62,7 @@ EXPORT_SYMBOL(file_bdev);
 
 static void bdev_write_inode(struct block_device *bdev)
 {
-	struct inode *inode = bdev->bd_inode;
+	struct inode *inode = BD_INODE(bdev);
 	int ret;
 
 	spin_lock(&inode->i_lock);
@@ -134,14 +139,14 @@ invalidate:
 static void set_init_blocksize(struct block_device *bdev)
 {
 	unsigned int bsize = bdev_logical_block_size(bdev);
-	loff_t size = i_size_read(bdev->bd_inode);
+	loff_t size = i_size_read(BD_INODE(bdev));
 
 	while (bsize < PAGE_SIZE) {
 		if (size & bsize)
 			break;
 		bsize <<= 1;
 	}
-	bdev->bd_inode->i_blkbits = blksize_bits(bsize);
+	BD_INODE(bdev)->i_blkbits = blksize_bits(bsize);
 }
 
 int set_blocksize(struct file *file, int size)
@@ -437,29 +442,30 @@ struct block_device *bdev_alloc(struct gendisk *disk, u8 partno)
 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);
+	i_size_write(BD_INODE(bdev), (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)
 {
+	struct inode *inode = BD_INODE(bdev);
 	if (bdev_stable_writes(bdev))
 		mapping_set_stable_writes(bdev->bd_mapping);
 	bdev->bd_dev = dev;
-	bdev->bd_inode->i_rdev = dev;
-	bdev->bd_inode->i_ino = dev;
-	insert_inode_hash(bdev->bd_inode);
+	inode->i_rdev = dev;
+	inode->i_ino = dev;
+	insert_inode_hash(inode);
 }
 
 void bdev_unhash(struct block_device *bdev)
 {
-	remove_inode_hash(bdev->bd_inode);
+	remove_inode_hash(BD_INODE(bdev));
 }
 
 void bdev_drop(struct block_device *bdev)
 {
-	iput(bdev->bd_inode);
+	iput(BD_INODE(bdev));
 }
 
 long nr_blockdev_pages(void)
@@ -987,13 +993,13 @@ struct file *bdev_file_open_by_dev(dev_t dev, blk_mode_t mode, void *holder,
 		return ERR_PTR(-ENXIO);
 
 	flags = blk_to_file_flags(mode);
-	bdev_file = alloc_file_pseudo_noaccount(bdev->bd_inode,
+	bdev_file = alloc_file_pseudo_noaccount(BD_INODE(bdev),
 			blockdev_mnt, "", flags | O_LARGEFILE, &def_blk_fops);
 	if (IS_ERR(bdev_file)) {
 		blkdev_put_no_open(bdev);
 		return bdev_file;
 	}
-	ihold(bdev->bd_inode);
+	ihold(BD_INODE(bdev));
 
 	ret = bdev_open(bdev, mode, holder, hops, bdev_file);
 	if (ret) {
@@ -1270,13 +1276,13 @@ void bdev_statx_dioalign(struct inode *inode, struct kstat *stat)
 
 bool disk_live(struct gendisk *disk)
 {
-	return !inode_unhashed(disk->part0->bd_inode);
+	return !inode_unhashed(BD_INODE(disk->part0));
 }
 EXPORT_SYMBOL_GPL(disk_live);
 
 unsigned int block_size(struct block_device *bdev)
 {
-	return 1 << bdev->bd_inode->i_blkbits;
+	return 1 << BD_INODE(bdev)->i_blkbits;
 }
 EXPORT_SYMBOL_GPL(block_size);
 
-- 
cgit v1.2.3


From 203c1ce0bb063d1620698e39637b64f2d09c1368 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Sun, 28 Apr 2024 20:47:14 -0400
Subject: RIP ->bd_inode

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 block/bdev.c              | 1 -
 include/linux/blk_types.h | 1 -
 2 files changed, 2 deletions(-)

(limited to 'block/bdev.c')

diff --git a/block/bdev.c b/block/bdev.c
index a8c66cc1d6b8..0849a9cfa2b6 100644
--- a/block/bdev.c
+++ b/block/bdev.c
@@ -423,7 +423,6 @@ struct block_device *bdev_alloc(struct gendisk *disk, u8 partno)
 	spin_lock_init(&bdev->bd_size_lock);
 	mutex_init(&bdev->bd_holder_lock);
 	bdev->bd_partno = partno;
-	bdev->bd_inode = inode;
 	bdev->bd_mapping = &inode->i_data;
 	bdev->bd_queue = disk->queue;
 	if (partno)
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index 6438c75cbb35..5616d059cb23 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -50,7 +50,6 @@ struct block_device {
 	bool			bd_write_holder;
 	bool			bd_has_submit_bio;
 	dev_t			bd_dev;
-	struct inode		*bd_inode;	/* will die */
 	struct address_space	*bd_mapping;	/* page cache */
 
 	atomic_t		bd_openers;
-- 
cgit v1.2.3