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
  ...

5 files changed, 50 insertions, 61 deletions

diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c
index 5e86bea0a950..5f10965fd72b 100644
--- a/fs/btrfs/dev-replace.c
+++ b/fs/btrfs/dev-replace.c
@@ -257,8 +257,8 @@ static int btrfs_init_dev_replace_tgtdev(struct btrfs_fs_info *fs_info,
 		return -EINVAL;
 	}
 
-	bdev = blkdev_get_by_path(device_path, FMODE_WRITE | FMODE_EXCL,
-				  fs_info->bdev_holder);
+	bdev = blkdev_get_by_path(device_path, BLK_OPEN_WRITE,
+				  fs_info->bdev_holder, NULL);
 	if (IS_ERR(bdev)) {
 		btrfs_err(fs_info, "target device %s is invalid!", device_path);
 		return PTR_ERR(bdev);
@@ -315,7 +315,7 @@ static int btrfs_init_dev_replace_tgtdev(struct btrfs_fs_info *fs_info,
 	device->bdev = bdev;
 	set_bit(BTRFS_DEV_STATE_IN_FS_METADATA, &device->dev_state);
 	set_bit(BTRFS_DEV_STATE_REPLACE_TGT, &device->dev_state);
-	device->mode = FMODE_EXCL;
+	device->holder = fs_info->bdev_holder;
 	device->dev_stats_valid = 1;
 	set_blocksize(device->bdev, BTRFS_BDEV_BLOCKSIZE);
 	device->fs_devices = fs_devices;
@@ -334,7 +334,7 @@ static int btrfs_init_dev_replace_tgtdev(struct btrfs_fs_info *fs_info,
 	return 0;
 
 error:
-	blkdev_put(bdev, FMODE_EXCL);
+	blkdev_put(bdev, fs_info->bdev_holder);
 	return ret;
 }
 
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index edbbd5cf23fc..a895d105464b 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -2671,7 +2671,7 @@ static long btrfs_ioctl_rm_dev_v2(struct file *file, void __user *arg)
 	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
 	struct btrfs_ioctl_vol_args_v2 *vol_args;
 	struct block_device *bdev = NULL;
-	fmode_t mode;
+	void *holder;
 	int ret;
 	bool cancel = false;
 
@@ -2708,7 +2708,7 @@ static long btrfs_ioctl_rm_dev_v2(struct file *file, void __user *arg)
 		goto err_drop;
 
 	/* Exclusive operation is now claimed */
-	ret = btrfs_rm_device(fs_info, &args, &bdev, &mode);
+	ret = btrfs_rm_device(fs_info, &args, &bdev, &holder);
 
 	btrfs_exclop_finish(fs_info);
 
@@ -2723,7 +2723,7 @@ static long btrfs_ioctl_rm_dev_v2(struct file *file, void __user *arg)
 err_drop:
 	mnt_drop_write_file(file);
 	if (bdev)
-		blkdev_put(bdev, mode);
+		blkdev_put(bdev, holder);
 out:
 	btrfs_put_dev_args_from_path(&args);
 	kfree(vol_args);
@@ -2737,7 +2737,7 @@ static long btrfs_ioctl_rm_dev(struct file *file, void __user *arg)
 	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
 	struct btrfs_ioctl_vol_args *vol_args;
 	struct block_device *bdev = NULL;
-	fmode_t mode;
+	void *holder;
 	int ret;
 	bool cancel = false;
 
@@ -2764,7 +2764,7 @@ static long btrfs_ioctl_rm_dev(struct file *file, void __user *arg)
 	ret = exclop_start_or_cancel_reloc(fs_info, BTRFS_EXCLOP_DEV_REMOVE,
 					   cancel);
 	if (ret == 0) {
-		ret = btrfs_rm_device(fs_info, &args, &bdev, &mode);
+		ret = btrfs_rm_device(fs_info, &args, &bdev, &holder);
 		if (!ret)
 			btrfs_info(fs_info, "disk deleted %s", vol_args->name);
 		btrfs_exclop_finish(fs_info);
@@ -2772,7 +2772,7 @@ static long btrfs_ioctl_rm_dev(struct file *file, void __user *arg)
 
 	mnt_drop_write_file(file);
 	if (bdev)
-		blkdev_put(bdev, mode);
+		blkdev_put(bdev, holder);
 out:
 	btrfs_put_dev_args_from_path(&args);
 	kfree(vol_args);
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index 8b1c1225245e..f1dd172d8d5b 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -849,8 +849,7 @@ out:
  * All other options will be parsed on much later in the mount process and
  * only when we need to allocate a new super block.
  */
-static int btrfs_parse_device_options(const char *options, fmode_t flags,
-				      void *holder)
+static int btrfs_parse_device_options(const char *options, blk_mode_t flags)
 {
 	substring_t args[MAX_OPT_ARGS];
 	char *device_name, *opts, *orig, *p;
@@ -884,8 +883,7 @@ static int btrfs_parse_device_options(const char *options, fmode_t flags,
 				error = -ENOMEM;
 				goto out;
 			}
-			device = btrfs_scan_one_device(device_name, flags,
-					holder);
+			device = btrfs_scan_one_device(device_name, flags);
 			kfree(device_name);
 			if (IS_ERR(device)) {
 				error = PTR_ERR(device);
@@ -1442,12 +1440,9 @@ static struct dentry *btrfs_mount_root(struct file_system_type *fs_type,
 	struct btrfs_fs_devices *fs_devices = NULL;
 	struct btrfs_fs_info *fs_info = NULL;
 	void *new_sec_opts = NULL;
-	fmode_t mode = FMODE_READ;
+	blk_mode_t mode = sb_open_mode(flags);
 	int error = 0;
 
-	if (!(flags & SB_RDONLY))
-		mode |= FMODE_WRITE;
-
 	if (data) {
 		error = security_sb_eat_lsm_opts(data, &new_sec_opts);
 		if (error)
@@ -1477,13 +1472,13 @@ static struct dentry *btrfs_mount_root(struct file_system_type *fs_type,
 	}
 
 	mutex_lock(&uuid_mutex);
-	error = btrfs_parse_device_options(data, mode, fs_type);
+	error = btrfs_parse_device_options(data, mode);
 	if (error) {
 		mutex_unlock(&uuid_mutex);
 		goto error_fs_info;
 	}
 
-	device = btrfs_scan_one_device(device_name, mode, fs_type);
+	device = btrfs_scan_one_device(device_name, mode);
 	if (IS_ERR(device)) {
 		mutex_unlock(&uuid_mutex);
 		error = PTR_ERR(device);
@@ -2195,8 +2190,7 @@ static long btrfs_control_ioctl(struct file *file, unsigned int cmd,
 	switch (cmd) {
 	case BTRFS_IOC_SCAN_DEV:
 		mutex_lock(&uuid_mutex);
-		device = btrfs_scan_one_device(vol->name, FMODE_READ,
-					       &btrfs_root_fs_type);
+		device = btrfs_scan_one_device(vol->name, BLK_OPEN_READ);
 		ret = PTR_ERR_OR_ZERO(device);
 		mutex_unlock(&uuid_mutex);
 		break;
@@ -2210,8 +2204,7 @@ static long btrfs_control_ioctl(struct file *file, unsigned int cmd,
 		break;
 	case BTRFS_IOC_DEVICES_READY:
 		mutex_lock(&uuid_mutex);
-		device = btrfs_scan_one_device(vol->name, FMODE_READ,
-					       &btrfs_root_fs_type);
+		device = btrfs_scan_one_device(vol->name, BLK_OPEN_READ);
 		if (IS_ERR(device)) {
 			mutex_unlock(&uuid_mutex);
 			ret = PTR_ERR(device);
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 4193ace3fb5a..73f9ea7672db 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -510,13 +510,13 @@ static struct btrfs_fs_devices *find_fsid_with_metadata_uuid(
 
 
 static int
-btrfs_get_bdev_and_sb(const char *device_path, fmode_t flags, void *holder,
+btrfs_get_bdev_and_sb(const char *device_path, blk_mode_t flags, void *holder,
 		      int flush, struct block_device **bdev,
 		      struct btrfs_super_block **disk_super)
 {
 	int ret;
 
-	*bdev = blkdev_get_by_path(device_path, flags, holder);
+	*bdev = blkdev_get_by_path(device_path, flags, holder, NULL);
 
 	if (IS_ERR(*bdev)) {
 		ret = PTR_ERR(*bdev);
@@ -527,14 +527,14 @@ btrfs_get_bdev_and_sb(const char *device_path, fmode_t flags, void *holder,
 		sync_blockdev(*bdev);
 	ret = set_blocksize(*bdev, BTRFS_BDEV_BLOCKSIZE);
 	if (ret) {
-		blkdev_put(*bdev, flags);
+		blkdev_put(*bdev, holder);
 		goto error;
 	}
 	invalidate_bdev(*bdev);
 	*disk_super = btrfs_read_dev_super(*bdev);
 	if (IS_ERR(*disk_super)) {
 		ret = PTR_ERR(*disk_super);
-		blkdev_put(*bdev, flags);
+		blkdev_put(*bdev, holder);
 		goto error;
 	}
 
@@ -610,7 +610,7 @@ static int btrfs_free_stale_devices(dev_t devt, struct btrfs_device *skip_device
  * fs_devices->device_list_mutex here.
  */
 static int btrfs_open_one_device(struct btrfs_fs_devices *fs_devices,
-			struct btrfs_device *device, fmode_t flags,
+			struct btrfs_device *device, blk_mode_t flags,
 			void *holder)
 {
 	struct block_device *bdev;
@@ -662,7 +662,7 @@ static int btrfs_open_one_device(struct btrfs_fs_devices *fs_devices,
 
 	device->bdev = bdev;
 	clear_bit(BTRFS_DEV_STATE_IN_FS_METADATA, &device->dev_state);
-	device->mode = flags;
+	device->holder = holder;
 
 	fs_devices->open_devices++;
 	if (test_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state) &&
@@ -676,7 +676,7 @@ static int btrfs_open_one_device(struct btrfs_fs_devices *fs_devices,
 
 error_free_page:
 	btrfs_release_disk_super(disk_super);
-	blkdev_put(bdev, flags);
+	blkdev_put(bdev, holder);
 
 	return -EINVAL;
 }
@@ -1067,7 +1067,7 @@ static void __btrfs_free_extra_devids(struct btrfs_fs_devices *fs_devices,
 			continue;
 
 		if (device->bdev) {
-			blkdev_put(device->bdev, device->mode);
+			blkdev_put(device->bdev, device->holder);
 			device->bdev = NULL;
 			fs_devices->open_devices--;
 		}
@@ -1113,7 +1113,7 @@ static void btrfs_close_bdev(struct btrfs_device *device)
 		invalidate_bdev(device->bdev);
 	}
 
-	blkdev_put(device->bdev, device->mode);
+	blkdev_put(device->bdev, device->holder);
 }
 
 static void btrfs_close_one_device(struct btrfs_device *device)
@@ -1217,14 +1217,12 @@ void btrfs_close_devices(struct btrfs_fs_devices *fs_devices)
 }
 
 static int open_fs_devices(struct btrfs_fs_devices *fs_devices,
-				fmode_t flags, void *holder)
+				blk_mode_t flags, void *holder)
 {
 	struct btrfs_device *device;
 	struct btrfs_device *latest_dev = NULL;
 	struct btrfs_device *tmp_device;
 
-	flags |= FMODE_EXCL;
-
 	list_for_each_entry_safe(device, tmp_device, &fs_devices->devices,
 				 dev_list) {
 		int ret;
@@ -1267,7 +1265,7 @@ static int devid_cmp(void *priv, const struct list_head *a,
 }
 
 int btrfs_open_devices(struct btrfs_fs_devices *fs_devices,
-		       fmode_t flags, void *holder)
+		       blk_mode_t flags, void *holder)
 {
 	int ret;
 
@@ -1358,8 +1356,7 @@ int btrfs_forget_devices(dev_t devt)
  * and we are not allowed to call set_blocksize during the scan. The superblock
  * is read via pagecache
  */
-struct btrfs_device *btrfs_scan_one_device(const char *path, fmode_t flags,
-					   void *holder)
+struct btrfs_device *btrfs_scan_one_device(const char *path, blk_mode_t flags)
 {
 	struct btrfs_super_block *disk_super;
 	bool new_device_added = false;
@@ -1378,16 +1375,16 @@ struct btrfs_device *btrfs_scan_one_device(const char *path, fmode_t flags,
 	 */
 
 	/*
-	 * Avoid using flag |= FMODE_EXCL here, as the systemd-udev may
-	 * initiate the device scan which may race with the user's mount
-	 * or mkfs command, resulting in failure.
-	 * Since the device scan is solely for reading purposes, there is
-	 * no need for FMODE_EXCL. Additionally, the devices are read again
+	 * Avoid an exclusive open here, as the systemd-udev may initiate the
+	 * device scan which may race with the user's mount or mkfs command,
+	 * resulting in failure.
+	 * Since the device scan is solely for reading purposes, there is no
+	 * need for an exclusive open. Additionally, the devices are read again
 	 * during the mount process. It is ok to get some inconsistent
 	 * values temporarily, as the device paths of the fsid are the only
 	 * required information for assembling the volume.
 	 */
-	bdev = blkdev_get_by_path(path, flags, holder);
+	bdev = blkdev_get_by_path(path, flags, NULL, NULL);
 	if (IS_ERR(bdev))
 		return ERR_CAST(bdev);
 
@@ -1411,7 +1408,7 @@ struct btrfs_device *btrfs_scan_one_device(const char *path, fmode_t flags,
 	btrfs_release_disk_super(disk_super);
 
 error_bdev_put:
-	blkdev_put(bdev, flags);
+	blkdev_put(bdev, NULL);
 
 	return device;
 }
@@ -2098,7 +2095,7 @@ void btrfs_scratch_superblocks(struct btrfs_fs_info *fs_info,
 
 int btrfs_rm_device(struct btrfs_fs_info *fs_info,
 		    struct btrfs_dev_lookup_args *args,
-		    struct block_device **bdev, fmode_t *mode)
+		    struct block_device **bdev, void **holder)
 {
 	struct btrfs_trans_handle *trans;
 	struct btrfs_device *device;
@@ -2237,7 +2234,7 @@ int btrfs_rm_device(struct btrfs_fs_info *fs_info,
 	}
 
 	*bdev = device->bdev;
-	*mode = device->mode;
+	*holder = device->holder;
 	synchronize_rcu();
 	btrfs_free_device(device);
 
@@ -2391,7 +2388,7 @@ int btrfs_get_dev_args_from_path(struct btrfs_fs_info *fs_info,
 		return -ENOMEM;
 	}
 
-	ret = btrfs_get_bdev_and_sb(path, FMODE_READ, fs_info->bdev_holder, 0,
+	ret = btrfs_get_bdev_and_sb(path, BLK_OPEN_READ, NULL, 0,
 				    &bdev, &disk_super);
 	if (ret) {
 		btrfs_put_dev_args_from_path(args);
@@ -2405,7 +2402,7 @@ int btrfs_get_dev_args_from_path(struct btrfs_fs_info *fs_info,
 	else
 		memcpy(args->fsid, disk_super->fsid, BTRFS_FSID_SIZE);
 	btrfs_release_disk_super(disk_super);
-	blkdev_put(bdev, FMODE_READ);
+	blkdev_put(bdev, NULL);
 	return 0;
 }
 
@@ -2638,8 +2635,8 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path
 	if (sb_rdonly(sb) && !fs_devices->seeding)
 		return -EROFS;
 
-	bdev = blkdev_get_by_path(device_path, FMODE_WRITE | FMODE_EXCL,
-				  fs_info->bdev_holder);
+	bdev = blkdev_get_by_path(device_path, BLK_OPEN_WRITE,
+				  fs_info->bdev_holder, NULL);
 	if (IS_ERR(bdev))
 		return PTR_ERR(bdev);
 
@@ -2701,7 +2698,7 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path
 	device->commit_total_bytes = device->total_bytes;
 	set_bit(BTRFS_DEV_STATE_IN_FS_METADATA, &device->dev_state);
 	clear_bit(BTRFS_DEV_STATE_REPLACE_TGT, &device->dev_state);
-	device->mode = FMODE_EXCL;
+	device->holder = fs_info->bdev_holder;
 	device->dev_stats_valid = 1;
 	set_blocksize(device->bdev, BTRFS_BDEV_BLOCKSIZE);
 
@@ -2859,7 +2856,7 @@ error_free_zone:
 error_free_device:
 	btrfs_free_device(device);
 error:
-	blkdev_put(bdev, FMODE_EXCL);
+	blkdev_put(bdev, fs_info->bdev_holder);
 	if (locked) {
 		mutex_unlock(&uuid_mutex);
 		up_write(&sb->s_umount);
@@ -6898,7 +6895,7 @@ static struct btrfs_fs_devices *open_seed_devices(struct btrfs_fs_info *fs_info,
 	if (IS_ERR(fs_devices))
 		return fs_devices;
 
-	ret = open_fs_devices(fs_devices, FMODE_READ, fs_info->bdev_holder);
+	ret = open_fs_devices(fs_devices, BLK_OPEN_READ, fs_info->bdev_holder);
 	if (ret) {
 		free_fs_devices(fs_devices);
 		return ERR_PTR(ret);
diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h
index d44cb9d22d63..b8c51f16ba86 100644
--- a/fs/btrfs/volumes.h
+++ b/fs/btrfs/volumes.h
@@ -94,8 +94,8 @@ struct btrfs_device {
 
 	struct btrfs_zoned_device_info *zone_info;
 
-	/* the mode sent to blkdev_get */
-	fmode_t mode;
+	/* block device holder for blkdev_get/put */
+	void *holder;
 
 	/*
 	 * Device's major-minor number. Must be set even if the device is not
@@ -610,9 +610,8 @@ struct btrfs_block_group *btrfs_create_chunk(struct btrfs_trans_handle *trans,
 					    u64 type);
 void btrfs_mapping_tree_free(struct extent_map_tree *tree);
 int btrfs_open_devices(struct btrfs_fs_devices *fs_devices,
-		       fmode_t flags, void *holder);
-struct btrfs_device *btrfs_scan_one_device(const char *path,
-					   fmode_t flags, void *holder);
+		       blk_mode_t flags, void *holder);
+struct btrfs_device *btrfs_scan_one_device(const char *path, blk_mode_t flags);
 int btrfs_forget_devices(dev_t devt);
 void btrfs_close_devices(struct btrfs_fs_devices *fs_devices);
 void btrfs_free_extra_devids(struct btrfs_fs_devices *fs_devices);
@@ -630,7 +629,7 @@ struct btrfs_device *btrfs_alloc_device(struct btrfs_fs_info *fs_info,
 void btrfs_put_dev_args_from_path(struct btrfs_dev_lookup_args *args);
 int btrfs_rm_device(struct btrfs_fs_info *fs_info,
 		    struct btrfs_dev_lookup_args *args,
-		    struct block_device **bdev, fmode_t *mode);
+		    struct block_device **bdev, void **holder);
 void __exit btrfs_cleanup_fs_uuids(void);
 int btrfs_num_copies(struct btrfs_fs_info *fs_info, u64 logical, u64 len);
 int btrfs_grow_device(struct btrfs_trans_handle *trans,