Merge tag 'zonefs-6.3-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/dlemoal/zonefs

Pull zonefs updates from Damien Le Moal:

 - Reorganize zonefs code to split file related operations to a new
   fs/zonefs/file.c file (me)

 - Modify zonefs to use dynamically allocated inodes and dentries (using
   the inode and dentry caches) instead of statically allocating
   everything on mount. This saves a significant amount of memory for
   very large zoned block devices with 10s of thousands of zones (me)

 - Make zonefs_sb_ktype a const struct kobj_type (Thomas)

* tag 'zonefs-6.3-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/dlemoal/zonefs:
  zonefs: make kobj_type structure constant
  zonefs: Cache zone group directory inodes
  zonefs: Dynamically create file inodes when needed
  zonefs: Separate zone information from inode information
  zonefs: Reduce struct zonefs_inode_info size
  zonefs: Simplify IO error handling
  zonefs: Reorganize code

6 files changed, 1656 insertions, 1243 deletions

diff --git a/fs/zonefs/Makefile b/fs/zonefs/Makefile
index 9fe54f5319f222..645f7229de4a05 100644
--- a/fs/zonefs/Makefile
+++ b/fs/zonefs/Makefile
@@ -3,4 +3,4 @@ ccflags-y				+= -I$(src)
 
 obj-$(CONFIG_ZONEFS_FS) += zonefs.o
 
-zonefs-y	:= super.o sysfs.o
+zonefs-y	:= super.o file.o sysfs.o
diff --git a/fs/zonefs/file.c b/fs/zonefs/file.c
new file mode 100644
index 00000000000000..738b0e28d74b52
--- /dev/null
+++ b/fs/zonefs/file.c
@@ -0,0 +1,878 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Simple file system for zoned block devices exposing zones as files.
+ *
+ * Copyright (C) 2022 Western Digital Corporation or its affiliates.
+ */
+#include <linux/module.h>
+#include <linux/pagemap.h>
+#include <linux/iomap.h>
+#include <linux/init.h>
+#include <linux/slab.h>
+#include <linux/blkdev.h>
+#include <linux/statfs.h>
+#include <linux/writeback.h>
+#include <linux/quotaops.h>
+#include <linux/seq_file.h>
+#include <linux/parser.h>
+#include <linux/uio.h>
+#include <linux/mman.h>
+#include <linux/sched/mm.h>
+#include <linux/task_io_accounting_ops.h>
+
+#include "zonefs.h"
+
+#include "trace.h"
+
+static int zonefs_read_iomap_begin(struct inode *inode, loff_t offset,
+				   loff_t length, unsigned int flags,
+				   struct iomap *iomap, struct iomap *srcmap)
+{
+	struct zonefs_inode_info *zi = ZONEFS_I(inode);
+	struct zonefs_zone *z = zonefs_inode_zone(inode);
+	struct super_block *sb = inode->i_sb;
+	loff_t isize;
+
+	/*
+	 * All blocks are always mapped below EOF. If reading past EOF,
+	 * act as if there is a hole up to the file maximum size.
+	 */
+	mutex_lock(&zi->i_truncate_mutex);
+	iomap->bdev = inode->i_sb->s_bdev;
+	iomap->offset = ALIGN_DOWN(offset, sb->s_blocksize);
+	isize = i_size_read(inode);
+	if (iomap->offset >= isize) {
+		iomap->type = IOMAP_HOLE;
+		iomap->addr = IOMAP_NULL_ADDR;
+		iomap->length = length;
+	} else {
+		iomap->type = IOMAP_MAPPED;
+		iomap->addr = (z->z_sector << SECTOR_SHIFT) + iomap->offset;
+		iomap->length = isize - iomap->offset;
+	}
+	mutex_unlock(&zi->i_truncate_mutex);
+
+	trace_zonefs_iomap_begin(inode, iomap);
+
+	return 0;
+}
+
+static const struct iomap_ops zonefs_read_iomap_ops = {
+	.iomap_begin	= zonefs_read_iomap_begin,
+};
+
+static int zonefs_write_iomap_begin(struct inode *inode, loff_t offset,
+				    loff_t length, unsigned int flags,
+				    struct iomap *iomap, struct iomap *srcmap)
+{
+	struct zonefs_inode_info *zi = ZONEFS_I(inode);
+	struct zonefs_zone *z = zonefs_inode_zone(inode);
+	struct super_block *sb = inode->i_sb;
+	loff_t isize;
+
+	/* All write I/Os should always be within the file maximum size */
+	if (WARN_ON_ONCE(offset + length > z->z_capacity))
+		return -EIO;
+
+	/*
+	 * Sequential zones can only accept direct writes. This is already
+	 * checked when writes are issued, so warn if we see a page writeback
+	 * operation.
+	 */
+	if (WARN_ON_ONCE(zonefs_zone_is_seq(z) && !(flags & IOMAP_DIRECT)))
+		return -EIO;
+
+	/*
+	 * For conventional zones, all blocks are always mapped. For sequential
+	 * zones, all blocks after always mapped below the inode size (zone
+	 * write pointer) and unwriten beyond.
+	 */
+	mutex_lock(&zi->i_truncate_mutex);
+	iomap->bdev = inode->i_sb->s_bdev;
+	iomap->offset = ALIGN_DOWN(offset, sb->s_blocksize);
+	iomap->addr = (z->z_sector << SECTOR_SHIFT) + iomap->offset;
+	isize = i_size_read(inode);
+	if (iomap->offset >= isize) {
+		iomap->type = IOMAP_UNWRITTEN;
+		iomap->length = z->z_capacity - iomap->offset;
+	} else {
+		iomap->type = IOMAP_MAPPED;
+		iomap->length = isize - iomap->offset;
+	}
+	mutex_unlock(&zi->i_truncate_mutex);
+
+	trace_zonefs_iomap_begin(inode, iomap);
+
+	return 0;
+}
+
+static const struct iomap_ops zonefs_write_iomap_ops = {
+	.iomap_begin	= zonefs_write_iomap_begin,
+};
+
+static int zonefs_read_folio(struct file *unused, struct folio *folio)
+{
+	return iomap_read_folio(folio, &zonefs_read_iomap_ops);
+}
+
+static void zonefs_readahead(struct readahead_control *rac)
+{
+	iomap_readahead(rac, &zonefs_read_iomap_ops);
+}
+
+/*
+ * Map blocks for page writeback. This is used only on conventional zone files,
+ * which implies that the page range can only be within the fixed inode size.
+ */
+static int zonefs_write_map_blocks(struct iomap_writepage_ctx *wpc,
+				   struct inode *inode, loff_t offset)
+{
+	struct zonefs_zone *z = zonefs_inode_zone(inode);
+
+	if (WARN_ON_ONCE(zonefs_zone_is_seq(z)))
+		return -EIO;
+	if (WARN_ON_ONCE(offset >= i_size_read(inode)))
+		return -EIO;
+
+	/* If the mapping is already OK, nothing needs to be done */
+	if (offset >= wpc->iomap.offset &&
+	    offset < wpc->iomap.offset + wpc->iomap.length)
+		return 0;
+
+	return zonefs_write_iomap_begin(inode, offset,
+					z->z_capacity - offset,
+					IOMAP_WRITE, &wpc->iomap, NULL);
+}
+
+static const struct iomap_writeback_ops zonefs_writeback_ops = {
+	.map_blocks		= zonefs_write_map_blocks,
+};
+
+static int zonefs_writepages(struct address_space *mapping,
+			     struct writeback_control *wbc)
+{
+	struct iomap_writepage_ctx wpc = { };
+
+	return iomap_writepages(mapping, wbc, &wpc, &zonefs_writeback_ops);
+}
+
+static int zonefs_swap_activate(struct swap_info_struct *sis,
+				struct file *swap_file, sector_t *span)
+{
+	struct inode *inode = file_inode(swap_file);
+
+	if (zonefs_inode_is_seq(inode)) {
+		zonefs_err(inode->i_sb,
+			   "swap file: not a conventional zone file\n");
+		return -EINVAL;
+	}
+
+	return iomap_swapfile_activate(sis, swap_file, span,
+				       &zonefs_read_iomap_ops);
+}
+
+const struct address_space_operations zonefs_file_aops = {
+	.read_folio		= zonefs_read_folio,
+	.readahead		= zonefs_readahead,
+	.writepages		= zonefs_writepages,
+	.dirty_folio		= filemap_dirty_folio,
+	.release_folio		= iomap_release_folio,
+	.invalidate_folio	= iomap_invalidate_folio,
+	.migrate_folio		= filemap_migrate_folio,
+	.is_partially_uptodate	= iomap_is_partially_uptodate,
+	.error_remove_page	= generic_error_remove_page,
+	.direct_IO		= noop_direct_IO,
+	.swap_activate		= zonefs_swap_activate,
+};
+
+int zonefs_file_truncate(struct inode *inode, loff_t isize)
+{
+	struct zonefs_inode_info *zi = ZONEFS_I(inode);
+	struct zonefs_zone *z = zonefs_inode_zone(inode);
+	loff_t old_isize;
+	enum req_op op;
+	int ret = 0;
+
+	/*
+	 * Only sequential zone files can be truncated and truncation is allowed
+	 * only down to a 0 size, which is equivalent to a zone reset, and to
+	 * the maximum file size, which is equivalent to a zone finish.
+	 */
+	if (!zonefs_zone_is_seq(z))
+		return -EPERM;
+
+	if (!isize)
+		op = REQ_OP_ZONE_RESET;
+	else if (isize == z->z_capacity)
+		op = REQ_OP_ZONE_FINISH;
+	else
+		return -EPERM;
+
+	inode_dio_wait(inode);
+
+	/* Serialize against page faults */
+	filemap_invalidate_lock(inode->i_mapping);
+
+	/* Serialize against zonefs_iomap_begin() */
+	mutex_lock(&zi->i_truncate_mutex);
+
+	old_isize = i_size_read(inode);
+	if (isize == old_isize)
+		goto unlock;
+
+	ret = zonefs_inode_zone_mgmt(inode, op);
+	if (ret)
+		goto unlock;
+
+	/*
+	 * If the mount option ZONEFS_MNTOPT_EXPLICIT_OPEN is set,
+	 * take care of open zones.
+	 */
+	if (z->z_flags & ZONEFS_ZONE_OPEN) {
+		/*
+		 * Truncating a zone to EMPTY or FULL is the equivalent of
+		 * closing the zone. For a truncation to 0, we need to
+		 * re-open the zone to ensure new writes can be processed.
+		 * For a truncation to the maximum file size, the zone is
+		 * closed and writes cannot be accepted anymore, so clear
+		 * the open flag.
+		 */
+		if (!isize)
+			ret = zonefs_inode_zone_mgmt(inode, REQ_OP_ZONE_OPEN);
+		else
+			z->z_flags &= ~ZONEFS_ZONE_OPEN;
+	}
+
+	zonefs_update_stats(inode, isize);
+	truncate_setsize(inode, isize);
+	z->z_wpoffset = isize;
+	zonefs_inode_account_active(inode);
+
+unlock:
+	mutex_unlock(&zi->i_truncate_mutex);
+	filemap_invalidate_unlock(inode->i_mapping);
+
+	return ret;
+}
+
+static int zonefs_file_fsync(struct file *file, loff_t start, loff_t end,
+			     int datasync)
+{
+	struct inode *inode = file_inode(file);
+	int ret = 0;
+
+	if (unlikely(IS_IMMUTABLE(inode)))
+		return -EPERM;
+
+	/*
+	 * Since only direct writes are allowed in sequential files, page cache
+	 * flush is needed only for conventional zone files.
+	 */
+	if (zonefs_inode_is_cnv(inode))
+		ret = file_write_and_wait_range(file, start, end);
+	if (!ret)
+		ret = blkdev_issue_flush(inode->i_sb->s_bdev);
+
+	if (ret)
+		zonefs_io_error(inode, true);
+
+	return ret;
+}
+
+static vm_fault_t zonefs_filemap_page_mkwrite(struct vm_fault *vmf)
+{
+	struct inode *inode = file_inode(vmf->vma->vm_file);
+	vm_fault_t ret;
+
+	if (unlikely(IS_IMMUTABLE(inode)))
+		return VM_FAULT_SIGBUS;
+
+	/*
+	 * Sanity check: only conventional zone files can have shared
+	 * writeable mappings.
+	 */
+	if (zonefs_inode_is_seq(inode))
+		return VM_FAULT_NOPAGE;
+
+	sb_start_pagefault(inode->i_sb);
+	file_update_time(vmf->vma->vm_file);
+
+	/* Serialize against truncates */
+	filemap_invalidate_lock_shared(inode->i_mapping);
+	ret = iomap_page_mkwrite(vmf, &zonefs_write_iomap_ops);
+	filemap_invalidate_unlock_shared(inode->i_mapping);
+
+	sb_end_pagefault(inode->i_sb);
+	return ret;
+}
+
+static const struct vm_operations_struct zonefs_file_vm_ops = {
+	.fault		= filemap_fault,
+	.map_pages	= filemap_map_pages,
+	.page_mkwrite	= zonefs_filemap_page_mkwrite,
+};
+
+static int zonefs_file_mmap(struct file *file, struct vm_area_struct *vma)
+{
+	/*
+	 * Conventional zones accept random writes, so their files can support
+	 * shared writable mappings. For sequential zone files, only read
+	 * mappings are possible since there are no guarantees for write
+	 * ordering between msync() and page cache writeback.
+	 */
+	if (zonefs_inode_is_seq(file_inode(file)) &&
+	    (vma->vm_flags & VM_SHARED) && (vma->vm_flags & VM_MAYWRITE))
+		return -EINVAL;
+
+	file_accessed(file);
+	vma->vm_ops = &zonefs_file_vm_ops;
+
+	return 0;
+}
+
+static loff_t zonefs_file_llseek(struct file *file, loff_t offset, int whence)
+{
+	loff_t isize = i_size_read(file_inode(file));
+
+	/*
+	 * Seeks are limited to below the zone size for conventional zones
+	 * and below the zone write pointer for sequential zones. In both
+	 * cases, this limit is the inode size.
+	 */
+	return generic_file_llseek_size(file, offset, whence, isize, isize);
+}
+
+static int zonefs_file_write_dio_end_io(struct kiocb *iocb, ssize_t size,
+					int error, unsigned int flags)
+{
+	struct inode *inode = file_inode(iocb->ki_filp);
+	struct zonefs_inode_info *zi = ZONEFS_I(inode);
+
+	if (error) {
+		zonefs_io_error(inode, true);
+		return error;
+	}
+
+	if (size && zonefs_inode_is_seq(inode)) {
+		/*
+		 * Note that we may be seeing completions out of order,
+		 * but that is not a problem since a write completed
+		 * successfully necessarily means that all preceding writes
+		 * were also successful. So we can safely increase the inode
+		 * size to the write end location.
+		 */
+		mutex_lock(&zi->i_truncate_mutex);
+		if (i_size_read(inode) < iocb->ki_pos + size) {
+			zonefs_update_stats(inode, iocb->ki_pos + size);
+			zonefs_i_size_write(inode, iocb->ki_pos + size);
+		}
+		mutex_unlock(&zi->i_truncate_mutex);
+	}
+
+	return 0;
+}
+
+static const struct iomap_dio_ops zonefs_write_dio_ops = {
+	.end_io			= zonefs_file_write_dio_end_io,
+};
+
+static ssize_t zonefs_file_dio_append(struct kiocb *iocb, struct iov_iter *from)
+{
+	struct inode *inode = file_inode(iocb->ki_filp);
+	struct zonefs_zone *z = zonefs_inode_zone(inode);
+	struct block_device *bdev = inode->i_sb->s_bdev;
+	unsigned int max = bdev_max_zone_append_sectors(bdev);
+	struct bio *bio;
+	ssize_t size;
+	int nr_pages;
+	ssize_t ret;
+
+	max = ALIGN_DOWN(max << SECTOR_SHIFT, inode->i_sb->s_blocksize);
+	iov_iter_truncate(from, max);
+
+	nr_pages = iov_iter_npages(from, BIO_MAX_VECS);
+	if (!nr_pages)
+		return 0;
+
+	bio = bio_alloc(bdev, nr_pages,
+			REQ_OP_ZONE_APPEND | REQ_SYNC | REQ_IDLE, GFP_NOFS);
+	bio->bi_iter.bi_sector = z->z_sector;
+	bio->bi_ioprio = iocb->ki_ioprio;
+	if (iocb_is_dsync(iocb))
+		bio->bi_opf |= REQ_FUA;
+
+	ret = bio_iov_iter_get_pages(bio, from);
+	if (unlikely(ret))
+		goto out_release;
+
+	size = bio->bi_iter.bi_size;
+	task_io_account_write(size);
+
+	if (iocb->ki_flags & IOCB_HIPRI)
+		bio_set_polled(bio, iocb);
+
+	ret = submit_bio_wait(bio);
+
+	/*
+	 * If the file zone was written underneath the file system, the zone
+	 * write pointer may not be where we expect it to be, but the zone
+	 * append write can still succeed. So check manually that we wrote where
+	 * we intended to, that is, at zi->i_wpoffset.
+	 */
+	if (!ret) {
+		sector_t wpsector =
+			z->z_sector + (z->z_wpoffset >> SECTOR_SHIFT);
+
+		if (bio->bi_iter.bi_sector != wpsector) {
+			zonefs_warn(inode->i_sb,
+				"Corrupted write pointer %llu for zone at %llu\n",
+				wpsector, z->z_sector);
+			ret = -EIO;
+		}
+	}
+
+	zonefs_file_write_dio_end_io(iocb, size, ret, 0);
+	trace_zonefs_file_dio_append(inode, size, ret);
+
+out_release:
+	bio_release_pages(bio, false);
+	bio_put(bio);
+
+	if (ret >= 0) {
+		iocb->ki_pos += size;
+		return size;
+	}
+
+	return ret;
+}
+
+/*
+ * Do not exceed the LFS limits nor the file zone size. If pos is under the
+ * limit it becomes a short access. If it exceeds the limit, return -EFBIG.
+ */
+static loff_t zonefs_write_check_limits(struct file *file, loff_t pos,
+					loff_t count)
+{
+	struct inode *inode = file_inode(file);
+	struct zonefs_zone *z = zonefs_inode_zone(inode);
+	loff_t limit = rlimit(RLIMIT_FSIZE);
+	loff_t max_size = z->z_capacity;
+
+	if (limit != RLIM_INFINITY) {
+		if (pos >= limit) {
+			send_sig(SIGXFSZ, current, 0);
+			return -EFBIG;
+		}
+		count = min(count, limit - pos);
+	}
+
+	if (!(file->f_flags & O_LARGEFILE))
+		max_size = min_t(loff_t, MAX_NON_LFS, max_size);
+
+	if (unlikely(pos >= max_size))
+		return -EFBIG;
+
+	return min(count, max_size - pos);
+}
+
+static ssize_t zonefs_write_checks(struct kiocb *iocb, struct iov_iter *from)
+{
+	struct file *file = iocb->ki_filp;
+	struct inode *inode = file_inode(file);
+	struct zonefs_inode_info *zi = ZONEFS_I(inode);
+	struct zonefs_zone *z = zonefs_inode_zone(inode);
+	loff_t count;
+
+	if (IS_SWAPFILE(inode))
+		return -ETXTBSY;
+
+	if (!iov_iter_count(from))
+		return 0;
+
+	if ((iocb->ki_flags & IOCB_NOWAIT) && !(iocb->ki_flags & IOCB_DIRECT))
+		return -EINVAL;
+
+	if (iocb->ki_flags & IOCB_APPEND) {
+		if (zonefs_zone_is_cnv(z))
+			return -EINVAL;
+		mutex_lock(&zi->i_truncate_mutex);
+		iocb->ki_pos = z->z_wpoffset;
+		mutex_unlock(&zi->i_truncate_mutex);
+	}
+
+	count = zonefs_write_check_limits(file, iocb->ki_pos,
+					  iov_iter_count(from));
+	if (count < 0)
+		return count;
+
+	iov_iter_truncate(from, count);
+	return iov_iter_count(from);
+}
+
+/*
+ * Handle direct writes. For sequential zone files, this is the only possible
+ * write path. For these files, check that the user is issuing writes
+ * sequentially from the end of the file. This code assumes that the block layer
+ * delivers write requests to the device in sequential order. This is always the
+ * case if a block IO scheduler implementing the ELEVATOR_F_ZBD_SEQ_WRITE
+ * elevator feature is being used (e.g. mq-deadline). The block layer always
+ * automatically select such an elevator for zoned block devices during the
+ * device initialization.
+ */
+static ssize_t zonefs_file_dio_write(struct kiocb *iocb, struct iov_iter *from)
+{
+	struct inode *inode = file_inode(iocb->ki_filp);
+	struct zonefs_inode_info *zi = ZONEFS_I(inode);
+	struct zonefs_zone *z = zonefs_inode_zone(inode);
+	struct super_block *sb = inode->i_sb;
+	bool sync = is_sync_kiocb(iocb);
+	bool append = false;
+	ssize_t ret, count;
+
+	/*
+	 * For async direct IOs to sequential zone files, refuse IOCB_NOWAIT
+	 * as this can cause write reordering (e.g. the first aio gets EAGAIN
+	 * on the inode lock but the second goes through but is now unaligned).
+	 */
+	if (zonefs_zone_is_seq(z) && !sync && (iocb->ki_flags & IOCB_NOWAIT))
+		return -EOPNOTSUPP;
+
+	if (iocb->ki_flags & IOCB_NOWAIT) {
+		if (!inode_trylock(inode))
+			return -EAGAIN;
+	} else {
+		inode_lock(inode);
+	}
+
+	count = zonefs_write_checks(iocb, from);
+	if (count <= 0) {
+		ret = count;
+		goto inode_unlock;
+	}
+
+	if ((iocb->ki_pos | count) & (sb->s_blocksize - 1)) {
+		ret = -EINVAL;
+		goto inode_unlock;
+	}
+
+	/* Enforce sequential writes (append only) in sequential zones */
+	if (zonefs_zone_is_seq(z)) {
+		mutex_lock(&zi->i_truncate_mutex);
+		if (iocb->ki_pos != z->z_wpoffset) {
+			mutex_unlock(&zi->i_truncate_mutex);
+			ret = -EINVAL;
+			goto inode_unlock;
+		}
+		mutex_unlock(&zi->i_truncate_mutex);
+		append = sync;
+	}
+
+	if (append)
+		ret = zonefs_file_dio_append(iocb, from);
+	else
+		ret = iomap_dio_rw(iocb, from, &zonefs_write_iomap_ops,
+				   &zonefs_write_dio_ops, 0, NULL, 0);
+	if (zonefs_zone_is_seq(z) &&
+	    (ret > 0 || ret == -EIOCBQUEUED)) {
+		if (ret > 0)
+			count = ret;
+
+		/*
+		 * Update the zone write pointer offset assuming the write
+		 * operation succeeded. If it did not, the error recovery path
+		 * will correct it. Also do active seq file accounting.
+		 */
+		mutex_lock(&zi->i_truncate_mutex);
+		z->z_wpoffset += count;
+		zonefs_inode_account_active(inode);
+		mutex_unlock(&zi->i_truncate_mutex);
+	}
+
+inode_unlock:
+	inode_unlock(inode);
+
+	return ret;
+}
+
+static ssize_t zonefs_file_buffered_write(struct kiocb *iocb,
+					  struct iov_iter *from)
+{
+	struct inode *inode = file_inode(iocb->ki_filp);
+	ssize_t ret;
+
+	/*
+	 * Direct IO writes are mandatory for sequential zone files so that the
+	 * write IO issuing order is preserved.
+	 */
+	if (zonefs_inode_is_seq(inode))
+		return -EIO;
+
+	if (iocb->ki_flags & IOCB_NOWAIT) {
+		if (!inode_trylock(inode))
+			return -EAGAIN;
+	} else {
+		inode_lock(inode);
+	}
+
+	ret = zonefs_write_checks(iocb, from);
+	if (ret <= 0)
+		goto inode_unlock;
+
+	ret = iomap_file_buffered_write(iocb, from, &zonefs_write_iomap_ops);
+	if (ret > 0)
+		iocb->ki_pos += ret;
+	else if (ret == -EIO)
+		zonefs_io_error(inode, true);
+
+inode_unlock:
+	inode_unlock(inode);
+	if (ret > 0)
+		ret = generic_write_sync(iocb, ret);
+
+	return ret;
+}
+
+static ssize_t zonefs_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
+{
+	struct inode *inode = file_inode(iocb->ki_filp);
+	struct zonefs_zone *z = zonefs_inode_zone(inode);
+
+	if (unlikely(IS_IMMUTABLE(inode)))
+		return -EPERM;
+
+	if (sb_rdonly(inode->i_sb))
+		return -EROFS;
+
+	/* Write operations beyond the zone capacity are not allowed */
+	if (iocb->ki_pos >= z->z_capacity)
+		return -EFBIG;
+
+	if (iocb->ki_flags & IOCB_DIRECT) {
+		ssize_t ret = zonefs_file_dio_write(iocb, from);
+
+		if (ret != -ENOTBLK)
+			return ret;
+	}
+
+	return zonefs_file_buffered_write(iocb, from);
+}
+
+static int zonefs_file_read_dio_end_io(struct kiocb *iocb, ssize_t size,
+				       int error, unsigned int flags)
+{
+	if (error) {
+		zonefs_io_error(file_inode(iocb->ki_filp), false);
+		return error;
+	}
+
+	return 0;
+}
+
+static const struct iomap_dio_ops zonefs_read_dio_ops = {
+	.end_io			= zonefs_file_read_dio_end_io,
+};
+
+static ssize_t zonefs_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
+{
+	struct inode *inode = file_inode(iocb->ki_filp);
+	struct zonefs_inode_info *zi = ZONEFS_I(inode);
+	struct zonefs_zone *z = zonefs_inode_zone(inode);
+	struct super_block *sb = inode->i_sb;
+	loff_t isize;
+	ssize_t ret;
+
+	/* Offline zones cannot be read */
+	if (unlikely(IS_IMMUTABLE(inode) && !(inode->i_mode & 0777)))
+		return -EPERM;
+
+	if (iocb->ki_pos >= z->z_capacity)
+		return 0;
+
+	if (iocb->ki_flags & IOCB_NOWAIT) {
+		if (!inode_trylock_shared(inode))
+			return -EAGAIN;
+	} else {
+		inode_lock_shared(inode);
+	}
+
+	/* Limit read operations to written data */
+	mutex_lock(&zi->i_truncate_mutex);
+	isize = i_size_read(inode);
+	if (iocb->ki_pos >= isize) {
+		mutex_unlock(&zi->i_truncate_mutex);
+		ret = 0;
+		goto inode_unlock;
+	}
+	iov_iter_truncate(to, isize - iocb->ki_pos);
+	mutex_unlock(&zi->i_truncate_mutex);
+
+	if (iocb->ki_flags & IOCB_DIRECT) {
+		size_t count = iov_iter_count(to);
+
+		if ((iocb->ki_pos | count) & (sb->s_blocksize - 1)) {
+			ret = -EINVAL;
+			goto inode_unlock;
+		}
+		file_accessed(iocb->ki_filp);
+		ret = iomap_dio_rw(iocb, to, &zonefs_read_iomap_ops,
+				   &zonefs_read_dio_ops, 0, NULL, 0);
+	} else {
+		ret = generic_file_read_iter(iocb, to);
+		if (ret == -EIO)
+			zonefs_io_error(inode, false);
+	}
+
+inode_unlock:
+	inode_unlock_shared(inode);
+
+	return ret;
+}
+
+/*
+ * Write open accounting is done only for sequential files.
+ */
+static inline bool zonefs_seq_file_need_wro(struct inode *inode,
+					    struct file *file)
+{
+	if (zonefs_inode_is_cnv(inode))
+		return false;
+
+	if (!(file->f_mode & FMODE_WRITE))
+		return false;
+
+	return true;
+}
+
+static int zonefs_seq_file_write_open(struct inode *inode)
+{
+	struct zonefs_inode_info *zi = ZONEFS_I(inode);
+	struct zonefs_zone *z = zonefs_inode_zone(inode);
+	int ret = 0;
+
+	mutex_lock(&zi->i_truncate_mutex);
+
+	if (!zi->i_wr_refcnt) {
+		struct zonefs_sb_info *sbi = ZONEFS_SB(inode->i_sb);
+		unsigned int wro = atomic_inc_return(&sbi->s_wro_seq_files);
+
+		if (sbi->s_mount_opts & ZONEFS_MNTOPT_EXPLICIT_OPEN) {
+
+			if (sbi->s_max_wro_seq_files
+			    && wro > sbi->s_max_wro_seq_files) {
+				atomic_dec(&sbi->s_wro_seq_files);
+				ret = -EBUSY;
+				goto unlock;
+			}
+
+			if (i_size_read(inode) < z->z_capacity) {
+				ret = zonefs_inode_zone_mgmt(inode,
+							     REQ_OP_ZONE_OPEN);
+				if (ret) {
+					atomic_dec(&sbi->s_wro_seq_files);
+					goto unlock;
+				}
+				z->z_flags |= ZONEFS_ZONE_OPEN;
+				zonefs_inode_account_active(inode);
+			}
+		}
+	}
+
+	zi->i_wr_refcnt++;
+
+unlock:
+	mutex_unlock(&zi->i_truncate_mutex);
+
+	return ret;
+}
+
+static int zonefs_file_open(struct inode *inode, struct file *file)
+{
+	int ret;
+
+	ret = generic_file_open(inode, file);
+	if (ret)
+		return ret;
+
+	if (zonefs_seq_file_need_wro(inode, file))
+		return zonefs_seq_file_write_open(inode);
+
+	return 0;
+}
+
+static void zonefs_seq_file_write_close(struct inode *inode)
+{
+	struct zonefs_inode_info *zi = ZONEFS_I(inode);
+	struct zonefs_zone *z = zonefs_inode_zone(inode);
+	struct super_block *sb = inode->i_sb;
+	struct zonefs_sb_info *sbi = ZONEFS_SB(sb);
+	int ret = 0;
+
+	mutex_lock(&zi->i_truncate_mutex);
+
+	zi->i_wr_refcnt--;
+	if (zi->i_wr_refcnt)
+		goto unlock;
+
+	/*
+	 * The file zone may not be open anymore (e.g. the file was truncated to
+	 * its maximum size or it was fully written). For this case, we only
+	 * need to decrement the write open count.
+	 */
+	if (z->z_flags & ZONEFS_ZONE_OPEN) {
+		ret = zonefs_inode_zone_mgmt(inode, REQ_OP_ZONE_CLOSE);
+		if (ret) {
+			__zonefs_io_error(inode, false);
+			/*
+			 * Leaving zones explicitly open may lead to a state
+			 * where most zones cannot be written (zone resources
+			 * exhausted). So take preventive action by remounting
+			 * read-only.
+			 */
+			if (z->z_flags & ZONEFS_ZONE_OPEN &&
+			    !(sb->s_flags & SB_RDONLY)) {
+				zonefs_warn(sb,
+					"closing zone at %llu failed %d\n",
+					z->z_sector, ret);
+				zonefs_warn(sb,
+					"remounting filesystem read-only\n");
+				sb->s_flags |= SB_RDONLY;
+			}
+			goto unlock;
+		}
+
+		z->z_flags &= ~ZONEFS_ZONE_OPEN;
+		zonefs_inode_account_active(inode);
+	}
+
+	atomic_dec(&sbi->s_wro_seq_files);
+
+unlock:
+	mutex_unlock(&zi->i_truncate_mutex);
+}
+
+static int zonefs_file_release(struct inode *inode, struct file *file)
+{
+	/*
+	 * If we explicitly open a zone we must close it again as well, but the
+	 * zone management operation can fail (either due to an IO error or as
+	 * the zone has gone offline or read-only). Make sure we don't fail the
+	 * close(2) for user-space.
+	 */
+	if (zonefs_seq_file_need_wro(inode, file))
+		zonefs_seq_file_write_close(inode);
+
+	return 0;
+}
+
+const struct file_operations zonefs_file_operations = {
+	.open		= zonefs_file_open,
+	.release	= zonefs_file_release,
+	.fsync		= zonefs_file_fsync,
+	.mmap		= zonefs_file_mmap,
+	.llseek		= zonefs_file_llseek,
+	.read_iter	= zonefs_file_read_iter,
+	.write_iter	= zonefs_file_write_iter,
+	.splice_read	= generic_file_splice_read,
+	.splice_write	= iter_file_splice_write,
+	.iopoll		= iocb_bio_iopoll,
+};
diff --git a/fs/zonefs/super.c b/fs/zonefs/super.c
index 72ef97320b9906..23b8b299c64e1e 100644
--- a/fs/zonefs/super.c
+++ b/fs/zonefs/super.c
@@ -28,33 +28,47 @@
 #include "trace.h"
 
 /*
- * Manage the active zone count. Called with zi->i_truncate_mutex held.
+ * Get the name of a zone group directory.
  */
-static void zonefs_account_active(struct inode *inode)
+static const char *zonefs_zgroup_name(enum zonefs_ztype ztype)
 {
-	struct zonefs_sb_info *sbi = ZONEFS_SB(inode->i_sb);
-	struct zonefs_inode_info *zi = ZONEFS_I(inode);
+	switch (ztype) {
+	case ZONEFS_ZTYPE_CNV:
+		return "cnv";
+	case ZONEFS_ZTYPE_SEQ:
+		return "seq";
+	default:
+		WARN_ON_ONCE(1);
+		return "???";
+	}
+}
 
-	lockdep_assert_held(&zi->i_truncate_mutex);
+/*
+ * Manage the active zone count.
+ */
+static void zonefs_account_active(struct super_block *sb,
+				  struct zonefs_zone *z)
+{
+	struct zonefs_sb_info *sbi = ZONEFS_SB(sb);
 
-	if (zi->i_ztype != ZONEFS_ZTYPE_SEQ)
+	if (zonefs_zone_is_cnv(z))
 		return;
 
 	/*
 	 * For zones that transitioned to the offline or readonly condition,
 	 * we only need to clear the active state.
 	 */
-	if (zi->i_flags & (ZONEFS_ZONE_OFFLINE | ZONEFS_ZONE_READONLY))
+	if (z->z_flags & (ZONEFS_ZONE_OFFLINE | ZONEFS_ZONE_READONLY))
 		goto out;
 
 	/*
 	 * If the zone is active, that is, if it is explicitly open or
 	 * partially written, check if it was already accounted as active.
 	 */
-	if ((zi->i_flags & ZONEFS_ZONE_OPEN) ||
-	    (zi->i_wpoffset > 0 && zi->i_wpoffset < zi->i_max_size)) {
-		if (!(zi->i_flags & ZONEFS_ZONE_ACTIVE)) {
-			zi->i_flags |= ZONEFS_ZONE_ACTIVE;
+	if ((z->z_flags & ZONEFS_ZONE_OPEN) ||
+	    (z->z_wpoffset > 0 && z->z_wpoffset < z->z_capacity)) {
+		if (!(z->z_flags & ZONEFS_ZONE_ACTIVE)) {
+			z->z_flags |= ZONEFS_ZONE_ACTIVE;
 			atomic_inc(&sbi->s_active_seq_files);
 		}
 		return;
@@ -62,18 +76,29 @@ static void zonefs_account_active(struct inode *inode)
 
 out:
 	/* The zone is not active. If it was, update the active count */
-	if (zi->i_flags & ZONEFS_ZONE_ACTIVE) {
-		zi->i_flags &= ~ZONEFS_ZONE_ACTIVE;
+	if (z->z_flags & ZONEFS_ZONE_ACTIVE) {
+		z->z_flags &= ~ZONEFS_ZONE_ACTIVE;
 		atomic_dec(&sbi->s_active_seq_files);
 	}
 }
 
-static inline int zonefs_zone_mgmt(struct inode *inode, enum req_op op)
+/*
+ * Manage the active zone count. Called with zi->i_truncate_mutex held.
+ */
+void zonefs_inode_account_active(struct inode *inode)
 {
-	struct zonefs_inode_info *zi = ZONEFS_I(inode);
-	int ret;
+	lockdep_assert_held(&ZONEFS_I(inode)->i_truncate_mutex);
 
-	lockdep_assert_held(&zi->i_truncate_mutex);
+	return zonefs_account_active(inode->i_sb, zonefs_inode_zone(inode));
+}
+
+/*
+ * Execute a zone management operation.
+ */
+static int zonefs_zone_mgmt(struct super_block *sb,
+			    struct zonefs_zone *z, enum req_op op)
+{
+	int ret;
 
 	/*
 	 * With ZNS drives, closing an explicitly open zone that has not been
@@ -83,201 +108,49 @@ static inline int zonefs_zone_mgmt(struct inode *inode, enum req_op op)
 	 * are exceeded, make sure that the zone does not remain active by
 	 * resetting it.
 	 */
-	if (op == REQ_OP_ZONE_CLOSE && !zi->i_wpoffset)
+	if (op == REQ_OP_ZONE_CLOSE && !z->z_wpoffset)
 		op = REQ_OP_ZONE_RESET;
 
-	trace_zonefs_zone_mgmt(inode, op);
-	ret = blkdev_zone_mgmt(inode->i_sb->s_bdev, op, zi->i_zsector,
-			       zi->i_zone_size >> SECTOR_SHIFT, GFP_NOFS);
+	trace_zonefs_zone_mgmt(sb, z, op);
+	ret = blkdev_zone_mgmt(sb->s_bdev, op, z->z_sector,
+			       z->z_size >> SECTOR_SHIFT, GFP_NOFS);
 	if (ret) {
-		zonefs_err(inode->i_sb,
+		zonefs_err(sb,
 			   "Zone management operation %s at %llu failed %d\n",
-			   blk_op_str(op), zi->i_zsector, ret);
+			   blk_op_str(op), z->z_sector, ret);
 		return ret;
 	}
 
 	return 0;
 }
 
-static inline void zonefs_i_size_write(struct inode *inode, loff_t isize)
-{
-	struct zonefs_inode_info *zi = ZONEFS_I(inode);
-
-	i_size_write(inode, isize);
-	/*
-	 * A full zone is no longer open/active and does not need
-	 * explicit closing.
-	 */
-	if (isize >= zi->i_max_size) {
-		struct zonefs_sb_info *sbi = ZONEFS_SB(inode->i_sb);
-
-		if (zi->i_flags & ZONEFS_ZONE_ACTIVE)
-			atomic_dec(&sbi->s_active_seq_files);
-		zi->i_flags &= ~(ZONEFS_ZONE_OPEN | ZONEFS_ZONE_ACTIVE);
-	}
-}
-
-static int zonefs_read_iomap_begin(struct inode *inode, loff_t offset,
-				   loff_t length, unsigned int flags,
-				   struct iomap *iomap, struct iomap *srcmap)
+int zonefs_inode_zone_mgmt(struct inode *inode, enum req_op op)
 {
-	struct zonefs_inode_info *zi = ZONEFS_I(inode);
-	struct super_block *sb = inode->i_sb;
-	loff_t isize;
+	lockdep_assert_held(&ZONEFS_I(inode)->i_truncate_mutex);
 
-	/*
-	 * All blocks are always mapped below EOF. If reading past EOF,
-	 * act as if there is a hole up to the file maximum size.
-	 */
-	mutex_lock(&zi->i_truncate_mutex);
-	iomap->bdev = inode->i_sb->s_bdev;
-	iomap->offset = ALIGN_DOWN(offset, sb->s_blocksize);
-	isize = i_size_read(inode);
-	if (iomap->offset >= isize) {
-		iomap->type = IOMAP_HOLE;
-		iomap->addr = IOMAP_NULL_ADDR;
-		iomap->length = length;
-	} else {
-		iomap->type = IOMAP_MAPPED;
-		iomap->addr = (zi->i_zsector << SECTOR_SHIFT) + iomap->offset;
-		iomap->length = isize - iomap->offset;
-	}
-	mutex_unlock(&zi->i_truncate_mutex);
-
-	trace_zonefs_iomap_begin(inode, iomap);
-
-	return 0;
+	return zonefs_zone_mgmt(inode->i_sb, zonefs_inode_zone(inode), op);
 }
 
-static const struct iomap_ops zonefs_read_iomap_ops = {
-	.iomap_begin	= zonefs_read_iomap_begin,
-};
-
-static int zonefs_write_iomap_begin(struct inode *inode, loff_t offset,
-				    loff_t length, unsigned int flags,
-				    struct iomap *iomap, struct iomap *srcmap)
+void zonefs_i_size_write(struct inode *inode, loff_t isize)
 {
-	struct zonefs_inode_info *zi = ZONEFS_I(inode);
-	struct super_block *sb = inode->i_sb;
-	loff_t isize;
+	struct zonefs_zone *z = zonefs_inode_zone(inode);
 
-	/* All write I/Os should always be within the file maximum size */
-	if (WARN_ON_ONCE(offset + length > zi->i_max_size))
-		return -EIO;
-
-	/*
-	 * Sequential zones can only accept direct writes. This is already
-	 * checked when writes are issued, so warn if we see a page writeback
-	 * operation.
-	 */
-	if (WARN_ON_ONCE(zi->i_ztype == ZONEFS_ZTYPE_SEQ &&
-			 !(flags & IOMAP_DIRECT)))
-		return -EIO;
+	i_size_write(inode, isize);
 
 	/*
-	 * For conventional zones, all blocks are always mapped. For sequential
-	 * zones, all blocks after always mapped below the inode size (zone
-	 * write pointer) and unwriten beyond.
+	 * A full zone is no longer open/active and does not need
+	 * explicit closing.
 	 */
-	mutex_lock(&zi->i_truncate_mutex);
-	iomap->bdev = inode->i_sb->s_bdev;
-	iomap->offset = ALIGN_DOWN(offset, sb->s_blocksize);
-	iomap->addr = (zi->i_zsector << SECTOR_SHIFT) + iomap->offset;
-	isize = i_size_read(inode);
-	if (iomap->offset >= isize) {
-		iomap->type = IOMAP_UNWRITTEN;
-		iomap->length = zi->i_max_size - iomap->offset;
-	} else {
-		iomap->type = IOMAP_MAPPED;
-		iomap->length = isize - iomap->offset;
-	}
-	mutex_unlock(&zi->i_truncate_mutex);
-
-	trace_zonefs_iomap_begin(inode, iomap);
-
-	return 0;
-}
-
-static const struct iomap_ops zonefs_write_iomap_ops = {
-	.iomap_begin	= zonefs_write_iomap_begin,
-};
-
-static int zonefs_read_folio(struct file *unused, struct folio *folio)
-{
-	return iomap_read_folio(folio, &zonefs_read_iomap_ops);
-}
-
-static void zonefs_readahead(struct readahead_control *rac)
-{
-	iomap_readahead(rac, &zonefs_read_iomap_ops);
-}
-
-/*
- * Map blocks for page writeback. This is used only on conventional zone files,
- * which implies that the page range can only be within the fixed inode size.
- */
-static int zonefs_write_map_blocks(struct iomap_writepage_ctx *wpc,
-				   struct inode *inode, loff_t offset)
-{
-	struct zonefs_inode_info *zi = ZONEFS_I(inode);
-
-	if (WARN_ON_ONCE(zi->i_ztype != ZONEFS_ZTYPE_CNV))
-		return -EIO;
-	if (WARN_ON_ONCE(offset >= i_size_read(inode)))
-		return -EIO;
-
-	/* If the mapping is already OK, nothing needs to be done */
-	if (offset >= wpc->iomap.offset &&
-	    offset < wpc->iomap.offset + wpc->iomap.length)
-		return 0;
-
-	return zonefs_write_iomap_begin(inode, offset, zi->i_max_size - offset,
-					IOMAP_WRITE, &wpc->iomap, NULL);
-}
-
-static const struct iomap_writeback_ops zonefs_writeback_ops = {
-	.map_blocks		= zonefs_write_map_blocks,
-};
-
-static int zonefs_writepages(struct address_space *mapping,
-			     struct writeback_control *wbc)
-{
-	struct iomap_writepage_ctx wpc = { };
-
-	return iomap_writepages(mapping, wbc, &wpc, &zonefs_writeback_ops);
-}
-
-static int zonefs_swap_activate(struct swap_info_struct *sis,
-				struct file *swap_file, sector_t *span)
-{
-	struct inode *inode = file_inode(swap_file);
-	struct zonefs_inode_info *zi = ZONEFS_I(inode);
+	if (isize >= z->z_capacity) {
+		struct zonefs_sb_info *sbi = ZONEFS_SB(inode->i_sb);
 
-	if (zi->i_ztype != ZONEFS_ZTYPE_CNV) {
-		zonefs_err(inode->i_sb,
-			   "swap file: not a conventional zone file\n");
-		return -EINVAL;
+		if (z->z_flags & ZONEFS_ZONE_ACTIVE)
+			atomic_dec(&sbi->s_active_seq_files);
+		z->z_flags &= ~(ZONEFS_ZONE_OPEN | ZONEFS_ZONE_ACTIVE);
 	}
-
-	return iomap_swapfile_activate(sis, swap_file, span,
-				       &zonefs_read_iomap_ops);
 }
 
-static const struct address_space_operations zonefs_file_aops = {
-	.read_folio		= zonefs_read_folio,
-	.readahead		= zonefs_readahead,
-	.writepages		= zonefs_writepages,
-	.dirty_folio		= filemap_dirty_folio,
-	.release_folio		= iomap_release_folio,
-	.invalidate_folio	= iomap_invalidate_folio,
-	.migrate_folio		= filemap_migrate_folio,
-	.is_partially_uptodate	= iomap_is_partially_uptodate,
-	.error_remove_page	= generic_error_remove_page,
-	.direct_IO		= noop_direct_IO,
-	.swap_activate		= zonefs_swap_activate,
-};
-
-static void zonefs_update_stats(struct inode *inode, loff_t new_isize)
+void zonefs_update_stats(struct inode *inode, loff_t new_isize)
 {
 	struct super_block *sb = inode->i_sb;
 	struct zonefs_sb_info *sbi = ZONEFS_SB(sb);
@@ -310,63 +183,69 @@ static void zonefs_update_stats(struct inode *inode, loff_t new_isize)
 }
 
 /*
- * Check a zone condition and adjust its file inode access permissions for
- * offline and readonly zones. Return the inode size corresponding to the
- * amount of readable data in the zone.
+ * Check a zone condition. Return the amount of written (and still readable)
+ * data in the zone.
  */
-static loff_t zonefs_check_zone_condition(struct inode *inode,
-					  struct blk_zone *zone, bool warn,
-					  bool mount)
+static loff_t zonefs_check_zone_condition(struct super_block *sb,
+					  struct zonefs_zone *z,
+					  struct blk_zone *zone)
 {
-	struct zonefs_inode_info *zi = ZONEFS_I(inode);
-
 	switch (zone->cond) {
 	case BLK_ZONE_COND_OFFLINE:
-		/*
-		 * Dead zone: make the inode immutable, disable all accesses
-		 * and set the file size to 0 (zone wp set to zone start).
-		 */
-		if (warn)
-			zonefs_warn(inode->i_sb, "inode %lu: offline zone\n",
-				    inode->i_ino);
-		inode->i_flags |= S_IMMUTABLE;
-		inode->i_mode &= ~0777;
-		zone->wp = zone->start;
-		zi->i_flags |= ZONEFS_ZONE_OFFLINE;
+		zonefs_warn(sb, "Zone %llu: offline zone\n",
+			    z->z_sector);
+		z->z_flags |= ZONEFS_ZONE_OFFLINE;
 		return 0;
 	case BLK_ZONE_COND_READONLY:
 		/*
-		 * The write pointer of read-only zones is invalid. If such a
-		 * zone is found during mount, the file size cannot be retrieved
-		 * so we treat the zone as offline (mount == true case).
-		 * Otherwise, keep the file size as it was when last updated
-		 * so that the user can recover data. In both cases, writes are
-		 * always disabled for the zone.
+		 * The write pointer of read-only zones is invalid, so we cannot
+		 * determine the zone wpoffset (inode size). We thus keep the
+		 * zone wpoffset as is, which leads to an empty file
+		 * (wpoffset == 0) on mount. For a runtime error, this keeps
+		 * the inode size as it was when last updated so that the user
+		 * can recover data.
 		 */
-		if (warn)
-			zonefs_warn(inode->i_sb, "inode %lu: read-only zone\n",
-				    inode->i_ino);
-		inode->i_flags |= S_IMMUTABLE;
-		if (mount) {
-			zone->cond = BLK_ZONE_COND_OFFLINE;
-			inode->i_mode &= ~0777;
-			zone->wp = zone->start;
-			zi->i_flags |= ZONEFS_ZONE_OFFLINE;
-			return 0;
-		}
-		zi->i_flags |= ZONEFS_ZONE_READONLY;
-		inode->i_mode &= ~0222;
-		return i_size_read(inode);
+		zonefs_warn(sb, "Zone %llu: read-only zone\n",
+			    z->z_sector);
+		z->z_flags |= ZONEFS_ZONE_READONLY;
+		if (zonefs_zone_is_cnv(z))
+			return z->z_capacity;
+		return z->z_wpoffset;
 	case BLK_ZONE_COND_FULL:
 		/* The write pointer of full zones is invalid. */
-		return zi->i_max_size;
+		return z->z_capacity;
 	default:
-		if (zi->i_ztype == ZONEFS_ZTYPE_CNV)
-			return zi->i_max_size;
+		if (zonefs_zone_is_cnv(z))
+			return z->z_capacity;
 		return (zone->wp - zone->start) << SECTOR_SHIFT;
 	}
 }
 
+/*
+ * Check a zone condition and adjust its inode access permissions for
+ * offline and readonly zones.
+ */
+static void zonefs_inode_update_mode(struct inode *inode)
+{
+	struct zonefs_zone *z = zonefs_inode_zone(inode);
+
+	if (z->z_flags & ZONEFS_ZONE_OFFLINE) {
+		/* Offline zones cannot be read nor written */
+		inode->i_flags |= S_IMMUTABLE;
+		inode->i_mode &= ~0777;
+	} else if (z->z_flags & ZONEFS_ZONE_READONLY) {
+		/* Readonly zones cannot be written */
+		inode->i_flags |= S_IMMUTABLE;
+		if (z->z_flags & ZONEFS_ZONE_INIT_MODE)
+			inode->i_mode &= ~0777;
+		else
+			inode->i_mode &= ~0222;
+	}
+
+	z->z_flags &= ~ZONEFS_ZONE_INIT_MODE;
+	z->z_mode = inode->i_mode;
+}
+
 struct zonefs_ioerr_data {
 	struct inode	*inode;
 	bool		write;
@@ -377,7 +256,7 @@ static int zonefs_io_error_cb(struct blk_zone *zone, unsigned int idx,
 {
 	struct zonefs_ioerr_data *err = data;
 	struct inode *inode = err->inode;
-	struct zonefs_inode_info *zi = ZONEFS_I(inode);
+	struct zonefs_zone *z = zonefs_inode_zone(inode);
 	struct super_block *sb = inode->i_sb;
 	struct zonefs_sb_info *sbi = ZONEFS_SB(sb);
 	loff_t isize, data_size;
@@ -388,10 +267,9 @@ static int zonefs_io_error_cb(struct blk_zone *zone, unsigned int idx,
 	 * as there is no inconsistency between the inode size and the amount of
 	 * data writen in the zone (data_size).
 	 */
-	data_size = zonefs_check_zone_condition(inode, zone, true, false);
+	data_size = zonefs_check_zone_condition(sb, z, zone);
 	isize = i_size_read(inode);
-	if (zone->cond != BLK_ZONE_COND_OFFLINE &&
-	    zone->cond != BLK_ZONE_COND_READONLY &&
+	if (!(z->z_flags & (ZONEFS_ZONE_READONLY | ZONEFS_ZONE_OFFLINE)) &&
 	    !err->write && isize == data_size)
 		return 0;
 
@@ -414,8 +292,9 @@ static int zonefs_io_error_cb(struct blk_zone *zone, unsigned int idx,
 	 * In all cases, warn about inode size inconsistency and handle the
 	 * IO error according to the zone condition and to the mount options.
 	 */
-	if (zi->i_ztype == ZONEFS_ZTYPE_SEQ && isize != data_size)
-		zonefs_warn(sb, "inode %lu: invalid size %lld (should be %lld)\n",
+	if (zonefs_zone_is_seq(z) && isize != data_size)
+		zonefs_warn(sb,
+			    "inode %lu: invalid size %lld (should be %lld)\n",
 			    inode->i_ino, isize, data_size);
 
 	/*
@@ -424,24 +303,22 @@ static int zonefs_io_error_cb(struct blk_zone *zone, unsigned int idx,
 	 * zone condition to read-only and offline respectively, as if the
 	 * condition was signaled by the hardware.
 	 */
-	if (zone->cond == BLK_ZONE_COND_OFFLINE ||
-	    sbi->s_mount_opts & ZONEFS_MNTOPT_ERRORS_ZOL) {
+	if ((z->z_flags & ZONEFS_ZONE_OFFLINE) ||
+	    (sbi->s_mount_opts & ZONEFS_MNTOPT_ERRORS_ZOL)) {
 		zonefs_warn(sb, "inode %lu: read/write access disabled\n",
 			    inode->i_ino);
-		if (zone->cond != BLK_ZONE_COND_OFFLINE) {
-			zone->cond = BLK_ZONE_COND_OFFLINE;
-			data_size = zonefs_check_zone_condition(inode, zone,
-								false, false);
-		}
-	} else if (zone->cond == BLK_ZONE_COND_READONLY ||
-		   sbi->s_mount_opts & ZONEFS_MNTOPT_ERRORS_ZRO) {
+		if (!(z->z_flags & ZONEFS_ZONE_OFFLINE))
+			z->z_flags |= ZONEFS_ZONE_OFFLINE;
+		zonefs_inode_update_mode(inode);
+		data_size = 0;
+	} else if ((z->z_flags & ZONEFS_ZONE_READONLY) ||
+		   (sbi->s_mount_opts & ZONEFS_MNTOPT_ERRORS_ZRO)) {
 		zonefs_warn(sb, "inode %lu: write access disabled\n",
 			    inode->i_ino);
-		if (zone->cond != BLK_ZONE_COND_READONLY) {
-			zone->cond = BLK_ZONE_COND_READONLY;
-			data_size = zonefs_check_zone_condition(inode, zone,
-								false, false);
-		}
+		if (!(z->z_flags & ZONEFS_ZONE_READONLY))
+			z->z_flags |= ZONEFS_ZONE_READONLY;
+		zonefs_inode_update_mode(inode);
+		data_size = isize;
 	} else if (sbi->s_mount_opts & ZONEFS_MNTOPT_ERRORS_RO &&
 		   data_size > isize) {
 		/* Do not expose garbage data */
@@ -455,9 +332,8 @@ static int zonefs_io_error_cb(struct blk_zone *zone, unsigned int idx,
 	 * close of the zone when the inode file is closed.
 	 */
 	if ((sbi->s_mount_opts & ZONEFS_MNTOPT_EXPLICIT_OPEN) &&
-	    (zone->cond == BLK_ZONE_COND_OFFLINE ||
-	     zone->cond == BLK_ZONE_COND_READONLY))
-		zi->i_flags &= ~ZONEFS_ZONE_OPEN;
+	    (z->z_flags & (ZONEFS_ZONE_READONLY | ZONEFS_ZONE_OFFLINE)))
+		z->z_flags &= ~ZONEFS_ZONE_OPEN;
 
 	/*
 	 * If error=remount-ro was specified, any error result in remounting
@@ -474,8 +350,8 @@ static int zonefs_io_error_cb(struct blk_zone *zone, unsigned int idx,
 	 */
 	zonefs_update_stats(inode, data_size);
 	zonefs_i_size_write(inode, data_size);
-	zi->i_wpoffset = data_size;
-	zonefs_account_active(inode);
+	z->z_wpoffset = data_size;
+	zonefs_inode_account_active(inode);
 
 	return 0;
 }
@@ -487,9 +363,9 @@ static int zonefs_io_error_cb(struct blk_zone *zone, unsigned int idx,
  * eventually correct the file size and zonefs inode write pointer offset
  * (which can be out of sync with the drive due to partial write failures).
  */
-static void __zonefs_io_error(struct inode *inode, bool write)
+void __zonefs_io_error(struct inode *inode, bool write)
 {
-	struct zonefs_inode_info *zi = ZONEFS_I(inode);
+	struct zonefs_zone *z = zonefs_inode_zone(inode);
 	struct super_block *sb = inode->i_sb;
 	struct zonefs_sb_info *sbi = ZONEFS_SB(sb);
 	unsigned int noio_flag;
@@ -505,8 +381,8 @@ static void __zonefs_io_error(struct inode *inode, bool write)
 	 * files with aggregated conventional zones, for which the inode zone
 	 * size is always larger than the device zone size.
 	 */
-	if (zi->i_zone_size > bdev_zone_sectors(sb->s_bdev))
-		nr_zones = zi->i_zone_size >>
+	if (z->z_size > bdev_zone_sectors(sb->s_bdev))
+		nr_zones = z->z_size >>
 			(sbi->s_zone_sectors_shift + SECTOR_SHIFT);
 
 	/*
@@ -518,7 +394,7 @@ static void __zonefs_io_error(struct inode *inode, bool write)
 	 * the GFP_NOIO context avoids both problems.
 	 */
 	noio_flag = memalloc_noio_save();
-	ret = blkdev_report_zones(sb->s_bdev, zi->i_zsector, nr_zones,
+	ret = blkdev_report_zones(sb->s_bdev, z->z_sector, nr_zones,
 				  zonefs_io_error_cb, &err);
 	if (ret != nr_zones)
 		zonefs_err(sb, "Get inode %lu zone information failed %d\n",
@@ -526,749 +402,6 @@ static void __zonefs_io_error(struct inode *inode, bool write)
 	memalloc_noio_restore(noio_flag);
 }
 
-static void zonefs_io_error(struct inode *inode, bool write)
-{
-	struct zonefs_inode_info *zi = ZONEFS_I(inode);
-
-	mutex_lock(&zi->i_truncate_mutex);
-	__zonefs_io_error(inode, write);
-	mutex_unlock(&zi->i_truncate_mutex);
-}
-
-static int zonefs_file_truncate(struct inode *inode, loff_t isize)
-{
-	struct zonefs_inode_info *zi = ZONEFS_I(inode);
-	loff_t old_isize;
-	enum req_op op;
-	int ret = 0;
-
-	/*
-	 * Only sequential zone files can be truncated and truncation is allowed
-	 * only down to a 0 size, which is equivalent to a zone reset, and to
-	 * the maximum file size, which is equivalent to a zone finish.
-	 */
-	if (zi->i_ztype != ZONEFS_ZTYPE_SEQ)
-		return -EPERM;
-
-	if (!isize)
-		op = REQ_OP_ZONE_RESET;
-	else if (isize == zi->i_max_size)
-		op = REQ_OP_ZONE_FINISH;
-	else
-		return -EPERM;
-
-	inode_dio_wait(inode);
-
-	/* Serialize against page faults */
-	filemap_invalidate_lock(inode->i_mapping);
-
-	/* Serialize against zonefs_iomap_begin() */
-	mutex_lock(&zi->i_truncate_mutex);
-
-	old_isize = i_size_read(inode);
-	if (isize == old_isize)
-		goto unlock;
-
-	ret = zonefs_zone_mgmt(inode, op);
-	if (ret)
-		goto unlock;
-
-	/*
-	 * If the mount option ZONEFS_MNTOPT_EXPLICIT_OPEN is set,
-	 * take care of open zones.
-	 */
-	if (zi->i_flags & ZONEFS_ZONE_OPEN) {
-		/*
-		 * Truncating a zone to EMPTY or FULL is the equivalent of
-		 * closing the zone. For a truncation to 0, we need to
-		 * re-open the zone to ensure new writes can be processed.
-		 * For a truncation to the maximum file size, the zone is
-		 * closed and writes cannot be accepted anymore, so clear
-		 * the open flag.
-		 */
-		if (!isize)
-			ret = zonefs_zone_mgmt(inode, REQ_OP_ZONE_OPEN);
-		else
-			zi->i_flags &= ~ZONEFS_ZONE_OPEN;
-	}
-
-	zonefs_update_stats(inode, isize);
-	truncate_setsize(inode, isize);
-	zi->i_wpoffset = isize;
-	zonefs_account_active(inode);
-
-unlock:
-	mutex_unlock(&zi->i_truncate_mutex);
-	filemap_invalidate_unlock(inode->i_mapping);
-
-	return ret;
-}
-
-static int zonefs_inode_setattr(struct mnt_idmap *idmap,
-				struct dentry *dentry, struct iattr *iattr)
-{
-	struct inode *inode = d_inode(dentry);
-	int ret;
-
-	if (unlikely(IS_IMMUTABLE(inode)))
-		return -EPERM;
-
-	ret = setattr_prepare(&nop_mnt_idmap, dentry, iattr);
-	if (ret)
-		return ret;
-
-	/*
-	 * Since files and directories cannot be created nor deleted, do not
-	 * allow setting any write attributes on the sub-directories grouping
-	 * files by zone type.
-	 */
-	if ((iattr->ia_valid & ATTR_MODE) && S_ISDIR(inode->i_mode) &&
-	    (iattr->ia_mode & 0222))
-		return -EPERM;
-
-	if (((iattr->ia_valid & ATTR_UID) &&
-	     !uid_eq(iattr->ia_uid, inode->i_uid)) ||
-	    ((iattr->ia_valid & ATTR_GID) &&
-	     !gid_eq(iattr->ia_gid, inode->i_gid))) {
-		ret = dquot_transfer(&nop_mnt_idmap, inode, iattr);
-		if (ret)
-			return ret;
-	}
-
-	if (iattr->ia_valid & ATTR_SIZE) {
-		ret = zonefs_file_truncate(inode, iattr->ia_size);
-		if (ret)
-			return ret;
-	}
-
-	setattr_copy(&nop_mnt_idmap, inode, iattr);
-
-	return 0;
-}
-
-static const struct inode_operations zonefs_file_inode_operations = {
-	.setattr	= zonefs_inode_setattr,
-};
-
-static int zonefs_file_fsync(struct file *file, loff_t start, loff_t end,
-			     int datasync)
-{
-	struct inode *inode = file_inode(file);
-	int ret = 0;
-
-	if (unlikely(IS_IMMUTABLE(inode)))
-		return -EPERM;
-
-	/*
-	 * Since only direct writes are allowed in sequential files, page cache
-	 * flush is needed only for conventional zone files.
-	 */
-	if (ZONEFS_I(inode)->i_ztype == ZONEFS_ZTYPE_CNV)
-		ret = file_write_and_wait_range(file, start, end);
-	if (!ret)
-		ret = blkdev_issue_flush(inode->i_sb->s_bdev);
-
-	if (ret)
-		zonefs_io_error(inode, true);
-
-	return ret;
-}
-
-static vm_fault_t zonefs_filemap_page_mkwrite(struct vm_fault *vmf)
-{
-	struct inode *inode = file_inode(vmf->vma->vm_file);
-	struct zonefs_inode_info *zi = ZONEFS_I(inode);
-	vm_fault_t ret;
-
-	if (unlikely(IS_IMMUTABLE(inode)))
-		return VM_FAULT_SIGBUS;
-
-	/*
-	 * Sanity check: only conventional zone files can have shared
-	 * writeable mappings.
-	 */
-	if (WARN_ON_ONCE(zi->i_ztype != ZONEFS_ZTYPE_CNV))
-		return VM_FAULT_NOPAGE;
-
-	sb_start_pagefault(inode->i_sb);
-	file_update_time(vmf->vma->vm_file);
-
-	/* Serialize against truncates */
-	filemap_invalidate_lock_shared(inode->i_mapping);
-	ret = iomap_page_mkwrite(vmf, &zonefs_write_iomap_ops);
-	filemap_invalidate_unlock_shared(inode->i_mapping);
-
-	sb_end_pagefault(inode->i_sb);
-	return ret;
-}
-
-static const struct vm_operations_struct zonefs_file_vm_ops = {
-	.fault		= filemap_fault,
-	.map_pages	= filemap_map_pages,
-	.page_mkwrite	= zonefs_filemap_page_mkwrite,
-};
-
-static int zonefs_file_mmap(struct file *file, struct vm_area_struct *vma)
-{
-	/*
-	 * Conventional zones accept random writes, so their files can support
-	 * shared writable mappings. For sequential zone files, only read
-	 * mappings are possible since there are no guarantees for write
-	 * ordering between msync() and page cache writeback.
-	 */
-	if (ZONEFS_I(file_inode(file))->i_ztype == ZONEFS_ZTYPE_SEQ &&
-	    (vma->vm_flags & VM_SHARED) && (vma->vm_flags & VM_MAYWRITE))
-		return -EINVAL;
-
-	file_accessed(file);
-	vma->vm_ops = &zonefs_file_vm_ops;
-
-	return 0;
-}
-
-static loff_t zonefs_file_llseek(struct file *file, loff_t offset, int whence)
-{
-	loff_t isize = i_size_read(file_inode(file));
-
-	/*
-	 * Seeks are limited to below the zone size for conventional zones
-	 * and below the zone write pointer for sequential zones. In both
-	 * cases, this limit is the inode size.
-	 */
-	return generic_file_llseek_size(file, offset, whence, isize, isize);
-}
-
-static int zonefs_file_write_dio_end_io(struct kiocb *iocb, ssize_t size,
-					int error, unsigned int flags)
-{
-	struct inode *inode = file_inode(iocb->ki_filp);
-	struct zonefs_inode_info *zi = ZONEFS_I(inode);
-
-	if (error) {
-		zonefs_io_error(inode, true);
-		return error;
-	}
-
-	if (size && zi->i_ztype != ZONEFS_ZTYPE_CNV) {
-		/*
-		 * Note that we may be seeing completions out of order,
-		 * but that is not a problem since a write completed
-		 * successfully necessarily means that all preceding writes
-		 * were also successful. So we can safely increase the inode
-		 * size to the write end location.
-		 */
-		mutex_lock(&zi->i_truncate_mutex);
-		if (i_size_read(inode) < iocb->ki_pos + size) {
-			zonefs_update_stats(inode, iocb->ki_pos + size);
-			zonefs_i_size_write(inode, iocb->ki_pos + size);
-		}
-		mutex_unlock(&zi->i_truncate_mutex);
-	}
-
-	return 0;
-}
-
-static const struct iomap_dio_ops zonefs_write_dio_ops = {
-	.end_io			= zonefs_file_write_dio_end_io,
-};
-
-static ssize_t zonefs_file_dio_append(struct kiocb *iocb, struct iov_iter *from)
-{
-	struct inode *inode = file_inode(iocb->ki_filp);
-	struct zonefs_inode_info *zi = ZONEFS_I(inode);
-	struct block_device *bdev = inode->i_sb->s_bdev;
-	unsigned int max = bdev_max_zone_append_sectors(bdev);
-	struct bio *bio;
-	ssize_t size;
-	int nr_pages;
-	ssize_t ret;
-
-	max = ALIGN_DOWN(max << SECTOR_SHIFT, inode->i_sb->s_blocksize);
-	iov_iter_truncate(from, max);
-
-	nr_pages = iov_iter_npages(from, BIO_MAX_VECS);
-	if (!nr_pages)
-		return 0;
-
-	bio = bio_alloc(bdev, nr_pages,
-			REQ_OP_ZONE_APPEND | REQ_SYNC | REQ_IDLE, GFP_NOFS);
-	bio->bi_iter.bi_sector = zi->i_zsector;
-	bio->bi_ioprio = iocb->ki_ioprio;
-	if (iocb_is_dsync(iocb))
-		bio->bi_opf |= REQ_FUA;
-
-	ret = bio_iov_iter_get_pages(bio, from);
-	if (unlikely(ret))
-		goto out_release;
-
-	size = bio->bi_iter.bi_size;
-	task_io_account_write(size);
-
-	if (iocb->ki_flags & IOCB_HIPRI)
-		bio_set_polled(bio, iocb);
-
-	ret = submit_bio_wait(bio);
-
-	/*
-	 * If the file zone was written underneath the file system, the zone
-	 * write pointer may not be where we expect it to be, but the zone
-	 * append write can still succeed. So check manually that we wrote where
-	 * we intended to, that is, at zi->i_wpoffset.
-	 */
-	if (!ret) {
-		sector_t wpsector =
-			zi->i_zsector + (zi->i_wpoffset >> SECTOR_SHIFT);
-
-		if (bio->bi_iter.bi_sector != wpsector) {
-			zonefs_warn(inode->i_sb,
-				"Corrupted write pointer %llu for zone at %llu\n",
-				wpsector, zi->i_zsector);
-			ret = -EIO;
-		}
-	}
-
-	zonefs_file_write_dio_end_io(iocb, size, ret, 0);
-	trace_zonefs_file_dio_append(inode, size, ret);
-
-out_release:
-	bio_release_pages(bio, false);
-	bio_put(bio);
-
-	if (ret >= 0) {
-		iocb->ki_pos += size;
-		return size;
-	}
-
-	return ret;
-}
-
-/*
- * Do not exceed the LFS limits nor the file zone size. If pos is under the
- * limit it becomes a short access. If it exceeds the limit, return -EFBIG.
- */
-static loff_t zonefs_write_check_limits(struct file *file, loff_t pos,
-					loff_t count)
-{
-	struct inode *inode = file_inode(file);
-	struct zonefs_inode_info *zi = ZONEFS_I(inode);
-	loff_t limit = rlimit(RLIMIT_FSIZE);
-	loff_t max_size = zi->i_max_size;
-
-	if (limit != RLIM_INFINITY) {
-		if (pos >= limit) {
-			send_sig(SIGXFSZ, current, 0);
-			return -EFBIG;
-		}
-		count = min(count, limit - pos);
-	}
-
-	if (!(file->f_flags & O_LARGEFILE))
-		max_size = min_t(loff_t, MAX_NON_LFS, max_size);
-
-	if (unlikely(pos >= max_size))
-		return -EFBIG;
-
-	return min(count, max_size - pos);
-}
-
-static ssize_t zonefs_write_checks(struct kiocb *iocb, struct iov_iter *from)
-{
-	struct file *file = iocb->ki_filp;
-	struct inode *inode = file_inode(file);
-	struct zonefs_inode_info *zi = ZONEFS_I(inode);
-	loff_t count;
-
-	if (IS_SWAPFILE(inode))
-		return -ETXTBSY;
-
-	if (!iov_iter_count(from))
-		return 0;
-
-	if ((iocb->ki_flags & IOCB_NOWAIT) && !(iocb->ki_flags & IOCB_DIRECT))
-		return -EINVAL;
-
-	if (iocb->ki_flags & IOCB_APPEND) {
-		if (zi->i_ztype != ZONEFS_ZTYPE_SEQ)
-			return -EINVAL;
-		mutex_lock(&zi->i_truncate_mutex);
-		iocb->ki_pos = zi->i_wpoffset;
-		mutex_unlock(&zi->i_truncate_mutex);
-	}
-
-	count = zonefs_write_check_limits(file, iocb->ki_pos,
-					  iov_iter_count(from));
-	if (count < 0)
-		return count;
-
-	iov_iter_truncate(from, count);
-	return iov_iter_count(from);
-}
-
-/*
- * Handle direct writes. For sequential zone files, this is the only possible
- * write path. For these files, check that the user is issuing writes
- * sequentially from the end of the file. This code assumes that the block layer
- * delivers write requests to the device in sequential order. This is always the
- * case if a block IO scheduler implementing the ELEVATOR_F_ZBD_SEQ_WRITE
- * elevator feature is being used (e.g. mq-deadline). The block layer always
- * automatically select such an elevator for zoned block devices during the
- * device initialization.
- */
-static ssize_t zonefs_file_dio_write(struct kiocb *iocb, struct iov_iter *from)
-{
-	struct inode *inode = file_inode(iocb->ki_filp);
-	struct zonefs_inode_info *zi = ZONEFS_I(inode);
-	struct super_block *sb = inode->i_sb;
-	bool sync = is_sync_kiocb(iocb);
-	bool append = false;
-	ssize_t ret, count;
-
-	/*
-	 * For async direct IOs to sequential zone files, refuse IOCB_NOWAIT
-	 * as this can cause write reordering (e.g. the first aio gets EAGAIN
-	 * on the inode lock but the second goes through but is now unaligned).
-	 */
-	if (zi->i_ztype == ZONEFS_ZTYPE_SEQ && !sync &&
-	    (iocb->ki_flags & IOCB_NOWAIT))
-		return -EOPNOTSUPP;
-
-	if (iocb->ki_flags & IOCB_NOWAIT) {
-		if (!inode_trylock(inode))
-			return -EAGAIN;
-	} else {
-		inode_lock(inode);
-	}
-
-	count = zonefs_write_checks(iocb, from);
-	if (count <= 0) {
-		ret = count;
-		goto inode_unlock;
-	}
-
-	if ((iocb->ki_pos | count) & (sb->s_blocksize - 1)) {
-		ret = -EINVAL;
-		goto inode_unlock;
-	}
-
-	/* Enforce sequential writes (append only) in sequential zones */
-	if (zi->i_ztype == ZONEFS_ZTYPE_SEQ) {
-		mutex_lock(&zi->i_truncate_mutex);
-		if (iocb->ki_pos != zi->i_wpoffset) {
-			mutex_unlock(&zi->i_truncate_mutex);
-			ret = -EINVAL;
-			goto inode_unlock;
-		}
-		mutex_unlock(&zi->i_truncate_mutex);
-		append = sync;
-	}
-
-	if (append)
-		ret = zonefs_file_dio_append(iocb, from);
-	else
-		ret = iomap_dio_rw(iocb, from, &zonefs_write_iomap_ops,
-				   &zonefs_write_dio_ops, 0, NULL, 0);
-	if (zi->i_ztype == ZONEFS_ZTYPE_SEQ &&
-	    (ret > 0 || ret == -EIOCBQUEUED)) {
-		if (ret > 0)
-			count = ret;
-
-		/*
-		 * Update the zone write pointer offset assuming the write
-		 * operation succeeded. If it did not, the error recovery path
-		 * will correct it. Also do active seq file accounting.
-		 */
-		mutex_lock(&zi->i_truncate_mutex);
-		zi->i_wpoffset += count;
-		zonefs_account_active(inode);
-		mutex_unlock(&zi->i_truncate_mutex);
-	}
-
-inode_unlock:
-	inode_unlock(inode);
-
-	return ret;
-}
-
-static ssize_t zonefs_file_buffered_write(struct kiocb *iocb,
-					  struct iov_iter *from)
-{
-	struct inode *inode = file_inode(iocb->ki_filp);
-	struct zonefs_inode_info *zi = ZONEFS_I(inode);
-	ssize_t ret;
-
-	/*
-	 * Direct IO writes are mandatory for sequential zone files so that the
-	 * write IO issuing order is preserved.
-	 */
-	if (zi->i_ztype != ZONEFS_ZTYPE_CNV)
-		return -EIO;
-
-	if (iocb->ki_flags & IOCB_NOWAIT) {
-		if (!inode_trylock(inode))
-			return -EAGAIN;
-	} else {
-		inode_lock(inode);
-	}
-
-	ret = zonefs_write_checks(iocb, from);
-	if (ret <= 0)
-		goto inode_unlock;
-
-	ret = iomap_file_buffered_write(iocb, from, &zonefs_write_iomap_ops);
-	if (ret > 0)
-		iocb->ki_pos += ret;
-	else if (ret == -EIO)
-		zonefs_io_error(inode, true);
-
-inode_unlock:
-	inode_unlock(inode);
-	if (ret > 0)
-		ret = generic_write_sync(iocb, ret);
-
-	return ret;
-}
-
-static ssize_t zonefs_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
-{
-	struct inode *inode = file_inode(iocb->ki_filp);
-
-	if (unlikely(IS_IMMUTABLE(inode)))
-		return -EPERM;
-
-	if (sb_rdonly(inode->i_sb))
-		return -EROFS;
-
-	/* Write operations beyond the zone size are not allowed */
-	if (iocb->ki_pos >= ZONEFS_I(inode)->i_max_size)
-		return -EFBIG;
-
-	if (iocb->ki_flags & IOCB_DIRECT) {
-		ssize_t ret = zonefs_file_dio_write(iocb, from);
-		if (ret != -ENOTBLK)
-			return ret;
-	}
-
-	return zonefs_file_buffered_write(iocb, from);
-}
-
-static int zonefs_file_read_dio_end_io(struct kiocb *iocb, ssize_t size,
-				       int error, unsigned int flags)
-{
-	if (error) {
-		zonefs_io_error(file_inode(iocb->ki_filp), false);
-		return error;
-	}
-
-	return 0;
-}
-
-static const struct iomap_dio_ops zonefs_read_dio_ops = {
-	.end_io			= zonefs_file_read_dio_end_io,
-};
-
-static ssize_t zonefs_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
-{
-	struct inode *inode = file_inode(iocb->ki_filp);
-	struct zonefs_inode_info *zi = ZONEFS_I(inode);
-	struct super_block *sb = inode->i_sb;
-	loff_t isize;
-	ssize_t ret;
-
-	/* Offline zones cannot be read */
-	if (unlikely(IS_IMMUTABLE(inode) && !(inode->i_mode & 0777)))
-		return -EPERM;
-
-	if (iocb->ki_pos >= zi->i_max_size)
-		return 0;
-
-	if (iocb->ki_flags & IOCB_NOWAIT) {
-		if (!inode_trylock_shared(inode))
-			return -EAGAIN;
-	} else {
-		inode_lock_shared(inode);
-	}
-
-	/* Limit read operations to written data */
-	mutex_lock(&zi->i_truncate_mutex);
-	isize = i_size_read(inode);
-	if (iocb->ki_pos >= isize) {
-		mutex_unlock(&zi->i_truncate_mutex);
-		ret = 0;
-		goto inode_unlock;
-	}
-	iov_iter_truncate(to, isize - iocb->ki_pos);
-	mutex_unlock(&zi->i_truncate_mutex);
-
-	if (iocb->ki_flags & IOCB_DIRECT) {
-		size_t count = iov_iter_count(to);
-
-		if ((iocb->ki_pos | count) & (sb->s_blocksize - 1)) {
-			ret = -EINVAL;
-			goto inode_unlock;
-		}
-		file_accessed(iocb->ki_filp);
-		ret = iomap_dio_rw(iocb, to, &zonefs_read_iomap_ops,
-				   &zonefs_read_dio_ops, 0, NULL, 0);
-	} else {
-		ret = generic_file_read_iter(iocb, to);
-		if (ret == -EIO)
-			zonefs_io_error(inode, false);
-	}
-
-inode_unlock:
-	inode_unlock_shared(inode);
-
-	return ret;
-}
-
-/*
- * Write open accounting is done only for sequential files.
- */
-static inline bool zonefs_seq_file_need_wro(struct inode *inode,
-					    struct file *file)
-{
-	struct zonefs_inode_info *zi = ZONEFS_I(inode);
-
-	if (zi->i_ztype != ZONEFS_ZTYPE_SEQ)
-		return false;
-
-	if (!(file->f_mode & FMODE_WRITE))
-		return false;
-
-	return true;
-}
-
-static int zonefs_seq_file_write_open(struct inode *inode)
-{
-	struct zonefs_inode_info *zi = ZONEFS_I(inode);
-	int ret = 0;
-
-	mutex_lock(&zi->i_truncate_mutex);
-
-	if (!zi->i_wr_refcnt) {
-		struct zonefs_sb_info *sbi = ZONEFS_SB(inode->i_sb);
-		unsigned int wro = atomic_inc_return(&sbi->s_wro_seq_files);
-
-		if (sbi->s_mount_opts & ZONEFS_MNTOPT_EXPLICIT_OPEN) {
-
-			if (sbi->s_max_wro_seq_files
-			    && wro > sbi->s_max_wro_seq_files) {
-				atomic_dec(&sbi->s_wro_seq_files);
-				ret = -EBUSY;
-				goto unlock;
-			}
-
-			if (i_size_read(inode) < zi->i_max_size) {
-				ret = zonefs_zone_mgmt(inode, REQ_OP_ZONE_OPEN);
-				if (ret) {
-					atomic_dec(&sbi->s_wro_seq_files);
-					goto unlock;
-				}
-				zi->i_flags |= ZONEFS_ZONE_OPEN;
-				zonefs_account_active(inode);
-			}
-		}
-	}
-
-	zi->i_wr_refcnt++;
-
-unlock:
-	mutex_unlock(&zi->i_truncate_mutex);
-
-	return ret;
-}
-
-static int zonefs_file_open(struct inode *inode, struct file *file)
-{
-	int ret;
-
-	ret = generic_file_open(inode, file);
-	if (ret)
-		return ret;
-
-	if (zonefs_seq_file_need_wro(inode, file))
-		return zonefs_seq_file_write_open(inode);
-
-	return 0;
-}
-
-static void zonefs_seq_file_write_close(struct inode *inode)
-{
-	struct zonefs_inode_info *zi = ZONEFS_I(inode);
-	struct super_block *sb = inode->i_sb;
-	struct zonefs_sb_info *sbi = ZONEFS_SB(sb);
-	int ret = 0;
-
-	mutex_lock(&zi->i_truncate_mutex);
-
-	zi->i_wr_refcnt--;
-	if (zi->i_wr_refcnt)
-		goto unlock;
-
-	/*
-	 * The file zone may not be open anymore (e.g. the file was truncated to
-	 * its maximum size or it was fully written). For this case, we only
-	 * need to decrement the write open count.
-	 */
-	if (zi->i_flags & ZONEFS_ZONE_OPEN) {
-		ret = zonefs_zone_mgmt(inode, REQ_OP_ZONE_CLOSE);
-		if (ret) {
-			__zonefs_io_error(inode, false);
-			/*
-			 * Leaving zones explicitly open may lead to a state
-			 * where most zones cannot be written (zone resources
-			 * exhausted). So take preventive action by remounting
-			 * read-only.
-			 */
-			if (zi->i_flags & ZONEFS_ZONE_OPEN &&
-			    !(sb->s_flags & SB_RDONLY)) {
-				zonefs_warn(sb,
-					"closing zone at %llu failed %d\n",
-					zi->i_zsector, ret);
-				zonefs_warn(sb,
-					"remounting filesystem read-only\n");
-				sb->s_flags |= SB_RDONLY;
-			}
-			goto unlock;
-		}
-
-		zi->i_flags &= ~ZONEFS_ZONE_OPEN;
-		zonefs_account_active(inode);
-	}
-
-	atomic_dec(&sbi->s_wro_seq_files);
-
-unlock:
-	mutex_unlock(&zi->i_truncate_mutex);
-}
-
-static int zonefs_file_release(struct inode *inode, struct file *file)
-{
-	/*
-	 * If we explicitly open a zone we must close it again as well, but the
-	 * zone management operation can fail (either due to an IO error or as
-	 * the zone has gone offline or read-only). Make sure we don't fail the
-	 * close(2) for user-space.
-	 */
-	if (zonefs_seq_file_need_wro(inode, file))
-		zonefs_seq_file_write_close(inode);
-
-	return 0;
-}
-
-static const struct file_operations zonefs_file_operations = {
-	.open		= zonefs_file_open,
-	.release	= zonefs_file_release,
-	.fsync		= zonefs_file_fsync,
-	.mmap		= zonefs_file_mmap,
-	.llseek		= zonefs_file_llseek,
-	.read_iter	= zonefs_file_read_iter,
-	.write_iter	= zonefs_file_write_iter,
-	.splice_read	= generic_file_splice_read,
-	.splice_write	= iter_file_splice_write,
-	.iopoll		= iocb_bio_iopoll,
-};
-
 static struct kmem_cache *zonefs_inode_cachep;
 
 static struct inode *zonefs_alloc_inode(struct super_block *sb)
@@ -1282,7 +415,6 @@ static struct inode *zonefs_alloc_inode(struct super_block *sb)
 	inode_init_once(&zi->i_vnode);
 	mutex_init(&zi->i_truncate_mutex);
 	zi->i_wr_refcnt = 0;
-	zi->i_flags = 0;
 
 	return &zi->i_vnode;
 }
@@ -1315,8 +447,8 @@ static int zonefs_statfs(struct dentry *dentry, struct kstatfs *buf)
 	buf->f_bavail = buf->f_bfree;
 
 	for (t = 0; t < ZONEFS_ZTYPE_MAX; t++) {
-		if (sbi->s_nr_files[t])
-			buf->f_files += sbi->s_nr_files[t] + 1;
+		if (sbi->s_zgroup[t].g_nr_zones)
+			buf->f_files += sbi->s_zgroup[t].g_nr_zones + 1;
 	}
 	buf->f_ffree = 0;
 
@@ -1408,185 +540,440 @@ static int zonefs_remount(struct super_block *sb, int *flags, char *data)
 	return zonefs_parse_options(sb, data);
 }
 
-static const struct super_operations zonefs_sops = {
-	.alloc_inode	= zonefs_alloc_inode,
-	.free_inode	= zonefs_free_inode,
-	.statfs		= zonefs_statfs,
-	.remount_fs	= zonefs_remount,
-	.show_options	= zonefs_show_options,
-};
+static int zonefs_inode_setattr(struct mnt_idmap *idmap,
+				struct dentry *dentry, struct iattr *iattr)
+{
+	struct inode *inode = d_inode(dentry);
+	int ret;
+
+	if (unlikely(IS_IMMUTABLE(inode)))
+		return -EPERM;
+
+	ret = setattr_prepare(&nop_mnt_idmap, dentry, iattr);
+	if (ret)
+		return ret;
+
+	/*
+	 * Since files and directories cannot be created nor deleted, do not
+	 * allow setting any write attributes on the sub-directories grouping
+	 * files by zone type.
+	 */
+	if ((iattr->ia_valid & ATTR_MODE) && S_ISDIR(inode->i_mode) &&
+	    (iattr->ia_mode & 0222))
+		return -EPERM;
+
+	if (((iattr->ia_valid & ATTR_UID) &&
+	     !uid_eq(iattr->ia_uid, inode->i_uid)) ||
+	    ((iattr->ia_valid & ATTR_GID) &&
+	     !gid_eq(iattr->ia_gid, inode->i_gid))) {
+		ret = dquot_transfer(&nop_mnt_idmap, inode, iattr);
+		if (ret)
+			return ret;
+	}
+
+	if (iattr->ia_valid & ATTR_SIZE) {
+		ret = zonefs_file_truncate(inode, iattr->ia_size);
+		if (ret)
+			return ret;
+	}
 
-static const struct inode_operations zonefs_dir_inode_operations = {
-	.lookup		= simple_lookup,
+	setattr_copy(&nop_mnt_idmap, inode, iattr);
+
+	if (S_ISREG(inode->i_mode)) {
+		struct zonefs_zone *z = zonefs_inode_zone(inode);
+
+		z->z_mode = inode->i_mode;
+		z->z_uid = inode->i_uid;
+		z->z_gid = inode->i_gid;
+	}
+
+	return 0;
+}
+
+static const struct inode_operations zonefs_file_inode_operations = {
 	.setattr	= zonefs_inode_setattr,
 };
 
-static void zonefs_init_dir_inode(struct inode *parent, struct inode *inode,
-				  enum zonefs_ztype type)
+static long zonefs_fname_to_fno(const struct qstr *fname)
 {
-	struct super_block *sb = parent->i_sb;
+	const char *name = fname->name;
+	unsigned int len = fname->len;
+	long fno = 0, shift = 1;
+	const char *rname;
+	char c = *name;
+	unsigned int i;
 
-	inode->i_ino = bdev_nr_zones(sb->s_bdev) + type + 1;
-	inode_init_owner(&nop_mnt_idmap, inode, parent, S_IFDIR | 0555);
-	inode->i_op = &zonefs_dir_inode_operations;
-	inode->i_fop = &simple_dir_operations;
-	set_nlink(inode, 2);
-	inc_nlink(parent);
+	/*
+	 * File names are always a base-10 number string without any
+	 * leading 0s.
+	 */
+	if (!isdigit(c))
+		return -ENOENT;
+
+	if (len > 1 && c == '0')
+		return -ENOENT;
+
+	if (len == 1)
+		return c - '0';
+
+	for (i = 0, rname = name + len - 1; i < len; i++, rname--) {
+		c = *rname;
+		if (!isdigit(c))
+			return -ENOENT;
+		fno += (c - '0') * shift;
+		shift *= 10;
+	}
+
+	return fno;
 }
 
-static int zonefs_init_file_inode(struct inode *inode, struct blk_zone *zone,
-				  enum zonefs_ztype type)
+static struct inode *zonefs_get_file_inode(struct inode *dir,
+					   struct dentry *dentry)
 {
-	struct super_block *sb = inode->i_sb;
+	struct zonefs_zone_group *zgroup = dir->i_private;
+	struct super_block *sb = dir->i_sb;
 	struct zonefs_sb_info *sbi = ZONEFS_SB(sb);
-	struct zonefs_inode_info *zi = ZONEFS_I(inode);
-	int ret = 0;
+	struct zonefs_zone *z;
+	struct inode *inode;
+	ino_t ino;
+	long fno;
 
-	inode->i_ino = zone->start >> sbi->s_zone_sectors_shift;
-	inode->i_mode = S_IFREG | sbi->s_perm;
+	/* Get the file number from the file name */
+	fno = zonefs_fname_to_fno(&dentry->d_name);
+	if (fno < 0)
+		return ERR_PTR(fno);
 
-	zi->i_ztype = type;
-	zi->i_zsector = zone->start;
-	zi->i_zone_size = zone->len << SECTOR_SHIFT;
-	if (zi->i_zone_size > bdev_zone_sectors(sb->s_bdev) << SECTOR_SHIFT &&
-	    !(sbi->s_features & ZONEFS_F_AGGRCNV)) {
-		zonefs_err(sb,
-			   "zone size %llu doesn't match device's zone sectors %llu\n",
-			   zi->i_zone_size,
-			   bdev_zone_sectors(sb->s_bdev) << SECTOR_SHIFT);
-		return -EINVAL;
-	}
+	if (!zgroup->g_nr_zones || fno >= zgroup->g_nr_zones)
+		return ERR_PTR(-ENOENT);
 
-	zi->i_max_size = min_t(loff_t, MAX_LFS_FILESIZE,
-			       zone->capacity << SECTOR_SHIFT);
-	zi->i_wpoffset = zonefs_check_zone_condition(inode, zone, true, true);
+	z = &zgroup->g_zones[fno];
+	ino = z->z_sector >> sbi->s_zone_sectors_shift;
+	inode = iget_locked(sb, ino);
+	if (!inode)
+		return ERR_PTR(-ENOMEM);
+	if (!(inode->i_state & I_NEW)) {
+		WARN_ON_ONCE(inode->i_private != z);
+		return inode;
+	}
 
-	inode->i_uid = sbi->s_uid;
-	inode->i_gid = sbi->s_gid;
-	inode->i_size = zi->i_wpoffset;
-	inode->i_blocks = zi->i_max_size >> SECTOR_SHIFT;
+	inode->i_ino = ino;
+	inode->i_mode = z->z_mode;
+	inode->i_ctime = inode->i_mtime = inode->i_atime = dir->i_ctime;
+	inode->i_uid = z->z_uid;
+	inode->i_gid = z->z_gid;
+	inode->i_size = z->z_wpoffset;
+	inode->i_blocks = z->z_capacity >> SECTOR_SHIFT;
+	inode->i_private = z;
 
 	inode->i_op = &zonefs_file_inode_operations;
 	inode->i_fop = &zonefs_file_operations;
 	inode->i_mapping->a_ops = &zonefs_file_aops;
 
-	sb->s_maxbytes = max(zi->i_max_size, sb->s_maxbytes);
-	sbi->s_blocks += zi->i_max_size >> sb->s_blocksize_bits;
-	sbi->s_used_blocks += zi->i_wpoffset >> sb->s_blocksize_bits;
+	/* Update the inode access rights depending on the zone condition */
+	zonefs_inode_update_mode(inode);
+
+	unlock_new_inode(inode);
+
+	return inode;
+}
+
+static struct inode *zonefs_get_zgroup_inode(struct super_block *sb,
+					     enum zonefs_ztype ztype)
+{
+	struct inode *root = d_inode(sb->s_root);
+	struct zonefs_sb_info *sbi = ZONEFS_SB(sb);
+	struct inode *inode;
+	ino_t ino = bdev_nr_zones(sb->s_bdev) + ztype + 1;
+
+	inode = iget_locked(sb, ino);
+	if (!inode)
+		return ERR_PTR(-ENOMEM);
+	if (!(inode->i_state & I_NEW))
+		return inode;
+
+	inode->i_ino = ino;
+	inode_init_owner(&nop_mnt_idmap, inode, root, S_IFDIR | 0555);
+	inode->i_size = sbi->s_zgroup[ztype].g_nr_zones;
+	inode->i_ctime = inode->i_mtime = inode->i_atime = root->i_ctime;
+	inode->i_private = &sbi->s_zgroup[ztype];
+	set_nlink(inode, 2);
+
+	inode->i_op = &zonefs_dir_inode_operations;
+	inode->i_fop = &zonefs_dir_operations;
+
+	unlock_new_inode(inode);
+
+	return inode;
+}
 
-	mutex_lock(&zi->i_truncate_mutex);
+
+static struct inode *zonefs_get_dir_inode(struct inode *dir,
+					  struct dentry *dentry)
+{
+	struct super_block *sb = dir->i_sb;
+	struct zonefs_sb_info *sbi = ZONEFS_SB(sb);
+	const char *name = dentry->d_name.name;
+	enum zonefs_ztype ztype;
 
 	/*
-	 * For sequential zones, make sure that any open zone is closed first
-	 * to ensure that the initial number of open zones is 0, in sync with
-	 * the open zone accounting done when the mount option
-	 * ZONEFS_MNTOPT_EXPLICIT_OPEN is used.
+	 * We only need to check for the "seq" directory and
+	 * the "cnv" directory if we have conventional zones.
 	 */
-	if (type == ZONEFS_ZTYPE_SEQ &&
-	    (zone->cond == BLK_ZONE_COND_IMP_OPEN ||
-	     zone->cond == BLK_ZONE_COND_EXP_OPEN)) {
-		ret = zonefs_zone_mgmt(inode, REQ_OP_ZONE_CLOSE);
-		if (ret)
-			goto unlock;
+	if (dentry->d_name.len != 3)
+		return ERR_PTR(-ENOENT);
+
+	for (ztype = 0; ztype < ZONEFS_ZTYPE_MAX; ztype++) {
+		if (sbi->s_zgroup[ztype].g_nr_zones &&
+		    memcmp(name, zonefs_zgroup_name(ztype), 3) == 0)
+			break;
 	}
+	if (ztype == ZONEFS_ZTYPE_MAX)
+		return ERR_PTR(-ENOENT);
 
-	zonefs_account_active(inode);
+	return zonefs_get_zgroup_inode(sb, ztype);
+}
 
-unlock:
-	mutex_unlock(&zi->i_truncate_mutex);
+static struct dentry *zonefs_lookup(struct inode *dir, struct dentry *dentry,
+				    unsigned int flags)
+{
+	struct inode *inode;
 
-	return ret;
+	if (dentry->d_name.len > ZONEFS_NAME_MAX)
+		return ERR_PTR(-ENAMETOOLONG);
+
+	if (dir == d_inode(dir->i_sb->s_root))
+		inode = zonefs_get_dir_inode(dir, dentry);
+	else
+		inode = zonefs_get_file_inode(dir, dentry);
+	if (IS_ERR(inode))
+		return ERR_CAST(inode);
+
+	return d_splice_alias(inode, dentry);
 }
 
-static struct dentry *zonefs_create_inode(struct dentry *parent,
-					const char *name, struct blk_zone *zone,
-					enum zonefs_ztype type)
+static int zonefs_readdir_root(struct file *file, struct dir_context *ctx)
 {
-	struct inode *dir = d_inode(parent);
-	struct dentry *dentry;
-	struct inode *inode;
-	int ret = -ENOMEM;
+	struct inode *inode = file_inode(file);
+	struct super_block *sb = inode->i_sb;
+	struct zonefs_sb_info *sbi = ZONEFS_SB(sb);
+	enum zonefs_ztype ztype = ZONEFS_ZTYPE_CNV;
+	ino_t base_ino = bdev_nr_zones(sb->s_bdev) + 1;
 
-	dentry = d_alloc_name(parent, name);
-	if (!dentry)
-		return ERR_PTR(ret);
+	if (ctx->pos >= inode->i_size)
+		return 0;
 
-	inode = new_inode(parent->d_sb);
-	if (!inode)
-		goto dput;
+	if (!dir_emit_dots(file, ctx))
+		return 0;
 
-	inode->i_ctime = inode->i_mtime = inode->i_atime = dir->i_ctime;
-	if (zone) {
-		ret = zonefs_init_file_inode(inode, zone, type);
-		if (ret) {
-			iput(inode);
-			goto dput;
-		}
-	} else {
-		zonefs_init_dir_inode(dir, inode, type);
+	if (ctx->pos == 2) {
+		if (!sbi->s_zgroup[ZONEFS_ZTYPE_CNV].g_nr_zones)
+			ztype = ZONEFS_ZTYPE_SEQ;
+
+		if (!dir_emit(ctx, zonefs_zgroup_name(ztype), 3,
+			      base_ino + ztype, DT_DIR))
+			return 0;
+		ctx->pos++;
 	}
 
-	d_add(dentry, inode);
-	dir->i_size++;
+	if (ctx->pos == 3 && ztype != ZONEFS_ZTYPE_SEQ) {
+		ztype = ZONEFS_ZTYPE_SEQ;
+		if (!dir_emit(ctx, zonefs_zgroup_name(ztype), 3,
+			      base_ino + ztype, DT_DIR))
+			return 0;
+		ctx->pos++;
+	}
 
-	return dentry;
+	return 0;
+}
+
+static int zonefs_readdir_zgroup(struct file *file,
+				 struct dir_context *ctx)
+{
+	struct inode *inode = file_inode(file);
+	struct zonefs_zone_group *zgroup = inode->i_private;
+	struct super_block *sb = inode->i_sb;
+	struct zonefs_sb_info *sbi = ZONEFS_SB(sb);
+	struct zonefs_zone *z;
+	int fname_len;
+	char *fname;
+	ino_t ino;
+	int f;
+
+	/*
+	 * The size of zone group directories is equal to the number
+	 * of zone files in the group and does note include the "." and
+	 * ".." entries. Hence the "+ 2" here.
+	 */
+	if (ctx->pos >= inode->i_size + 2)
+		return 0;
+
+	if (!dir_emit_dots(file, ctx))
+		return 0;
+
+	fname = kmalloc(ZONEFS_NAME_MAX, GFP_KERNEL);
+	if (!fname)
+		return -ENOMEM;
+
+	for (f = ctx->pos - 2; f < zgroup->g_nr_zones; f++) {
+		z = &zgroup->g_zones[f];
+		ino = z->z_sector >> sbi->s_zone_sectors_shift;
+		fname_len = snprintf(fname, ZONEFS_NAME_MAX - 1, "%u", f);
+		if (!dir_emit(ctx, fname, fname_len, ino, DT_REG))
+			break;
+		ctx->pos++;
+	}
 
-dput:
-	dput(dentry);
+	kfree(fname);
 
-	return ERR_PTR(ret);
+	return 0;
+}
+
+static int zonefs_readdir(struct file *file, struct dir_context *ctx)
+{
+	struct inode *inode = file_inode(file);
+
+	if (inode == d_inode(inode->i_sb->s_root))
+		return zonefs_readdir_root(file, ctx);
+
+	return zonefs_readdir_zgroup(file, ctx);
 }
 
+const struct inode_operations zonefs_dir_inode_operations = {
+	.lookup		= zonefs_lookup,
+	.setattr	= zonefs_inode_setattr,
+};
+
+const struct file_operations zonefs_dir_operations = {
+	.llseek		= generic_file_llseek,
+	.read		= generic_read_dir,
+	.iterate_shared	= zonefs_readdir,
+};
+
 struct zonefs_zone_data {
 	struct super_block	*sb;
 	unsigned int		nr_zones[ZONEFS_ZTYPE_MAX];
+	sector_t		cnv_zone_start;
 	struct blk_zone		*zones;
 };
 
+static int zonefs_get_zone_info_cb(struct blk_zone *zone, unsigned int idx,
+				   void *data)
+{
+	struct zonefs_zone_data *zd = data;
+	struct super_block *sb = zd->sb;
+	struct zonefs_sb_info *sbi = ZONEFS_SB(sb);
+
+	/*
+	 * We do not care about the first zone: it contains the super block
+	 * and not exposed as a file.
+	 */
+	if (!idx)
+		return 0;
+
+	/*
+	 * Count the number of zones that will be exposed as files.
+	 * For sequential zones, we always have as many files as zones.
+	 * FOr conventional zones, the number of files depends on if we have
+	 * conventional zones aggregation enabled.
+	 */
+	switch (zone->type) {
+	case BLK_ZONE_TYPE_CONVENTIONAL:
+		if (sbi->s_features & ZONEFS_F_AGGRCNV) {
+			/* One file per set of contiguous conventional zones */
+			if (!(sbi->s_zgroup[ZONEFS_ZTYPE_CNV].g_nr_zones) ||
+			    zone->start != zd->cnv_zone_start)
+				sbi->s_zgroup[ZONEFS_ZTYPE_CNV].g_nr_zones++;
+			zd->cnv_zone_start = zone->start + zone->len;
+		} else {
+			/* One file per zone */
+			sbi->s_zgroup[ZONEFS_ZTYPE_CNV].g_nr_zones++;
+		}
+		break;
+	case BLK_ZONE_TYPE_SEQWRITE_REQ:
+	case BLK_ZONE_TYPE_SEQWRITE_PREF:
+		sbi->s_zgroup[ZONEFS_ZTYPE_SEQ].g_nr_zones++;
+		break;
+	default:
+		zonefs_err(zd->sb, "Unsupported zone type 0x%x\n",
+			   zone->type);
+		return -EIO;
+	}
+
+	memcpy(&zd->zones[idx], zone, sizeof(struct blk_zone));
+
+	return 0;
+}
+
+static int zonefs_get_zone_info(struct zonefs_zone_data *zd)
+{
+	struct block_device *bdev = zd->sb->s_bdev;
+	int ret;
+
+	zd->zones = kvcalloc(bdev_nr_zones(bdev), sizeof(struct blk_zone),
+			     GFP_KERNEL);
+	if (!zd->zones)
+		return -ENOMEM;
+
+	/* Get zones information from the device */
+	ret = blkdev_report_zones(bdev, 0, BLK_ALL_ZONES,
+				  zonefs_get_zone_info_cb, zd);
+	if (ret < 0) {
+		zonefs_err(zd->sb, "Zone report failed %d\n", ret);
+		return ret;
+	}
+
+	if (ret != bdev_nr_zones(bdev)) {
+		zonefs_err(zd->sb, "Invalid zone report (%d/%u zones)\n",
+			   ret, bdev_nr_zones(bdev));
+		return -EIO;
+	}
+
+	return 0;
+}
+
+static inline void zonefs_free_zone_info(struct zonefs_zone_data *zd)
+{
+	kvfree(zd->zones);
+}
+
 /*
  * Create a zone group and populate it with zone files.
  */
-static int zonefs_create_zgroup(struct zonefs_zone_data *zd,
-				enum zonefs_ztype type)
+static int zonefs_init_zgroup(struct super_block *sb,
+			      struct zonefs_zone_data *zd,
+			      enum zonefs_ztype ztype)
 {
-	struct super_block *sb = zd->sb;
 	struct zonefs_sb_info *sbi = ZONEFS_SB(sb);
+	struct zonefs_zone_group *zgroup = &sbi->s_zgroup[ztype];
 	struct blk_zone *zone, *next, *end;
-	const char *zgroup_name;
-	char *file_name;
-	struct dentry *dir, *dent;
+	struct zonefs_zone *z;
 	unsigned int n = 0;
 	int ret;
 
-	/* If the group is empty, there is nothing to do */
-	if (!zd->nr_zones[type])
+	/* Allocate the zone group. If it is empty, we have nothing to do. */
+	if (!zgroup->g_nr_zones)
 		return 0;
 
-	file_name = kmalloc(ZONEFS_NAME_MAX, GFP_KERNEL);
-	if (!file_name)
+	zgroup->g_zones = kvcalloc(zgroup->g_nr_zones,
+				   sizeof(struct zonefs_zone), GFP_KERNEL);
+	if (!zgroup->g_zones)
 		return -ENOMEM;
 
-	if (type == ZONEFS_ZTYPE_CNV)
-		zgroup_name = "cnv";
-	else
-		zgroup_name = "seq";
-
-	dir = zonefs_create_inode(sb->s_root, zgroup_name, NULL, type);
-	if (IS_ERR(dir)) {
-		ret = PTR_ERR(dir);
-		goto free;
-	}
-
 	/*
-	 * The first zone contains the super block: skip it.
+	 * Initialize the zone groups using the device zone information.
+	 * We always skip the first zone as it contains the super block
+	 * and is not use to back a file.
 	 */
 	end = zd->zones + bdev_nr_zones(sb->s_bdev);
 	for (zone = &zd->zones[1]; zone < end; zone = next) {
 
 		next = zone + 1;
-		if (zonefs_zone_type(zone) != type)
+		if (zonefs_zone_type(zone) != ztype)
 			continue;
 
+		if (WARN_ON_ONCE(n >= zgroup->g_nr_zones))
+			return -EINVAL;
+
 		/*
 		 * For conventional zones, contiguous zones can be aggregated
 		 * together to form larger files. Note that this overwrites the
@@ -1595,10 +982,10 @@ static int zonefs_create_zgroup(struct zonefs_zone_data *zd,
 		 * found, assume that all zones aggregated have the same
 		 * condition.
 		 */
-		if (type == ZONEFS_ZTYPE_CNV &&
+		if (ztype == ZONEFS_ZTYPE_CNV &&
 		    (sbi->s_features & ZONEFS_F_AGGRCNV)) {
 			for (; next < end; next++) {
-				if (zonefs_zone_type(next) != type)
+				if (zonefs_zone_type(next) != ztype)
 					break;
 				zone->len += next->len;
 				zone->capacity += next->capacity;
@@ -1608,99 +995,118 @@ static int zonefs_create_zgroup(struct zonefs_zone_data *zd,
 				else if (next->cond == BLK_ZONE_COND_OFFLINE)
 					zone->cond = BLK_ZONE_COND_OFFLINE;
 			}
-			if (zone->capacity != zone->len) {
-				zonefs_err(sb, "Invalid conventional zone capacity\n");
-				ret = -EINVAL;
-				goto free;
-			}
 		}
 
+		z = &zgroup->g_zones[n];
+		if (ztype == ZONEFS_ZTYPE_CNV)
+			z->z_flags |= ZONEFS_ZONE_CNV;
+		z->z_sector = zone->start;
+		z->z_size = zone->len << SECTOR_SHIFT;
+		if (z->z_size > bdev_zone_sectors(sb->s_bdev) << SECTOR_SHIFT &&
+		    !(sbi->s_features & ZONEFS_F_AGGRCNV)) {
+			zonefs_err(sb,
+				"Invalid zone size %llu (device zone sectors %llu)\n",
+				z->z_size,
+				bdev_zone_sectors(sb->s_bdev) << SECTOR_SHIFT);
+			return -EINVAL;
+		}
+
+		z->z_capacity = min_t(loff_t, MAX_LFS_FILESIZE,
+				      zone->capacity << SECTOR_SHIFT);
+		z->z_wpoffset = zonefs_check_zone_condition(sb, z, zone);
+
+		z->z_mode = S_IFREG | sbi->s_perm;
+		z->z_uid = sbi->s_uid;
+		z->z_gid = sbi->s_gid;
+
 		/*
-		 * Use the file number within its group as file name.
+		 * Let zonefs_inode_update_mode() know that we will need
+		 * special initialization of the inode mode the first time
+		 * it is accessed.
 		 */
-		snprintf(file_name, ZONEFS_NAME_MAX - 1, "%u", n);
-		dent = zonefs_create_inode(dir, file_name, zone, type);
-		if (IS_ERR(dent)) {
-			ret = PTR_ERR(dent);
-			goto free;
+		z->z_flags |= ZONEFS_ZONE_INIT_MODE;
+
+		sb->s_maxbytes = max(z->z_capacity, sb->s_maxbytes);
+		sbi->s_blocks += z->z_capacity >> sb->s_blocksize_bits;
+		sbi->s_used_blocks += z->z_wpoffset >> sb->s_blocksize_bits;
+
+		/*
+		 * For sequential zones, make sure that any open zone is closed
+		 * first to ensure that the initial number of open zones is 0,
+		 * in sync with the open zone accounting done when the mount
+		 * option ZONEFS_MNTOPT_EXPLICIT_OPEN is used.
+		 */
+		if (ztype == ZONEFS_ZTYPE_SEQ &&
+		    (zone->cond == BLK_ZONE_COND_IMP_OPEN ||
+		     zone->cond == BLK_ZONE_COND_EXP_OPEN)) {
+			ret = zonefs_zone_mgmt(sb, z, REQ_OP_ZONE_CLOSE);
+			if (ret)
+				return ret;
 		}
 
+		zonefs_account_active(sb, z);
+
 		n++;
 	}
 
-	zonefs_info(sb, "Zone group \"%s\" has %u file%s\n",
-		    zgroup_name, n, n > 1 ? "s" : "");
-
-	sbi->s_nr_files[type] = n;
-	ret = 0;
+	if (WARN_ON_ONCE(n != zgroup->g_nr_zones))
+		return -EINVAL;
 
-free:
-	kfree(file_name);
+	zonefs_info(sb, "Zone group \"%s\" has %u file%s\n",
+		    zonefs_zgroup_name(ztype),
+		    zgroup->g_nr_zones,
+		    zgroup->g_nr_zones > 1 ? "s" : "");
 
-	return ret;
+	return 0;
 }
 
-static int zonefs_get_zone_info_cb(struct blk_zone *zone, unsigned int idx,
-				   void *data)
+static void zonefs_free_zgroups(struct super_block *sb)
 {
-	struct zonefs_zone_data *zd = data;
-
-	/*
-	 * Count the number of usable zones: the first zone at index 0 contains
-	 * the super block and is ignored.
-	 */
-	switch (zone->type) {
-	case BLK_ZONE_TYPE_CONVENTIONAL:
-		zone->wp = zone->start + zone->len;
-		if (idx)
-			zd->nr_zones[ZONEFS_ZTYPE_CNV]++;
-		break;
-	case BLK_ZONE_TYPE_SEQWRITE_REQ:
-	case BLK_ZONE_TYPE_SEQWRITE_PREF:
-		if (idx)
-			zd->nr_zones[ZONEFS_ZTYPE_SEQ]++;
-		break;
-	default:
-		zonefs_err(zd->sb, "Unsupported zone type 0x%x\n",
-			   zone->type);
-		return -EIO;
-	}
+	struct zonefs_sb_info *sbi = ZONEFS_SB(sb);
+	enum zonefs_ztype ztype;
 
-	memcpy(&zd->zones[idx], zone, sizeof(struct blk_zone));
+	if (!sbi)
+		return;
 
-	return 0;
+	for (ztype = 0; ztype < ZONEFS_ZTYPE_MAX; ztype++) {
+		kvfree(sbi->s_zgroup[ztype].g_zones);
+		sbi->s_zgroup[ztype].g_zones = NULL;
+	}
 }
 
-static int zonefs_get_zone_info(struct zonefs_zone_data *zd)
+/*
+ * Create a zone group and populate it with zone files.
+ */
+static int zonefs_init_zgroups(struct super_block *sb)
 {
-	struct block_device *bdev = zd->sb->s_bdev;
+	struct zonefs_zone_data zd;
+	enum zonefs_ztype ztype;
 	int ret;
 
-	zd->zones = kvcalloc(bdev_nr_zones(bdev), sizeof(struct blk_zone),
-			     GFP_KERNEL);
-	if (!zd->zones)
-		return -ENOMEM;
-
-	/* Get zones information from the device */
-	ret = blkdev_report_zones(bdev, 0, BLK_ALL_ZONES,
-				  zonefs_get_zone_info_cb, zd);
-	if (ret < 0) {
-		zonefs_err(zd->sb, "Zone report failed %d\n", ret);
-		return ret;
-	}
+	/* First get the device zone information */
+	memset(&zd, 0, sizeof(struct zonefs_zone_data));
+	zd.sb = sb;
+	ret = zonefs_get_zone_info(&zd);
+	if (ret)
+		goto cleanup;
 
-	if (ret != bdev_nr_zones(bdev)) {
-		zonefs_err(zd->sb, "Invalid zone report (%d/%u zones)\n",
-			   ret, bdev_nr_zones(bdev));
-		return -EIO;
+	/* Allocate and initialize the zone groups */
+	for (ztype = 0; ztype < ZONEFS_ZTYPE_MAX; ztype++) {
+		ret = zonefs_init_zgroup(sb, &zd, ztype);
+		if (ret) {
+			zonefs_info(sb,
+				    "Zone group \"%s\" initialization failed\n",
+				    zonefs_zgroup_name(ztype));
+			break;
+		}
 	}
 
-	return 0;
-}
+cleanup:
+	zonefs_free_zone_info(&zd);
+	if (ret)
+		zonefs_free_zgroups(sb);
 
-static inline void zonefs_cleanup_zone_info(struct zonefs_zone_data *zd)
-{
-	kvfree(zd->zones);
+	return ret;
 }
 
 /*
@@ -1785,6 +1191,50 @@ free_page:
 	return ret;
 }
 
+static const struct super_operations zonefs_sops = {
+	.alloc_inode	= zonefs_alloc_inode,
+	.free_inode	= zonefs_free_inode,
+	.statfs		= zonefs_statfs,
+	.remount_fs	= zonefs_remount,
+	.show_options	= zonefs_show_options,
+};
+
+static int zonefs_get_zgroup_inodes(struct super_block *sb)
+{
+	struct zonefs_sb_info *sbi = ZONEFS_SB(sb);
+	struct inode *dir_inode;
+	enum zonefs_ztype ztype;
+
+	for (ztype = 0; ztype < ZONEFS_ZTYPE_MAX; ztype++) {
+		if (!sbi->s_zgroup[ztype].g_nr_zones)
+			continue;
+
+		dir_inode = zonefs_get_zgroup_inode(sb, ztype);
+		if (IS_ERR(dir_inode))
+			return PTR_ERR(dir_inode);
+
+		sbi->s_zgroup[ztype].g_inode = dir_inode;
+	}
+
+	return 0;
+}
+
+static void zonefs_release_zgroup_inodes(struct super_block *sb)
+{
+	struct zonefs_sb_info *sbi = ZONEFS_SB(sb);
+	enum zonefs_ztype ztype;
+
+	if (!sbi)
+		return;
+
+	for (ztype = 0; ztype < ZONEFS_ZTYPE_MAX; ztype++) {
+		if (sbi->s_zgroup[ztype].g_inode) {
+			iput(sbi->s_zgroup[ztype].g_inode);
+			sbi->s_zgroup[ztype].g_inode = NULL;
+		}
+	}
+}
+
 /*
  * Check that the device is zoned. If it is, get the list of zones and create
  * sub-directories and files according to the device zone configuration and
@@ -1792,10 +1242,9 @@ free_page:
  */
 static int zonefs_fill_super(struct super_block *sb, void *data, int silent)
 {
-	struct zonefs_zone_data zd;
 	struct zonefs_sb_info *sbi;
 	struct inode *inode;
-	enum zonefs_ztype t;
+	enum zonefs_ztype ztype;
 	int ret;
 
 	if (!bdev_is_zoned(sb->s_bdev)) {
@@ -1845,16 +1294,6 @@ static int zonefs_fill_super(struct super_block *sb, void *data, int silent)
 	if (ret)
 		return ret;
 
-	memset(&zd, 0, sizeof(struct zonefs_zone_data));
-	zd.sb = sb;
-	ret = zonefs_get_zone_info(&zd);
-	if (ret)
-		goto cleanup;
-
-	ret = zonefs_sysfs_register(sb);
-	if (ret)
-		goto cleanup;
-
 	zonefs_info(sb, "Mounting %u zones", bdev_nr_zones(sb->s_bdev));
 
 	if (!sbi->s_max_wro_seq_files &&
@@ -1865,7 +1304,12 @@ static int zonefs_fill_super(struct super_block *sb, void *data, int silent)
 		sbi->s_mount_opts &= ~ZONEFS_MNTOPT_EXPLICIT_OPEN;
 	}
 
-	/* Create root directory inode */
+	/* Initialize the zone groups */
+	ret = zonefs_init_zgroups(sb);
+	if (ret)
+		goto cleanup;
+
+	/* Create the root directory inode */
 	ret = -ENOMEM;
 	inode = new_inode(sb);
 	if (!inode)
@@ -1875,22 +1319,37 @@ static int zonefs_fill_super(struct super_block *sb, void *data, int silent)
 	inode->i_mode = S_IFDIR | 0555;
 	inode->i_ctime = inode->i_mtime = inode->i_atime = current_time(inode);
 	inode->i_op = &zonefs_dir_inode_operations;
-	inode->i_fop = &simple_dir_operations;
+	inode->i_fop = &zonefs_dir_operations;
+	inode->i_size = 2;
 	set_nlink(inode, 2);
+	for (ztype = 0; ztype < ZONEFS_ZTYPE_MAX; ztype++) {
+		if (sbi->s_zgroup[ztype].g_nr_zones) {
+			inc_nlink(inode);
+			inode->i_size++;
+		}
+	}
 
 	sb->s_root = d_make_root(inode);
 	if (!sb->s_root)
 		goto cleanup;
 
-	/* Create and populate files in zone groups directories */
-	for (t = 0; t < ZONEFS_ZTYPE_MAX; t++) {
-		ret = zonefs_create_zgroup(&zd, t);
-		if (ret)
-			break;
-	}
+	/*
+	 * Take a reference on the zone groups directory inodes
+	 * to keep them in the inode cache.
+	 */
+	ret = zonefs_get_zgroup_inodes(sb);
+	if (ret)
+		goto cleanup;
+
+	ret = zonefs_sysfs_register(sb);
+	if (ret)
+		goto cleanup;
+
+	return 0;
 
 cleanup:
-	zonefs_cleanup_zone_info(&zd);
+	zonefs_release_zgroup_inodes(sb);
+	zonefs_free_zgroups(sb);
 
 	return ret;
 }
@@ -1905,11 +1364,13 @@ static void zonefs_kill_super(struct super_block *sb)
 {
 	struct zonefs_sb_info *sbi = ZONEFS_SB(sb);
 
-	if (sb->s_root)
-		d_genocide(sb->s_root);
+	/* Release the reference on the zone group directory inodes */
+	zonefs_release_zgroup_inodes(sb);
 
-	zonefs_sysfs_unregister(sb);
 	kill_block_super(sb);
+
+	zonefs_sysfs_unregister(sb);
+	zonefs_free_zgroups(sb);
 	kfree(sbi);
 }
 
diff --git a/fs/zonefs/sysfs.c b/fs/zonefs/sysfs.c
index 9920689dc098d9..8ccb65c2b419fb 100644
--- a/fs/zonefs/sysfs.c
+++ b/fs/zonefs/sysfs.c
@@ -79,7 +79,7 @@ static const struct sysfs_ops zonefs_sysfs_attr_ops = {
 	.show	= zonefs_sysfs_attr_show,
 };
 
-static struct kobj_type zonefs_sb_ktype = {
+static const struct kobj_type zonefs_sb_ktype = {
 	.default_groups = zonefs_sysfs_groups,
 	.sysfs_ops	= &zonefs_sysfs_attr_ops,
 	.release	= zonefs_sysfs_sb_release,
diff --git a/fs/zonefs/trace.h b/fs/zonefs/trace.h
index 42edcfd393ed25..9969db3a9c7dc9 100644
--- a/fs/zonefs/trace.h
+++ b/fs/zonefs/trace.h
@@ -20,8 +20,9 @@
 #define show_dev(dev) MAJOR(dev), MINOR(dev)
 
 TRACE_EVENT(zonefs_zone_mgmt,
-	    TP_PROTO(struct inode *inode, enum req_op op),
-	    TP_ARGS(inode, op),
+	    TP_PROTO(struct super_block *sb, struct zonefs_zone *z,
+		     enum req_op op),
+	    TP_ARGS(sb, z, op),
 	    TP_STRUCT__entry(
 			     __field(dev_t, dev)
 			     __field(ino_t, ino)
@@ -30,12 +31,12 @@ TRACE_EVENT(zonefs_zone_mgmt,
 			     __field(sector_t, nr_sectors)
 	    ),
 	    TP_fast_assign(
-			   __entry->dev = inode->i_sb->s_dev;
-			   __entry->ino = inode->i_ino;
+			   __entry->dev = sb->s_dev;
+			   __entry->ino =
+				z->z_sector >> ZONEFS_SB(sb)->s_zone_sectors_shift;
 			   __entry->op = op;
-			   __entry->sector = ZONEFS_I(inode)->i_zsector;
-			   __entry->nr_sectors =
-				   ZONEFS_I(inode)->i_zone_size >> SECTOR_SHIFT;
+			   __entry->sector = z->z_sector;
+			   __entry->nr_sectors = z->z_size >> SECTOR_SHIFT;
 	    ),
 	    TP_printk("bdev=(%d,%d), ino=%lu op=%s, sector=%llu, nr_sectors=%llu",
 		      show_dev(__entry->dev), (unsigned long)__entry->ino,
@@ -58,9 +59,10 @@ TRACE_EVENT(zonefs_file_dio_append,
 	    TP_fast_assign(
 			   __entry->dev = inode->i_sb->s_dev;
 			   __entry->ino = inode->i_ino;
-			   __entry->sector = ZONEFS_I(inode)->i_zsector;
+			   __entry->sector = zonefs_inode_zone(inode)->z_sector;
 			   __entry->size = size;
-			   __entry->wpoffset = ZONEFS_I(inode)->i_wpoffset;
+			   __entry->wpoffset =
+				zonefs_inode_zone(inode)->z_wpoffset;
 			   __entry->ret = ret;
 	    ),
 	    TP_printk("bdev=(%d, %d), ino=%lu, sector=%llu, size=%zu, wpoffset=%llu, ret=%zu",
diff --git a/fs/zonefs/zonefs.h b/fs/zonefs/zonefs.h
index 1dbe78119ff163..8175652241b5c4 100644
--- a/fs/zonefs/zonefs.h
+++ b/fs/zonefs/zonefs.h
@@ -39,31 +39,53 @@ static inline enum zonefs_ztype zonefs_zone_type(struct blk_zone *zone)
 	return ZONEFS_ZTYPE_SEQ;
 }
 
-#define ZONEFS_ZONE_OPEN	(1U << 0)
-#define ZONEFS_ZONE_ACTIVE	(1U << 1)
-#define ZONEFS_ZONE_OFFLINE	(1U << 2)
-#define ZONEFS_ZONE_READONLY	(1U << 3)
+#define ZONEFS_ZONE_INIT_MODE	(1U << 0)
+#define ZONEFS_ZONE_OPEN	(1U << 1)
+#define ZONEFS_ZONE_ACTIVE	(1U << 2)
+#define ZONEFS_ZONE_OFFLINE	(1U << 3)
+#define ZONEFS_ZONE_READONLY	(1U << 4)
+#define ZONEFS_ZONE_CNV		(1U << 31)
 
 /*
- * In-memory inode data.
+ * In-memory per-file inode zone data.
  */
-struct zonefs_inode_info {
-	struct inode		i_vnode;
+struct zonefs_zone {
+	/* Zone state flags */
+	unsigned int		z_flags;
 
-	/* File zone type */
-	enum zonefs_ztype	i_ztype;
+	/* Zone start sector (512B unit) */
+	sector_t		z_sector;
 
-	/* File zone start sector (512B unit) */
-	sector_t		i_zsector;
+	/* Zone size (bytes) */
+	loff_t			z_size;
 
-	/* File zone write pointer position (sequential zones only) */
-	loff_t			i_wpoffset;
+	/* Zone capacity (file maximum size, bytes) */
+	loff_t			z_capacity;
 
-	/* File maximum size */
-	loff_t			i_max_size;
+	/* Write pointer offset in the zone (sequential zones only, bytes) */
+	loff_t			z_wpoffset;
+
+	/* Saved inode uid, gid and access rights */
+	umode_t			z_mode;
+	kuid_t			z_uid;
+	kgid_t			z_gid;
+};
+
+/*
+ * In memory zone group information: all zones of a group are exposed
+ * as files, one file per zone.
+ */
+struct zonefs_zone_group {
+	struct inode		*g_inode;
+	unsigned int		g_nr_zones;
+	struct zonefs_zone	*g_zones;
+};
 
-	/* File zone size */
-	loff_t			i_zone_size;
+/*
+ * In-memory inode data.
+ */
+struct zonefs_inode_info {
+	struct inode		i_vnode;
 
 	/*
 	 * To serialise fully against both syscall and mmap based IO and
@@ -82,7 +104,6 @@ struct zonefs_inode_info {
 
 	/* guarded by i_truncate_mutex */
 	unsigned int		i_wr_refcnt;
-	unsigned int		i_flags;
 };
 
 static inline struct zonefs_inode_info *ZONEFS_I(struct inode *inode)
@@ -90,6 +111,31 @@ static inline struct zonefs_inode_info *ZONEFS_I(struct inode *inode)
 	return container_of(inode, struct zonefs_inode_info, i_vnode);
 }
 
+static inline bool zonefs_zone_is_cnv(struct zonefs_zone *z)
+{
+	return z->z_flags & ZONEFS_ZONE_CNV;
+}
+
+static inline bool zonefs_zone_is_seq(struct zonefs_zone *z)
+{
+	return !zonefs_zone_is_cnv(z);
+}
+
+static inline struct zonefs_zone *zonefs_inode_zone(struct inode *inode)
+{
+	return inode->i_private;
+}
+
+static inline bool zonefs_inode_is_cnv(struct inode *inode)
+{
+	return zonefs_zone_is_cnv(zonefs_inode_zone(inode));
+}
+
+static inline bool zonefs_inode_is_seq(struct inode *inode)
+{
+	return zonefs_zone_is_seq(zonefs_inode_zone(inode));
+}
+
 /*
  * On-disk super block (block 0).
  */
@@ -181,7 +227,7 @@ struct zonefs_sb_info {
 	uuid_t			s_uuid;
 	unsigned int		s_zone_sectors_shift;
 
-	unsigned int		s_nr_files[ZONEFS_ZTYPE_MAX];
+	struct zonefs_zone_group s_zgroup[ZONEFS_ZTYPE_MAX];
 
 	loff_t			s_blocks;
 	loff_t			s_used_blocks;
@@ -209,6 +255,32 @@ static inline struct zonefs_sb_info *ZONEFS_SB(struct super_block *sb)
 #define zonefs_warn(sb, format, args...)	\
 	pr_warn("zonefs (%s) WARNING: " format, sb->s_id, ## args)
 
+/* In super.c */
+void zonefs_inode_account_active(struct inode *inode);
+int zonefs_inode_zone_mgmt(struct inode *inode, enum req_op op);
+void zonefs_i_size_write(struct inode *inode, loff_t isize);
+void zonefs_update_stats(struct inode *inode, loff_t new_isize);
+void __zonefs_io_error(struct inode *inode, bool write);
+
+static inline void zonefs_io_error(struct inode *inode, bool write)
+{
+	struct zonefs_inode_info *zi = ZONEFS_I(inode);
+
+	mutex_lock(&zi->i_truncate_mutex);
+	__zonefs_io_error(inode, write);
+	mutex_unlock(&zi->i_truncate_mutex);
+}
+
+/* In super.c */
+extern const struct inode_operations zonefs_dir_inode_operations;
+extern const struct file_operations zonefs_dir_operations;
+
+/* In file.c */
+extern const struct address_space_operations zonefs_file_aops;
+extern const struct file_operations zonefs_file_operations;
+int zonefs_file_truncate(struct inode *inode, loff_t isize);
+
+/* In sysfs.c */
 int zonefs_sysfs_register(struct super_block *sb);
 void zonefs_sysfs_unregister(struct super_block *sb);
 int zonefs_sysfs_init(void);