xref: /openbmc/linux/fs/zonefs/super.c (revision 46a9c526eef7fb68a00321e2a9591ce5276ae92b)

// SPDX-License-Identifier: GPL-2.0
/*
 * Simple file system for zoned block devices exposing zones as files.
 *
 * Copyright (C) 2019 Western Digital Corporation or its affiliates.
 */
#include <linux/module.h>
#include <linux/pagemap.h>
#include <linux/magic.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/crc32.h>
#include <linux/task_io_accounting_ops.h>

#include "zonefs.h"

#define CREATE_TRACE_POINTS
#include "trace.h"

/*
 * Manage the active zone count. Called with zi->i_truncate_mutex held.
 */
void zonefs_account_active(struct inode *inode)
{
	struct zonefs_sb_info *sbi = ZONEFS_SB(inode->i_sb);
	struct zonefs_inode_info *zi = ZONEFS_I(inode);

	lockdep_assert_held(&zi->i_truncate_mutex);

	if (zi->i_ztype != ZONEFS_ZTYPE_SEQ)
		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))
		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;
			atomic_inc(&sbi->s_active_seq_files);
		}
		return;
	}

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;
		atomic_dec(&sbi->s_active_seq_files);
	}
}

int zonefs_zone_mgmt(struct inode *inode, enum req_op op)
{
	struct zonefs_inode_info *zi = ZONEFS_I(inode);
	int ret;

	lockdep_assert_held(&zi->i_truncate_mutex);

	/*
	 * With ZNS drives, closing an explicitly open zone that has not been
	 * written will change the zone state to "closed", that is, the zone
	 * will remain active. Since this can then cause failure of explicit
	 * open operation on other zones if the drive active zone resources
	 * are exceeded, make sure that the zone does not remain active by
	 * resetting it.
	 */
	if (op == REQ_OP_ZONE_CLOSE && !zi->i_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);
	if (ret) {
		zonefs_err(inode->i_sb,
			   "Zone management operation %s at %llu failed %d\n",
			   blk_op_str(op), zi->i_zsector, ret);
		return ret;
	}

	return 0;
}

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);
	}
}

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);
	loff_t old_isize = i_size_read(inode);
	loff_t nr_blocks;

	if (new_isize == old_isize)
		return;

	spin_lock(&sbi->s_lock);

	/*
	 * This may be called for an update after an IO error.
	 * So beware of the values seen.
	 */
	if (new_isize < old_isize) {
		nr_blocks = (old_isize - new_isize) >> sb->s_blocksize_bits;
		if (sbi->s_used_blocks > nr_blocks)
			sbi->s_used_blocks -= nr_blocks;
		else
			sbi->s_used_blocks = 0;
	} else {
		sbi->s_used_blocks +=
			(new_isize - old_isize) >> sb->s_blocksize_bits;
		if (sbi->s_used_blocks > sbi->s_blocks)
			sbi->s_used_blocks = sbi->s_blocks;
	}

	spin_unlock(&sbi->s_lock);
}

/*
 * 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.
 */
static loff_t zonefs_check_zone_condition(struct inode *inode,
					  struct blk_zone *zone)
{
	struct zonefs_inode_info *zi = ZONEFS_I(inode);

	switch (zone->cond) {
	case BLK_ZONE_COND_OFFLINE:
		zonefs_warn(inode->i_sb, "inode %lu: offline zone\n",
			    inode->i_ino);
		zi->i_flags |= ZONEFS_ZONE_OFFLINE;
		return 0;
	case BLK_ZONE_COND_READONLY:
		/*
		 * 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.
		 */
		zonefs_warn(inode->i_sb, "inode %lu: read-only zone\n",
			    inode->i_ino);
		zi->i_flags |= ZONEFS_ZONE_READONLY;
		if (zi->i_ztype == ZONEFS_ZTYPE_CNV)
			return zi->i_max_size;
		return zi->i_wpoffset;
	case BLK_ZONE_COND_FULL:
		/* The write pointer of full zones is invalid. */
		return zi->i_max_size;
	default:
		if (zi->i_ztype == ZONEFS_ZTYPE_CNV)
			return zi->i_max_size;
		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_inode_info *zi = ZONEFS_I(inode);

	if (zi->i_flags & ZONEFS_ZONE_OFFLINE) {
		/* Offline zones cannot be read nor written */
		inode->i_flags |= S_IMMUTABLE;
		inode->i_mode &= ~0777;
	} else if (zi->i_flags & ZONEFS_ZONE_READONLY) {
		/* Readonly zones cannot be written */
		inode->i_flags |= S_IMMUTABLE;
		if (zi->i_flags & ZONEFS_ZONE_INIT_MODE)
			inode->i_mode &= ~0777;
		else
			inode->i_mode &= ~0222;
	}

	zi->i_flags &= ~ZONEFS_ZONE_INIT_MODE;
}

struct zonefs_ioerr_data {
	struct inode	*inode;
	bool		write;
};

static int zonefs_io_error_cb(struct blk_zone *zone, unsigned int idx,
			      void *data)
{
	struct zonefs_ioerr_data *err = data;
	struct inode *inode = err->inode;
	struct zonefs_inode_info *zi = ZONEFS_I(inode);
	struct super_block *sb = inode->i_sb;
	struct zonefs_sb_info *sbi = ZONEFS_SB(sb);
	loff_t isize, data_size;

	/*
	 * Check the zone condition: if the zone is not "bad" (offline or
	 * read-only), read errors are simply signaled to the IO issuer as long
	 * 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);
	isize = i_size_read(inode);
	if (!(zi->i_flags & (ZONEFS_ZONE_READONLY | ZONEFS_ZONE_OFFLINE)) &&
	    !err->write && isize == data_size)
		return 0;

	/*
	 * At this point, we detected either a bad zone or an inconsistency
	 * between the inode size and the amount of data written in the zone.
	 * For the latter case, the cause may be a write IO error or an external
	 * action on the device. Two error patterns exist:
	 * 1) The inode size is lower than the amount of data in the zone:
	 *    a write operation partially failed and data was writen at the end
	 *    of the file. This can happen in the case of a large direct IO
	 *    needing several BIOs and/or write requests to be processed.
	 * 2) The inode size is larger than the amount of data in the zone:
	 *    this can happen with a deferred write error with the use of the
	 *    device side write cache after getting successful write IO
	 *    completions. Other possibilities are (a) an external corruption,
	 *    e.g. an application reset the zone directly, or (b) the device
	 *    has a serious problem (e.g. firmware bug).
	 *
	 * 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",
			    inode->i_ino, isize, data_size);

	/*
	 * First handle bad zones signaled by hardware. The mount options
	 * errors=zone-ro and errors=zone-offline result in changing the
	 * zone condition to read-only and offline respectively, as if the
	 * condition was signaled by the hardware.
	 */
	if ((zi->i_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 (!(zi->i_flags & ZONEFS_ZONE_OFFLINE))
			zi->i_flags |= ZONEFS_ZONE_OFFLINE;
		zonefs_inode_update_mode(inode);
		data_size = 0;
	} else if ((zi->i_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 (!(zi->i_flags & ZONEFS_ZONE_READONLY))
			zi->i_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 */
		data_size = isize;
	}

	/*
	 * If the filesystem is mounted with the explicit-open mount option, we
	 * need to clear the ZONEFS_ZONE_OPEN flag if the zone transitioned to
	 * the read-only or offline condition, to avoid attempting an explicit
	 * close of the zone when the inode file is closed.
	 */
	if ((sbi->s_mount_opts & ZONEFS_MNTOPT_EXPLICIT_OPEN) &&
	    (zi->i_flags & (ZONEFS_ZONE_READONLY | ZONEFS_ZONE_OFFLINE)))
		zi->i_flags &= ~ZONEFS_ZONE_OPEN;

	/*
	 * If error=remount-ro was specified, any error result in remounting
	 * the volume as read-only.
	 */
	if ((sbi->s_mount_opts & ZONEFS_MNTOPT_ERRORS_RO) && !sb_rdonly(sb)) {
		zonefs_warn(sb, "remounting filesystem read-only\n");
		sb->s_flags |= SB_RDONLY;
	}

	/*
	 * Update block usage stats and the inode size  to prevent access to
	 * invalid data.
	 */
	zonefs_update_stats(inode, data_size);
	zonefs_i_size_write(inode, data_size);
	zi->i_wpoffset = data_size;
	zonefs_account_active(inode);

	return 0;
}

/*
 * When an file IO error occurs, check the file zone to see if there is a change
 * in the zone condition (e.g. offline or read-only). For a failed write to a
 * sequential zone, the zone write pointer position must also be checked to
 * 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).
 */
void __zonefs_io_error(struct inode *inode, bool write)
{
	struct zonefs_inode_info *zi = ZONEFS_I(inode);
	struct super_block *sb = inode->i_sb;
	struct zonefs_sb_info *sbi = ZONEFS_SB(sb);
	unsigned int noio_flag;
	unsigned int nr_zones = 1;
	struct zonefs_ioerr_data err = {
		.inode = inode,
		.write = write,
	};
	int ret;

	/*
	 * The only files that have more than one zone are conventional zone
	 * 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 >>
			(sbi->s_zone_sectors_shift + SECTOR_SHIFT);

	/*
	 * Memory allocations in blkdev_report_zones() can trigger a memory
	 * reclaim which may in turn cause a recursion into zonefs as well as
	 * struct request allocations for the same device. The former case may
	 * end up in a deadlock on the inode truncate mutex, while the latter
	 * may prevent IO forward progress. Executing the report zones under
	 * the GFP_NOIO context avoids both problems.
	 */
	noio_flag = memalloc_noio_save();
	ret = blkdev_report_zones(sb->s_bdev, zi->i_zsector, nr_zones,
				  zonefs_io_error_cb, &err);
	if (ret != nr_zones)
		zonefs_err(sb, "Get inode %lu zone information failed %d\n",
			   inode->i_ino, ret);
	memalloc_noio_restore(noio_flag);
}

static struct kmem_cache *zonefs_inode_cachep;

static struct inode *zonefs_alloc_inode(struct super_block *sb)
{
	struct zonefs_inode_info *zi;

	zi = alloc_inode_sb(sb, zonefs_inode_cachep, GFP_KERNEL);
	if (!zi)
		return NULL;

	inode_init_once(&zi->i_vnode);
	mutex_init(&zi->i_truncate_mutex);
	zi->i_wpoffset = 0;
	zi->i_wr_refcnt = 0;
	zi->i_flags = 0;

	return &zi->i_vnode;
}

static void zonefs_free_inode(struct inode *inode)
{
	kmem_cache_free(zonefs_inode_cachep, ZONEFS_I(inode));
}

/*
 * File system stat.
 */
static int zonefs_statfs(struct dentry *dentry, struct kstatfs *buf)
{
	struct super_block *sb = dentry->d_sb;
	struct zonefs_sb_info *sbi = ZONEFS_SB(sb);
	enum zonefs_ztype t;

	buf->f_type = ZONEFS_MAGIC;
	buf->f_bsize = sb->s_blocksize;
	buf->f_namelen = ZONEFS_NAME_MAX;

	spin_lock(&sbi->s_lock);

	buf->f_blocks = sbi->s_blocks;
	if (WARN_ON(sbi->s_used_blocks > sbi->s_blocks))
		buf->f_bfree = 0;
	else
		buf->f_bfree = buf->f_blocks - sbi->s_used_blocks;
	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;
	}
	buf->f_ffree = 0;

	spin_unlock(&sbi->s_lock);

	buf->f_fsid = uuid_to_fsid(sbi->s_uuid.b);

	return 0;
}

enum {
	Opt_errors_ro, Opt_errors_zro, Opt_errors_zol, Opt_errors_repair,
	Opt_explicit_open, Opt_err,
};

static const match_table_t tokens = {
	{ Opt_errors_ro,	"errors=remount-ro"},
	{ Opt_errors_zro,	"errors=zone-ro"},
	{ Opt_errors_zol,	"errors=zone-offline"},
	{ Opt_errors_repair,	"errors=repair"},
	{ Opt_explicit_open,	"explicit-open" },
	{ Opt_err,		NULL}
};

static int zonefs_parse_options(struct super_block *sb, char *options)
{
	struct zonefs_sb_info *sbi = ZONEFS_SB(sb);
	substring_t args[MAX_OPT_ARGS];
	char *p;

	if (!options)
		return 0;

	while ((p = strsep(&options, ",")) != NULL) {
		int token;

		if (!*p)
			continue;

		token = match_token(p, tokens, args);
		switch (token) {
		case Opt_errors_ro:
			sbi->s_mount_opts &= ~ZONEFS_MNTOPT_ERRORS_MASK;
			sbi->s_mount_opts |= ZONEFS_MNTOPT_ERRORS_RO;
			break;
		case Opt_errors_zro:
			sbi->s_mount_opts &= ~ZONEFS_MNTOPT_ERRORS_MASK;
			sbi->s_mount_opts |= ZONEFS_MNTOPT_ERRORS_ZRO;
			break;
		case Opt_errors_zol:
			sbi->s_mount_opts &= ~ZONEFS_MNTOPT_ERRORS_MASK;
			sbi->s_mount_opts |= ZONEFS_MNTOPT_ERRORS_ZOL;
			break;
		case Opt_errors_repair:
			sbi->s_mount_opts &= ~ZONEFS_MNTOPT_ERRORS_MASK;
			sbi->s_mount_opts |= ZONEFS_MNTOPT_ERRORS_REPAIR;
			break;
		case Opt_explicit_open:
			sbi->s_mount_opts |= ZONEFS_MNTOPT_EXPLICIT_OPEN;
			break;
		default:
			return -EINVAL;
		}
	}

	return 0;
}

static int zonefs_show_options(struct seq_file *seq, struct dentry *root)
{
	struct zonefs_sb_info *sbi = ZONEFS_SB(root->d_sb);

	if (sbi->s_mount_opts & ZONEFS_MNTOPT_ERRORS_RO)
		seq_puts(seq, ",errors=remount-ro");
	if (sbi->s_mount_opts & ZONEFS_MNTOPT_ERRORS_ZRO)
		seq_puts(seq, ",errors=zone-ro");
	if (sbi->s_mount_opts & ZONEFS_MNTOPT_ERRORS_ZOL)
		seq_puts(seq, ",errors=zone-offline");
	if (sbi->s_mount_opts & ZONEFS_MNTOPT_ERRORS_REPAIR)
		seq_puts(seq, ",errors=repair");

	return 0;
}

static int zonefs_remount(struct super_block *sb, int *flags, char *data)
{
	sync_filesystem(sb);

	return zonefs_parse_options(sb, data);
}

static int zonefs_inode_setattr(struct user_namespace *mnt_userns,
				struct dentry *dentry, struct iattr *iattr)
{
	struct inode *inode = d_inode(dentry);
	int ret;

	if (unlikely(IS_IMMUTABLE(inode)))
		return -EPERM;

	ret = setattr_prepare(&init_user_ns, 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(mnt_userns, 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(&init_user_ns, inode, iattr);

	return 0;
}

static const struct inode_operations zonefs_dir_inode_operations = {
	.lookup		= simple_lookup,
	.setattr	= zonefs_inode_setattr,
};

static void zonefs_init_dir_inode(struct inode *parent, struct inode *inode,
				  enum zonefs_ztype type)
{
	struct super_block *sb = parent->i_sb;

	inode->i_ino = bdev_nr_zones(sb->s_bdev) + type + 1;
	inode_init_owner(&init_user_ns, 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);
}

static const struct inode_operations zonefs_file_inode_operations = {
	.setattr	= zonefs_inode_setattr,
};

static int zonefs_init_file_inode(struct inode *inode, struct blk_zone *zone,
				  enum zonefs_ztype type)
{
	struct super_block *sb = inode->i_sb;
	struct zonefs_sb_info *sbi = ZONEFS_SB(sb);
	struct zonefs_inode_info *zi = ZONEFS_I(inode);
	int ret = 0;

	inode->i_ino = zone->start >> sbi->s_zone_sectors_shift;
	inode->i_mode = S_IFREG | sbi->s_perm;

	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;
	}

	zi->i_max_size = min_t(loff_t, MAX_LFS_FILESIZE,
			       zone->capacity << SECTOR_SHIFT);
	zi->i_wpoffset = zonefs_check_zone_condition(inode, zone);

	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_op = &zonefs_file_inode_operations;
	inode->i_fop = &zonefs_file_operations;
	inode->i_mapping->a_ops = &zonefs_file_aops;

	/* Update the inode access rights depending on the zone condition */
	zi->i_flags |= ZONEFS_ZONE_INIT_MODE;
	zonefs_inode_update_mode(inode);

	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;

	mutex_lock(&zi->i_truncate_mutex);

	/*
	 * 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 (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;
	}

	zonefs_account_active(inode);

unlock:
	mutex_unlock(&zi->i_truncate_mutex);

	return ret;
}

static struct dentry *zonefs_create_inode(struct dentry *parent,
					const char *name, struct blk_zone *zone,
					enum zonefs_ztype type)
{
	struct inode *dir = d_inode(parent);
	struct dentry *dentry;
	struct inode *inode;
	int ret = -ENOMEM;

	dentry = d_alloc_name(parent, name);
	if (!dentry)
		return ERR_PTR(ret);

	inode = new_inode(parent->d_sb);
	if (!inode)
		goto dput;

	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);
	}

	d_add(dentry, inode);
	dir->i_size++;

	return dentry;

dput:
	dput(dentry);

	return ERR_PTR(ret);
}

struct zonefs_zone_data {
	struct super_block	*sb;
	unsigned int		nr_zones[ZONEFS_ZTYPE_MAX];
	struct blk_zone		*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)
{
	struct super_block *sb = zd->sb;
	struct zonefs_sb_info *sbi = ZONEFS_SB(sb);
	struct blk_zone *zone, *next, *end;
	const char *zgroup_name;
	char *file_name;
	struct dentry *dir, *dent;
	unsigned int n = 0;
	int ret;

	/* If the group is empty, there is nothing to do */
	if (!zd->nr_zones[type])
		return 0;

	file_name = kmalloc(ZONEFS_NAME_MAX, GFP_KERNEL);
	if (!file_name)
		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.
	 */
	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)
			continue;

		/*
		 * For conventional zones, contiguous zones can be aggregated
		 * together to form larger files. Note that this overwrites the
		 * length of the first zone of the set of contiguous zones
		 * aggregated together. If one offline or read-only zone is
		 * found, assume that all zones aggregated have the same
		 * condition.
		 */
		if (type == ZONEFS_ZTYPE_CNV &&
		    (sbi->s_features & ZONEFS_F_AGGRCNV)) {
			for (; next < end; next++) {
				if (zonefs_zone_type(next) != type)
					break;
				zone->len += next->len;
				zone->capacity += next->capacity;
				if (next->cond == BLK_ZONE_COND_READONLY &&
				    zone->cond != BLK_ZONE_COND_OFFLINE)
					zone->cond = BLK_ZONE_COND_READONLY;
				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;
			}
		}

		/*
		 * Use the file number within its group as file name.
		 */
		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;
		}

		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;

free:
	kfree(file_name);

	return ret;
}

static int zonefs_get_zone_info_cb(struct blk_zone *zone, unsigned int idx,
				   void *data)
{
	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;
	}

	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_cleanup_zone_info(struct zonefs_zone_data *zd)
{
	kvfree(zd->zones);
}

/*
 * Read super block information from the device.
 */
static int zonefs_read_super(struct super_block *sb)
{
	struct zonefs_sb_info *sbi = ZONEFS_SB(sb);
	struct zonefs_super *super;
	u32 crc, stored_crc;
	struct page *page;
	struct bio_vec bio_vec;
	struct bio bio;
	int ret;

	page = alloc_page(GFP_KERNEL);
	if (!page)
		return -ENOMEM;

	bio_init(&bio, sb->s_bdev, &bio_vec, 1, REQ_OP_READ);
	bio.bi_iter.bi_sector = 0;
	bio_add_page(&bio, page, PAGE_SIZE, 0);

	ret = submit_bio_wait(&bio);
	if (ret)
		goto free_page;

	super = page_address(page);

	ret = -EINVAL;
	if (le32_to_cpu(super->s_magic) != ZONEFS_MAGIC)
		goto free_page;

	stored_crc = le32_to_cpu(super->s_crc);
	super->s_crc = 0;
	crc = crc32(~0U, (unsigned char *)super, sizeof(struct zonefs_super));
	if (crc != stored_crc) {
		zonefs_err(sb, "Invalid checksum (Expected 0x%08x, got 0x%08x)",
			   crc, stored_crc);
		goto free_page;
	}

	sbi->s_features = le64_to_cpu(super->s_features);
	if (sbi->s_features & ~ZONEFS_F_DEFINED_FEATURES) {
		zonefs_err(sb, "Unknown features set 0x%llx\n",
			   sbi->s_features);
		goto free_page;
	}

	if (sbi->s_features & ZONEFS_F_UID) {
		sbi->s_uid = make_kuid(current_user_ns(),
				       le32_to_cpu(super->s_uid));
		if (!uid_valid(sbi->s_uid)) {
			zonefs_err(sb, "Invalid UID feature\n");
			goto free_page;
		}
	}

	if (sbi->s_features & ZONEFS_F_GID) {
		sbi->s_gid = make_kgid(current_user_ns(),
				       le32_to_cpu(super->s_gid));
		if (!gid_valid(sbi->s_gid)) {
			zonefs_err(sb, "Invalid GID feature\n");
			goto free_page;
		}
	}

	if (sbi->s_features & ZONEFS_F_PERM)
		sbi->s_perm = le32_to_cpu(super->s_perm);

	if (memchr_inv(super->s_reserved, 0, sizeof(super->s_reserved))) {
		zonefs_err(sb, "Reserved area is being used\n");
		goto free_page;
	}

	import_uuid(&sbi->s_uuid, super->s_uuid);
	ret = 0;

free_page:
	__free_page(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,
};

/*
 * 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
 * format options.
 */
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;
	int ret;

	if (!bdev_is_zoned(sb->s_bdev)) {
		zonefs_err(sb, "Not a zoned block device\n");
		return -EINVAL;
	}

	/*
	 * Initialize super block information: the maximum file size is updated
	 * when the zone files are created so that the format option
	 * ZONEFS_F_AGGRCNV which increases the maximum file size of a file
	 * beyond the zone size is taken into account.
	 */
	sbi = kzalloc(sizeof(*sbi), GFP_KERNEL);
	if (!sbi)
		return -ENOMEM;

	spin_lock_init(&sbi->s_lock);
	sb->s_fs_info = sbi;
	sb->s_magic = ZONEFS_MAGIC;
	sb->s_maxbytes = 0;
	sb->s_op = &zonefs_sops;
	sb->s_time_gran	= 1;

	/*
	 * The block size is set to the device zone write granularity to ensure
	 * that write operations are always aligned according to the device
	 * interface constraints.
	 */
	sb_set_blocksize(sb, bdev_zone_write_granularity(sb->s_bdev));
	sbi->s_zone_sectors_shift = ilog2(bdev_zone_sectors(sb->s_bdev));
	sbi->s_uid = GLOBAL_ROOT_UID;
	sbi->s_gid = GLOBAL_ROOT_GID;
	sbi->s_perm = 0640;
	sbi->s_mount_opts = ZONEFS_MNTOPT_ERRORS_RO;

	atomic_set(&sbi->s_wro_seq_files, 0);
	sbi->s_max_wro_seq_files = bdev_max_open_zones(sb->s_bdev);
	atomic_set(&sbi->s_active_seq_files, 0);
	sbi->s_max_active_seq_files = bdev_max_active_zones(sb->s_bdev);

	ret = zonefs_read_super(sb);
	if (ret)
		return ret;

	ret = zonefs_parse_options(sb, data);
	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 &&
	    !sbi->s_max_active_seq_files &&
	    sbi->s_mount_opts & ZONEFS_MNTOPT_EXPLICIT_OPEN) {
		zonefs_info(sb,
			"No open and active zone limits. Ignoring explicit_open mount option\n");
		sbi->s_mount_opts &= ~ZONEFS_MNTOPT_EXPLICIT_OPEN;
	}

	/* Create root directory inode */
	ret = -ENOMEM;
	inode = new_inode(sb);
	if (!inode)
		goto cleanup;

	inode->i_ino = bdev_nr_zones(sb->s_bdev);
	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;
	set_nlink(inode, 2);

	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;
	}

cleanup:
	zonefs_cleanup_zone_info(&zd);

	return ret;
}

static struct dentry *zonefs_mount(struct file_system_type *fs_type,
				   int flags, const char *dev_name, void *data)
{
	return mount_bdev(fs_type, flags, dev_name, data, zonefs_fill_super);
}

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);

	zonefs_sysfs_unregister(sb);
	kill_block_super(sb);
	kfree(sbi);
}

/*
 * File system definition and registration.
 */
static struct file_system_type zonefs_type = {
	.owner		= THIS_MODULE,
	.name		= "zonefs",
	.mount		= zonefs_mount,
	.kill_sb	= zonefs_kill_super,
	.fs_flags	= FS_REQUIRES_DEV,
};

static int __init zonefs_init_inodecache(void)
{
	zonefs_inode_cachep = kmem_cache_create("zonefs_inode_cache",
			sizeof(struct zonefs_inode_info), 0,
			(SLAB_RECLAIM_ACCOUNT | SLAB_MEM_SPREAD | SLAB_ACCOUNT),
			NULL);
	if (zonefs_inode_cachep == NULL)
		return -ENOMEM;
	return 0;
}

static void zonefs_destroy_inodecache(void)
{
	/*
	 * Make sure all delayed rcu free inodes are flushed before we
	 * destroy the inode cache.
	 */
	rcu_barrier();
	kmem_cache_destroy(zonefs_inode_cachep);
}

static int __init zonefs_init(void)
{
	int ret;

	BUILD_BUG_ON(sizeof(struct zonefs_super) != ZONEFS_SUPER_SIZE);

	ret = zonefs_init_inodecache();
	if (ret)
		return ret;

	ret = zonefs_sysfs_init();
	if (ret)
		goto destroy_inodecache;

	ret = register_filesystem(&zonefs_type);
	if (ret)
		goto sysfs_exit;

	return 0;

sysfs_exit:
	zonefs_sysfs_exit();
destroy_inodecache:
	zonefs_destroy_inodecache();

	return ret;
}

static void __exit zonefs_exit(void)
{
	unregister_filesystem(&zonefs_type);
	zonefs_sysfs_exit();
	zonefs_destroy_inodecache();
}

MODULE_AUTHOR("Damien Le Moal");
MODULE_DESCRIPTION("Zone file system for zoned block devices");
MODULE_LICENSE("GPL");
MODULE_ALIAS_FS("zonefs");
module_init(zonefs_init);
module_exit(zonefs_exit);