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);
zi->i_flags &= ~ZONEFS_ZONE_OPEN;
}
-static int zonefs_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
- unsigned int flags, struct iomap *iomap,
- struct iomap *srcmap)
+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 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 = (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;
+}
+
+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 super_block *sb = inode->i_sb;
loff_t isize;
- /* All I/Os should always be within the file maximum size */
+ /* All write I/Os should always be within the file maximum size */
if (WARN_ON_ONCE(offset + length > zi->i_max_size))
return -EIO;
* operation.
*/
if (WARN_ON_ONCE(zi->i_ztype == ZONEFS_ZTYPE_SEQ &&
- (flags & IOMAP_WRITE) && !(flags & IOMAP_DIRECT)))
+ !(flags & IOMAP_DIRECT)))
return -EIO;
/*
* 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 = (zi->i_zsector << SECTOR_SHIFT) + iomap->offset;
isize = i_size_read(inode);
- if (offset >= isize)
+ if (iomap->offset >= isize) {
iomap->type = IOMAP_UNWRITTEN;
- else
+ iomap->length = zi->i_max_size - iomap->offset;
+ } else {
iomap->type = IOMAP_MAPPED;
- if (flags & IOMAP_WRITE)
- length = zi->i_max_size - offset;
- else
- length = min(length, isize - offset);
+ iomap->length = isize - iomap->offset;
+ }
mutex_unlock(&zi->i_truncate_mutex);
- iomap->offset = ALIGN_DOWN(offset, sb->s_blocksize);
- iomap->length = ALIGN(offset + length, sb->s_blocksize) - iomap->offset;
- iomap->bdev = inode->i_sb->s_bdev;
- iomap->addr = (zi->i_zsector << SECTOR_SHIFT) + iomap->offset;
-
trace_zonefs_iomap_begin(inode, iomap);
return 0;
}
-static const struct iomap_ops zonefs_iomap_ops = {
- .iomap_begin = zonefs_iomap_begin,
+static const struct iomap_ops zonefs_write_iomap_ops = {
+ .iomap_begin = zonefs_write_iomap_begin,
};
static int zonefs_readpage(struct file *unused, struct page *page)
{
- return iomap_readpage(page, &zonefs_iomap_ops);
+ return iomap_readpage(page, &zonefs_read_iomap_ops);
}
static void zonefs_readahead(struct readahead_control *rac)
{
- iomap_readahead(rac, &zonefs_iomap_ops);
+ 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_map_blocks(struct iomap_writepage_ctx *wpc,
- struct inode *inode, loff_t offset)
+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);
offset < wpc->iomap.offset + wpc->iomap.length)
return 0;
- return zonefs_iomap_begin(inode, offset, zi->i_max_size - offset,
- IOMAP_WRITE, &wpc->iomap, NULL);
+ 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_map_blocks,
+ .map_blocks = zonefs_write_map_blocks,
};
static int zonefs_writepage(struct page *page, struct writeback_control *wbc)
return -EINVAL;
}
- return iomap_swapfile_activate(sis, swap_file, span, &zonefs_iomap_ops);
+ return iomap_swapfile_activate(sis, swap_file, span,
+ &zonefs_read_iomap_ops);
}
static const struct address_space_operations zonefs_file_aops = {
/* Serialize against truncates */
filemap_invalidate_lock_shared(inode->i_mapping);
- ret = iomap_page_mkwrite(vmf, &zonefs_iomap_ops);
+ ret = iomap_page_mkwrite(vmf, &zonefs_write_iomap_ops);
filemap_invalidate_unlock_shared(inode->i_mapping);
sb_end_pagefault(inode->i_sb);
if (append)
ret = zonefs_file_dio_append(iocb, from);
else
- ret = iomap_dio_rw(iocb, from, &zonefs_iomap_ops,
- &zonefs_write_dio_ops, 0);
+ ret = iomap_dio_rw(iocb, from, &zonefs_write_iomap_ops,
+ &zonefs_write_dio_ops, 0, 0);
if (zi->i_ztype == ZONEFS_ZTYPE_SEQ &&
(ret > 0 || ret == -EIOCBQUEUED)) {
if (ret > 0)
if (ret <= 0)
goto inode_unlock;
- ret = iomap_file_buffered_write(iocb, from, &zonefs_iomap_ops);
+ ret = iomap_file_buffered_write(iocb, from, &zonefs_write_iomap_ops);
if (ret > 0)
iocb->ki_pos += ret;
else if (ret == -EIO)
goto inode_unlock;
}
file_accessed(iocb->ki_filp);
- ret = iomap_dio_rw(iocb, to, &zonefs_iomap_ops,
- &zonefs_read_dio_ops, 0);
+ ret = iomap_dio_rw(iocb, to, &zonefs_read_iomap_ops,
+ &zonefs_read_dio_ops, 0, 0);
} else {
ret = generic_file_read_iter(iocb, to);
if (ret == -EIO)
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;
}
inc_nlink(parent);
}
-static void zonefs_init_file_inode(struct inode *inode, struct blk_zone *zone,
- enum zonefs_ztype type)
+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;
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;
+
+ /*
+ * 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)) {
+ mutex_lock(&zi->i_truncate_mutex);
+ ret = zonefs_zone_mgmt(inode, REQ_OP_ZONE_CLOSE);
+ mutex_unlock(&zi->i_truncate_mutex);
+ }
+
+ return ret;
}
static struct dentry *zonefs_create_inode(struct dentry *parent,
struct inode *dir = d_inode(parent);
struct dentry *dentry;
struct inode *inode;
+ int ret;
dentry = d_alloc_name(parent, name);
if (!dentry)
goto dput;
inode->i_ctime = inode->i_mtime = inode->i_atime = dir->i_ctime;
- if (zone)
- zonefs_init_file_inode(inode, zone, type);
- else
+ 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++;
sbi->s_mount_opts = ZONEFS_MNTOPT_ERRORS_RO;
sbi->s_max_open_zones = bdev_max_open_zones(sb->s_bdev);
atomic_set(&sbi->s_open_zones, 0);
- if (!sbi->s_max_open_zones &&
- sbi->s_mount_opts & ZONEFS_MNTOPT_EXPLICIT_OPEN) {
- zonefs_info(sb, "No open zones limit. Ignoring explicit_open mount option\n");
- sbi->s_mount_opts &= ~ZONEFS_MNTOPT_EXPLICIT_OPEN;
- }
ret = zonefs_read_super(sb);
if (ret)
zonefs_info(sb, "Mounting %u zones",
blkdev_nr_zones(sb->s_bdev->bd_disk));
+ if (!sbi->s_max_open_zones &&
+ sbi->s_mount_opts & ZONEFS_MNTOPT_EXPLICIT_OPEN) {
+ zonefs_info(sb, "No open zones limit. Ignoring explicit_open mount option\n");
+ sbi->s_mount_opts &= ~ZONEFS_MNTOPT_EXPLICIT_OPEN;
+ }
+
/* Create root directory inode */
ret = -ENOMEM;
inode = new_inode(sb);
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);