path: root/fs/zonefs/super.c

// 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/fs.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"

static int zonefs_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 */
	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_WRITE) && !(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);
	isize = i_size_read(inode);
	if (offset >= isize)
		iomap->type = IOMAP_UNWRITTEN;
	else
		iomap->type = IOMAP_MAPPED;
	if (flags & IOMAP_WRITE)
		length = zi->i_max_size - offset;
	else
		length = min(length, isize - 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;

	return 0;
}

static const struct iomap_ops zonefs_iomap_ops = {
	.iomap_begin	= zonefs_iomap_begin,
};

static int zonefs_readpage(struct file *unused, struct page *page)
{
	return iomap_readpage(page, &zonefs_iomap_ops);
}

static void zonefs_readahead(struct readahead_control *rac)
{
	iomap_readahead(rac, &zonefs_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)
{
	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_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,
};

static int zonefs_writepage(struct page *page, struct writeback_control *wbc)
{
	struct iomap_writepage_ctx wpc = { };

	return iomap_writepage(page, wbc, &wpc, &zonefs_writeback_ops);
}

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 const struct address_space_operations zonefs_file_aops = {
	.readpage		= zonefs_readpage,
	.readahead		= zonefs_readahead,
	.writepage		= zonefs_writepage,
	.writepages		= zonefs_writepages,
	.set_page_dirty		= iomap_set_page_dirty,
	.releasepage		= iomap_releasepage,
	.invalidatepage		= iomap_invalidatepage,
	.migratepage		= iomap_migrate_page,
	.is_partially_uptodate	= iomap_is_partially_uptodate,
	.error_remove_page	= generic_error_remove_page,
	.direct_IO		= noop_direct_IO,
};

static 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, bool warn,
					  bool mount)
{
	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;
		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.
		 */
		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;
			return 0;
		}
		inode->i_mode &= ~0222;
		return i_size_read(inode);
	default:
		if (zi->i_ztype == ZONEFS_ZTYPE_CNV)
			return zi->i_max_size;
		return (zone->wp - zone->start) << SECTOR_SHIFT;
	}
}

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, true, false);
	isize = i_size_read(inode);
	if (zone->cond != BLK_ZONE_COND_OFFLINE &&
	    zone->cond != BLK_ZONE_COND_READONLY &&
	    !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 f