mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-10-31 00:17:44 +00:00
e3e6a98054
commit56fbb0a4e8upstream. Commitbe1a1d7a5d("btrfs: zoned: finish fully written block group") introduced zone finishing code both for data and metadata end_io path. However, the metadata side is not working as it should. First, it compares logical address (eb->start + eb->len) with offset within a block group (cache->zone_capacity) in submit_eb_page(). That essentially disabled zone finishing on metadata end_io path. Furthermore, fixing the issue above revealed we cannot call btrfs_zone_finish_endio() in end_extent_buffer_writeback(). We cannot call btrfs_lookup_block_group() which require spin lock inside end_io context. Introduce btrfs_schedule_zone_finish_bg() to wait for the extent buffer writeback and do the zone finish IO in a workqueue. Also, drop EXTENT_BUFFER_ZONE_FINISH as it is no longer used. Fixes:be1a1d7a5d("btrfs: zoned: finish fully written block group") CC: stable@vger.kernel.org # 5.16+ Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com> Signed-off-by: Naohiro Aota <naohiro.aota@wdc.com> Signed-off-by: David Sterba <dsterba@suse.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
378 lines
11 KiB
C
378 lines
11 KiB
C
/* SPDX-License-Identifier: GPL-2.0 */
|
|
|
|
#ifndef BTRFS_ZONED_H
|
|
#define BTRFS_ZONED_H
|
|
|
|
#include <linux/types.h>
|
|
#include <linux/blkdev.h>
|
|
#include "volumes.h"
|
|
#include "disk-io.h"
|
|
#include "block-group.h"
|
|
#include "btrfs_inode.h"
|
|
|
|
/*
|
|
* Block groups with more than this value (percents) of unusable space will be
|
|
* scheduled for background reclaim.
|
|
*/
|
|
#define BTRFS_DEFAULT_RECLAIM_THRESH 75
|
|
|
|
struct btrfs_zoned_device_info {
|
|
/*
|
|
* Number of zones, zone size and types of zones if bdev is a
|
|
* zoned block device.
|
|
*/
|
|
u64 zone_size;
|
|
u8 zone_size_shift;
|
|
u32 nr_zones;
|
|
unsigned int max_active_zones;
|
|
atomic_t active_zones_left;
|
|
unsigned long *seq_zones;
|
|
unsigned long *empty_zones;
|
|
unsigned long *active_zones;
|
|
struct blk_zone *zone_cache;
|
|
struct blk_zone sb_zones[2 * BTRFS_SUPER_MIRROR_MAX];
|
|
};
|
|
|
|
#ifdef CONFIG_BLK_DEV_ZONED
|
|
int btrfs_get_dev_zone(struct btrfs_device *device, u64 pos,
|
|
struct blk_zone *zone);
|
|
int btrfs_get_dev_zone_info_all_devices(struct btrfs_fs_info *fs_info);
|
|
int btrfs_get_dev_zone_info(struct btrfs_device *device, bool populate_cache);
|
|
void btrfs_destroy_dev_zone_info(struct btrfs_device *device);
|
|
int btrfs_check_zoned_mode(struct btrfs_fs_info *fs_info);
|
|
int btrfs_check_mountopts_zoned(struct btrfs_fs_info *info);
|
|
int btrfs_sb_log_location_bdev(struct block_device *bdev, int mirror, int rw,
|
|
u64 *bytenr_ret);
|
|
int btrfs_sb_log_location(struct btrfs_device *device, int mirror, int rw,
|
|
u64 *bytenr_ret);
|
|
int btrfs_advance_sb_log(struct btrfs_device *device, int mirror);
|
|
int btrfs_reset_sb_log_zones(struct block_device *bdev, int mirror);
|
|
u64 btrfs_find_allocatable_zones(struct btrfs_device *device, u64 hole_start,
|
|
u64 hole_end, u64 num_bytes);
|
|
int btrfs_reset_device_zone(struct btrfs_device *device, u64 physical,
|
|
u64 length, u64 *bytes);
|
|
int btrfs_ensure_empty_zones(struct btrfs_device *device, u64 start, u64 size);
|
|
int btrfs_load_block_group_zone_info(struct btrfs_block_group *cache, bool new);
|
|
void btrfs_calc_zone_unusable(struct btrfs_block_group *cache);
|
|
void btrfs_redirty_list_add(struct btrfs_transaction *trans,
|
|
struct extent_buffer *eb);
|
|
void btrfs_free_redirty_list(struct btrfs_transaction *trans);
|
|
bool btrfs_use_zone_append(struct btrfs_inode *inode, u64 start);
|
|
void btrfs_record_physical_zoned(struct inode *inode, u64 file_offset,
|
|
struct bio *bio);
|
|
void btrfs_rewrite_logical_zoned(struct btrfs_ordered_extent *ordered);
|
|
bool btrfs_check_meta_write_pointer(struct btrfs_fs_info *fs_info,
|
|
struct extent_buffer *eb,
|
|
struct btrfs_block_group **cache_ret);
|
|
void btrfs_revert_meta_write_pointer(struct btrfs_block_group *cache,
|
|
struct extent_buffer *eb);
|
|
int btrfs_zoned_issue_zeroout(struct btrfs_device *device, u64 physical, u64 length);
|
|
int btrfs_sync_zone_write_pointer(struct btrfs_device *tgt_dev, u64 logical,
|
|
u64 physical_start, u64 physical_pos);
|
|
struct btrfs_device *btrfs_zoned_get_device(struct btrfs_fs_info *fs_info,
|
|
u64 logical, u64 length);
|
|
bool btrfs_zone_activate(struct btrfs_block_group *block_group);
|
|
int btrfs_zone_finish(struct btrfs_block_group *block_group);
|
|
bool btrfs_can_activate_zone(struct btrfs_fs_devices *fs_devices, u64 flags);
|
|
void btrfs_zone_finish_endio(struct btrfs_fs_info *fs_info, u64 logical,
|
|
u64 length);
|
|
void btrfs_schedule_zone_finish_bg(struct btrfs_block_group *bg,
|
|
struct extent_buffer *eb);
|
|
void btrfs_clear_data_reloc_bg(struct btrfs_block_group *bg);
|
|
void btrfs_free_zone_cache(struct btrfs_fs_info *fs_info);
|
|
#else /* CONFIG_BLK_DEV_ZONED */
|
|
static inline int btrfs_get_dev_zone(struct btrfs_device *device, u64 pos,
|
|
struct blk_zone *zone)
|
|
{
|
|
return 0;
|
|
}
|
|
|
|
static inline int btrfs_get_dev_zone_info_all_devices(struct btrfs_fs_info *fs_info)
|
|
{
|
|
return 0;
|
|
}
|
|
|
|
static inline int btrfs_get_dev_zone_info(struct btrfs_device *device,
|
|
bool populate_cache)
|
|
{
|
|
return 0;
|
|
}
|
|
|
|
static inline void btrfs_destroy_dev_zone_info(struct btrfs_device *device) { }
|
|
|
|
static inline int btrfs_check_zoned_mode(const struct btrfs_fs_info *fs_info)
|
|
{
|
|
if (!btrfs_is_zoned(fs_info))
|
|
return 0;
|
|
|
|
btrfs_err(fs_info, "zoned block devices support is not enabled");
|
|
return -EOPNOTSUPP;
|
|
}
|
|
|
|
static inline int btrfs_check_mountopts_zoned(struct btrfs_fs_info *info)
|
|
{
|
|
return 0;
|
|
}
|
|
|
|
static inline int btrfs_sb_log_location_bdev(struct block_device *bdev,
|
|
int mirror, int rw, u64 *bytenr_ret)
|
|
{
|
|
*bytenr_ret = btrfs_sb_offset(mirror);
|
|
return 0;
|
|
}
|
|
|
|
static inline int btrfs_sb_log_location(struct btrfs_device *device, int mirror,
|
|
int rw, u64 *bytenr_ret)
|
|
{
|
|
*bytenr_ret = btrfs_sb_offset(mirror);
|
|
return 0;
|
|
}
|
|
|
|
static inline int btrfs_advance_sb_log(struct btrfs_device *device, int mirror)
|
|
{
|
|
return 0;
|
|
}
|
|
|
|
static inline int btrfs_reset_sb_log_zones(struct block_device *bdev, int mirror)
|
|
{
|
|
return 0;
|
|
}
|
|
|
|
static inline u64 btrfs_find_allocatable_zones(struct btrfs_device *device,
|
|
u64 hole_start, u64 hole_end,
|
|
u64 num_bytes)
|
|
{
|
|
return hole_start;
|
|
}
|
|
|
|
static inline int btrfs_reset_device_zone(struct btrfs_device *device,
|
|
u64 physical, u64 length, u64 *bytes)
|
|
{
|
|
*bytes = 0;
|
|
return 0;
|
|
}
|
|
|
|
static inline int btrfs_ensure_empty_zones(struct btrfs_device *device,
|
|
u64 start, u64 size)
|
|
{
|
|
return 0;
|
|
}
|
|
|
|
static inline int btrfs_load_block_group_zone_info(
|
|
struct btrfs_block_group *cache, bool new)
|
|
{
|
|
return 0;
|
|
}
|
|
|
|
static inline void btrfs_calc_zone_unusable(struct btrfs_block_group *cache) { }
|
|
|
|
static inline void btrfs_redirty_list_add(struct btrfs_transaction *trans,
|
|
struct extent_buffer *eb) { }
|
|
static inline void btrfs_free_redirty_list(struct btrfs_transaction *trans) { }
|
|
|
|
static inline bool btrfs_use_zone_append(struct btrfs_inode *inode, u64 start)
|
|
{
|
|
return false;
|
|
}
|
|
|
|
static inline void btrfs_record_physical_zoned(struct inode *inode,
|
|
u64 file_offset, struct bio *bio)
|
|
{
|
|
}
|
|
|
|
static inline void btrfs_rewrite_logical_zoned(
|
|
struct btrfs_ordered_extent *ordered) { }
|
|
|
|
static inline bool btrfs_check_meta_write_pointer(struct btrfs_fs_info *fs_info,
|
|
struct extent_buffer *eb,
|
|
struct btrfs_block_group **cache_ret)
|
|
{
|
|
return true;
|
|
}
|
|
|
|
static inline void btrfs_revert_meta_write_pointer(
|
|
struct btrfs_block_group *cache,
|
|
struct extent_buffer *eb)
|
|
{
|
|
}
|
|
|
|
static inline int btrfs_zoned_issue_zeroout(struct btrfs_device *device,
|
|
u64 physical, u64 length)
|
|
{
|
|
return -EOPNOTSUPP;
|
|
}
|
|
|
|
static inline int btrfs_sync_zone_write_pointer(struct btrfs_device *tgt_dev,
|
|
u64 logical, u64 physical_start,
|
|
u64 physical_pos)
|
|
{
|
|
return -EOPNOTSUPP;
|
|
}
|
|
|
|
static inline struct btrfs_device *btrfs_zoned_get_device(
|
|
struct btrfs_fs_info *fs_info,
|
|
u64 logical, u64 length)
|
|
{
|
|
return ERR_PTR(-EOPNOTSUPP);
|
|
}
|
|
|
|
static inline bool btrfs_zone_activate(struct btrfs_block_group *block_group)
|
|
{
|
|
return true;
|
|
}
|
|
|
|
static inline int btrfs_zone_finish(struct btrfs_block_group *block_group)
|
|
{
|
|
return 0;
|
|
}
|
|
|
|
static inline bool btrfs_can_activate_zone(struct btrfs_fs_devices *fs_devices,
|
|
u64 flags)
|
|
{
|
|
return true;
|
|
}
|
|
|
|
static inline void btrfs_zone_finish_endio(struct btrfs_fs_info *fs_info,
|
|
u64 logical, u64 length) { }
|
|
|
|
static inline void btrfs_schedule_zone_finish_bg(struct btrfs_block_group *bg,
|
|
struct extent_buffer *eb) { }
|
|
|
|
static inline void btrfs_clear_data_reloc_bg(struct btrfs_block_group *bg) { }
|
|
|
|
static inline void btrfs_free_zone_cache(struct btrfs_fs_info *fs_info) { }
|
|
#endif
|
|
|
|
static inline bool btrfs_dev_is_sequential(struct btrfs_device *device, u64 pos)
|
|
{
|
|
struct btrfs_zoned_device_info *zone_info = device->zone_info;
|
|
|
|
if (!zone_info)
|
|
return false;
|
|
|
|
return test_bit(pos >> zone_info->zone_size_shift, zone_info->seq_zones);
|
|
}
|
|
|
|
static inline bool btrfs_dev_is_empty_zone(struct btrfs_device *device, u64 pos)
|
|
{
|
|
struct btrfs_zoned_device_info *zone_info = device->zone_info;
|
|
|
|
if (!zone_info)
|
|
return true;
|
|
|
|
return test_bit(pos >> zone_info->zone_size_shift, zone_info->empty_zones);
|
|
}
|
|
|
|
static inline void btrfs_dev_set_empty_zone_bit(struct btrfs_device *device,
|
|
u64 pos, bool set)
|
|
{
|
|
struct btrfs_zoned_device_info *zone_info = device->zone_info;
|
|
unsigned int zno;
|
|
|
|
if (!zone_info)
|
|
return;
|
|
|
|
zno = pos >> zone_info->zone_size_shift;
|
|
if (set)
|
|
set_bit(zno, zone_info->empty_zones);
|
|
else
|
|
clear_bit(zno, zone_info->empty_zones);
|
|
}
|
|
|
|
static inline void btrfs_dev_set_zone_empty(struct btrfs_device *device, u64 pos)
|
|
{
|
|
btrfs_dev_set_empty_zone_bit(device, pos, true);
|
|
}
|
|
|
|
static inline void btrfs_dev_clear_zone_empty(struct btrfs_device *device, u64 pos)
|
|
{
|
|
btrfs_dev_set_empty_zone_bit(device, pos, false);
|
|
}
|
|
|
|
static inline bool btrfs_check_device_zone_type(const struct btrfs_fs_info *fs_info,
|
|
struct block_device *bdev)
|
|
{
|
|
if (btrfs_is_zoned(fs_info)) {
|
|
/*
|
|
* We can allow a regular device on a zoned filesystem, because
|
|
* we will emulate the zoned capabilities.
|
|
*/
|
|
if (!bdev_is_zoned(bdev))
|
|
return true;
|
|
|
|
return fs_info->zone_size ==
|
|
(bdev_zone_sectors(bdev) << SECTOR_SHIFT);
|
|
}
|
|
|
|
/* Do not allow Host Manged zoned device */
|
|
return bdev_zoned_model(bdev) != BLK_ZONED_HM;
|
|
}
|
|
|
|
static inline bool btrfs_check_super_location(struct btrfs_device *device, u64 pos)
|
|
{
|
|
/*
|
|
* On a non-zoned device, any address is OK. On a zoned device,
|
|
* non-SEQUENTIAL WRITE REQUIRED zones are capable.
|
|
*/
|
|
return device->zone_info == NULL || !btrfs_dev_is_sequential(device, pos);
|
|
}
|
|
|
|
static inline bool btrfs_can_zone_reset(struct btrfs_device *device,
|
|
u64 physical, u64 length)
|
|
{
|
|
u64 zone_size;
|
|
|
|
if (!btrfs_dev_is_sequential(device, physical))
|
|
return false;
|
|
|
|
zone_size = device->zone_info->zone_size;
|
|
if (!IS_ALIGNED(physical, zone_size) || !IS_ALIGNED(length, zone_size))
|
|
return false;
|
|
|
|
return true;
|
|
}
|
|
|
|
static inline void btrfs_zoned_meta_io_lock(struct btrfs_fs_info *fs_info)
|
|
{
|
|
if (!btrfs_is_zoned(fs_info))
|
|
return;
|
|
mutex_lock(&fs_info->zoned_meta_io_lock);
|
|
}
|
|
|
|
static inline void btrfs_zoned_meta_io_unlock(struct btrfs_fs_info *fs_info)
|
|
{
|
|
if (!btrfs_is_zoned(fs_info))
|
|
return;
|
|
mutex_unlock(&fs_info->zoned_meta_io_lock);
|
|
}
|
|
|
|
static inline void btrfs_clear_treelog_bg(struct btrfs_block_group *bg)
|
|
{
|
|
struct btrfs_fs_info *fs_info = bg->fs_info;
|
|
|
|
if (!btrfs_is_zoned(fs_info))
|
|
return;
|
|
|
|
spin_lock(&fs_info->treelog_bg_lock);
|
|
if (fs_info->treelog_bg == bg->start)
|
|
fs_info->treelog_bg = 0;
|
|
spin_unlock(&fs_info->treelog_bg_lock);
|
|
}
|
|
|
|
static inline void btrfs_zoned_data_reloc_lock(struct btrfs_inode *inode)
|
|
{
|
|
struct btrfs_root *root = inode->root;
|
|
|
|
if (btrfs_is_data_reloc_root(root) && btrfs_is_zoned(root->fs_info))
|
|
mutex_lock(&root->fs_info->zoned_data_reloc_io_lock);
|
|
}
|
|
|
|
static inline void btrfs_zoned_data_reloc_unlock(struct btrfs_inode *inode)
|
|
{
|
|
struct btrfs_root *root = inode->root;
|
|
|
|
if (btrfs_is_data_reloc_root(root) && btrfs_is_zoned(root->fs_info))
|
|
mutex_unlock(&root->fs_info->zoned_data_reloc_io_lock);
|
|
}
|
|
|
|
#endif
|