2020-11-10 19:26:07 +08:00
|
|
|
/* SPDX-License-Identifier: GPL-2.0 */
|
|
|
|
|
|
|
|
#ifndef BTRFS_ZONED_H
|
|
|
|
#define BTRFS_ZONED_H
|
|
|
|
|
|
|
|
#include <linux/types.h>
|
2020-11-10 19:26:08 +08:00
|
|
|
#include <linux/blkdev.h>
|
btrfs: implement log-structured superblock for ZONED mode
Superblock (and its copies) is the only data structure in btrfs which
has a fixed location on a device. Since we cannot overwrite in a
sequential write required zone, we cannot place superblock in the zone.
One easy solution is limiting superblock and copies to be placed only in
conventional zones. However, this method has two downsides: one is
reduced number of superblock copies. The location of the second copy of
superblock is 256GB, which is in a sequential write required zone on
typical devices in the market today. So, the number of superblock and
copies is limited to be two. Second downside is that we cannot support
devices which have no conventional zones at all.
To solve these two problems, we employ superblock log writing. It uses
two adjacent zones as a circular buffer to write updated superblocks.
Once the first zone is filled up, start writing into the second one.
Then, when both zones are filled up and before starting to write to the
first zone again, it reset the first zone.
We can determine the position of the latest superblock by reading write
pointer information from a device. One corner case is when both zones
are full. For this situation, we read out the last superblock of each
zone, and compare them to determine which zone is older.
The following zones are reserved as the circular buffer on ZONED btrfs.
- The primary superblock: zones 0 and 1
- The first copy: zones 16 and 17
- The second copy: zones 1024 or zone at 256GB which is minimum, and
next to it
If these reserved zones are conventional, superblock is written fixed at
the start of the zone without logging.
Signed-off-by: Naohiro Aota <naohiro.aota@wdc.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2020-11-10 19:26:14 +08:00
|
|
|
#include "volumes.h"
|
|
|
|
#include "disk-io.h"
|
2020-11-10 19:26:07 +08:00
|
|
|
|
|
|
|
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;
|
2020-11-10 19:26:09 +08:00
|
|
|
u64 max_zone_append_size;
|
2020-11-10 19:26:07 +08:00
|
|
|
u32 nr_zones;
|
|
|
|
unsigned long *seq_zones;
|
|
|
|
unsigned long *empty_zones;
|
btrfs: implement log-structured superblock for ZONED mode
Superblock (and its copies) is the only data structure in btrfs which
has a fixed location on a device. Since we cannot overwrite in a
sequential write required zone, we cannot place superblock in the zone.
One easy solution is limiting superblock and copies to be placed only in
conventional zones. However, this method has two downsides: one is
reduced number of superblock copies. The location of the second copy of
superblock is 256GB, which is in a sequential write required zone on
typical devices in the market today. So, the number of superblock and
copies is limited to be two. Second downside is that we cannot support
devices which have no conventional zones at all.
To solve these two problems, we employ superblock log writing. It uses
two adjacent zones as a circular buffer to write updated superblocks.
Once the first zone is filled up, start writing into the second one.
Then, when both zones are filled up and before starting to write to the
first zone again, it reset the first zone.
We can determine the position of the latest superblock by reading write
pointer information from a device. One corner case is when both zones
are full. For this situation, we read out the last superblock of each
zone, and compare them to determine which zone is older.
The following zones are reserved as the circular buffer on ZONED btrfs.
- The primary superblock: zones 0 and 1
- The first copy: zones 16 and 17
- The second copy: zones 1024 or zone at 256GB which is minimum, and
next to it
If these reserved zones are conventional, superblock is written fixed at
the start of the zone without logging.
Signed-off-by: Naohiro Aota <naohiro.aota@wdc.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2020-11-10 19:26:14 +08:00
|
|
|
struct blk_zone sb_zones[2 * BTRFS_SUPER_MIRROR_MAX];
|
2020-11-10 19:26:07 +08:00
|
|
|
};
|
|
|
|
|
|
|
|
#ifdef CONFIG_BLK_DEV_ZONED
|
|
|
|
int btrfs_get_dev_zone(struct btrfs_device *device, u64 pos,
|
|
|
|
struct blk_zone *zone);
|
2021-02-04 18:21:42 +08:00
|
|
|
int btrfs_get_dev_zone_info_all_devices(struct btrfs_fs_info *fs_info);
|
2020-11-10 19:26:07 +08:00
|
|
|
int btrfs_get_dev_zone_info(struct btrfs_device *device);
|
|
|
|
void btrfs_destroy_dev_zone_info(struct btrfs_device *device);
|
2020-11-10 19:26:08 +08:00
|
|
|
int btrfs_check_zoned_mode(struct btrfs_fs_info *fs_info);
|
2020-11-10 19:26:10 +08:00
|
|
|
int btrfs_check_mountopts_zoned(struct btrfs_fs_info *info);
|
btrfs: implement log-structured superblock for ZONED mode
Superblock (and its copies) is the only data structure in btrfs which
has a fixed location on a device. Since we cannot overwrite in a
sequential write required zone, we cannot place superblock in the zone.
One easy solution is limiting superblock and copies to be placed only in
conventional zones. However, this method has two downsides: one is
reduced number of superblock copies. The location of the second copy of
superblock is 256GB, which is in a sequential write required zone on
typical devices in the market today. So, the number of superblock and
copies is limited to be two. Second downside is that we cannot support
devices which have no conventional zones at all.
To solve these two problems, we employ superblock log writing. It uses
two adjacent zones as a circular buffer to write updated superblocks.
Once the first zone is filled up, start writing into the second one.
Then, when both zones are filled up and before starting to write to the
first zone again, it reset the first zone.
We can determine the position of the latest superblock by reading write
pointer information from a device. One corner case is when both zones
are full. For this situation, we read out the last superblock of each
zone, and compare them to determine which zone is older.
The following zones are reserved as the circular buffer on ZONED btrfs.
- The primary superblock: zones 0 and 1
- The first copy: zones 16 and 17
- The second copy: zones 1024 or zone at 256GB which is minimum, and
next to it
If these reserved zones are conventional, superblock is written fixed at
the start of the zone without logging.
Signed-off-by: Naohiro Aota <naohiro.aota@wdc.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2020-11-10 19:26:14 +08:00
|
|
|
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);
|
|
|
|
void btrfs_advance_sb_log(struct btrfs_device *device, int mirror);
|
|
|
|
int btrfs_reset_sb_log_zones(struct block_device *bdev, int mirror);
|
2021-02-04 18:21:48 +08:00
|
|
|
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);
|
2021-02-04 18:21:51 +08:00
|
|
|
int btrfs_load_block_group_zone_info(struct btrfs_block_group *cache, bool new);
|
2021-02-04 18:21:52 +08:00
|
|
|
void btrfs_calc_zone_unusable(struct btrfs_block_group *cache);
|
2021-02-04 18:21:54 +08:00
|
|
|
void btrfs_redirty_list_add(struct btrfs_transaction *trans,
|
|
|
|
struct extent_buffer *eb);
|
|
|
|
void btrfs_free_redirty_list(struct btrfs_transaction *trans);
|
2020-11-10 19:26:07 +08:00
|
|
|
#else /* CONFIG_BLK_DEV_ZONED */
|
|
|
|
static inline int btrfs_get_dev_zone(struct btrfs_device *device, u64 pos,
|
|
|
|
struct blk_zone *zone)
|
|
|
|
{
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2021-02-04 18:21:42 +08:00
|
|
|
static inline int btrfs_get_dev_zone_info_all_devices(struct btrfs_fs_info *fs_info)
|
|
|
|
{
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2020-11-10 19:26:07 +08:00
|
|
|
static inline int btrfs_get_dev_zone_info(struct btrfs_device *device)
|
|
|
|
{
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline void btrfs_destroy_dev_zone_info(struct btrfs_device *device) { }
|
|
|
|
|
2020-11-10 19:26:08 +08:00
|
|
|
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;
|
|
|
|
}
|
|
|
|
|
2020-11-10 19:26:10 +08:00
|
|
|
static inline int btrfs_check_mountopts_zoned(struct btrfs_fs_info *info)
|
|
|
|
{
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
btrfs: implement log-structured superblock for ZONED mode
Superblock (and its copies) is the only data structure in btrfs which
has a fixed location on a device. Since we cannot overwrite in a
sequential write required zone, we cannot place superblock in the zone.
One easy solution is limiting superblock and copies to be placed only in
conventional zones. However, this method has two downsides: one is
reduced number of superblock copies. The location of the second copy of
superblock is 256GB, which is in a sequential write required zone on
typical devices in the market today. So, the number of superblock and
copies is limited to be two. Second downside is that we cannot support
devices which have no conventional zones at all.
To solve these two problems, we employ superblock log writing. It uses
two adjacent zones as a circular buffer to write updated superblocks.
Once the first zone is filled up, start writing into the second one.
Then, when both zones are filled up and before starting to write to the
first zone again, it reset the first zone.
We can determine the position of the latest superblock by reading write
pointer information from a device. One corner case is when both zones
are full. For this situation, we read out the last superblock of each
zone, and compare them to determine which zone is older.
The following zones are reserved as the circular buffer on ZONED btrfs.
- The primary superblock: zones 0 and 1
- The first copy: zones 16 and 17
- The second copy: zones 1024 or zone at 256GB which is minimum, and
next to it
If these reserved zones are conventional, superblock is written fixed at
the start of the zone without logging.
Signed-off-by: Naohiro Aota <naohiro.aota@wdc.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2020-11-10 19:26:14 +08:00
|
|
|
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 void btrfs_advance_sb_log(struct btrfs_device *device, int mirror)
|
|
|
|
{ }
|
|
|
|
|
|
|
|
static inline int btrfs_reset_sb_log_zones(struct block_device *bdev, int mirror)
|
|
|
|
{
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2021-02-04 18:21:48 +08:00
|
|
|
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;
|
|
|
|
}
|
|
|
|
|
2021-02-04 18:21:50 +08:00
|
|
|
static inline int btrfs_load_block_group_zone_info(
|
2021-02-04 18:21:51 +08:00
|
|
|
struct btrfs_block_group *cache, bool new)
|
2021-02-04 18:21:50 +08:00
|
|
|
{
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2021-02-04 18:21:52 +08:00
|
|
|
static inline void btrfs_calc_zone_unusable(struct btrfs_block_group *cache) { }
|
|
|
|
|
2021-02-04 18:21:54 +08:00
|
|
|
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) { }
|
|
|
|
|
2020-11-10 19:26:07 +08:00
|
|
|
#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);
|
|
|
|
}
|
|
|
|
|
2020-11-10 19:26:08 +08:00
|
|
|
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)) {
|
2021-02-04 18:21:47 +08:00
|
|
|
/*
|
|
|
|
* 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);
|
2020-11-10 19:26:08 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
/* Do not allow Host Manged zoned device */
|
|
|
|
return bdev_zoned_model(bdev) != BLK_ZONED_HM;
|
|
|
|
}
|
|
|
|
|
btrfs: implement log-structured superblock for ZONED mode
Superblock (and its copies) is the only data structure in btrfs which
has a fixed location on a device. Since we cannot overwrite in a
sequential write required zone, we cannot place superblock in the zone.
One easy solution is limiting superblock and copies to be placed only in
conventional zones. However, this method has two downsides: one is
reduced number of superblock copies. The location of the second copy of
superblock is 256GB, which is in a sequential write required zone on
typical devices in the market today. So, the number of superblock and
copies is limited to be two. Second downside is that we cannot support
devices which have no conventional zones at all.
To solve these two problems, we employ superblock log writing. It uses
two adjacent zones as a circular buffer to write updated superblocks.
Once the first zone is filled up, start writing into the second one.
Then, when both zones are filled up and before starting to write to the
first zone again, it reset the first zone.
We can determine the position of the latest superblock by reading write
pointer information from a device. One corner case is when both zones
are full. For this situation, we read out the last superblock of each
zone, and compare them to determine which zone is older.
The following zones are reserved as the circular buffer on ZONED btrfs.
- The primary superblock: zones 0 and 1
- The first copy: zones 16 and 17
- The second copy: zones 1024 or zone at 256GB which is minimum, and
next to it
If these reserved zones are conventional, superblock is written fixed at
the start of the zone without logging.
Signed-off-by: Naohiro Aota <naohiro.aota@wdc.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2020-11-10 19:26:14 +08:00
|
|
|
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);
|
|
|
|
}
|
|
|
|
|
2021-02-04 18:21:56 +08:00
|
|
|
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;
|
|
|
|
}
|
|
|
|
|
2020-11-10 19:26:07 +08:00
|
|
|
#endif
|