2020-11-10 14:26:07 +03:00
|
|
|
// SPDX-License-Identifier: GPL-2.0
|
|
|
|
|
2021-02-04 13:21:48 +03:00
|
|
|
#include <linux/bitops.h>
|
2020-11-10 14:26:07 +03:00
|
|
|
#include <linux/slab.h>
|
|
|
|
#include <linux/blkdev.h>
|
2021-02-04 13:21:50 +03:00
|
|
|
#include <linux/sched/mm.h>
|
2020-11-10 14:26:07 +03:00
|
|
|
#include "ctree.h"
|
|
|
|
#include "volumes.h"
|
|
|
|
#include "zoned.h"
|
|
|
|
#include "rcu-string.h"
|
2021-02-04 13:21:48 +03:00
|
|
|
#include "disk-io.h"
|
2021-02-04 13:21:50 +03:00
|
|
|
#include "block-group.h"
|
2020-11-10 14:26:07 +03:00
|
|
|
|
|
|
|
/* Maximum number of zones to report per blkdev_report_zones() call */
|
|
|
|
#define BTRFS_REPORT_NR_ZONES 4096
|
2021-02-04 13:21:50 +03:00
|
|
|
/* Invalid allocation pointer value for missing devices */
|
|
|
|
#define WP_MISSING_DEV ((u64)-1)
|
|
|
|
/* Pseudo write pointer value for conventional zone */
|
|
|
|
#define WP_CONVENTIONAL ((u64)-2)
|
2020-11-10 14:26:07 +03:00
|
|
|
|
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 14:26:14 +03:00
|
|
|
/* Number of superblock log zones */
|
|
|
|
#define BTRFS_NR_SB_LOG_ZONES 2
|
|
|
|
|
2020-11-10 14:26:07 +03:00
|
|
|
static int copy_zone_info_cb(struct blk_zone *zone, unsigned int idx, void *data)
|
|
|
|
{
|
|
|
|
struct blk_zone *zones = data;
|
|
|
|
|
|
|
|
memcpy(&zones[idx], zone, sizeof(*zone));
|
|
|
|
|
|
|
|
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 14:26:14 +03:00
|
|
|
static int sb_write_pointer(struct block_device *bdev, struct blk_zone *zones,
|
|
|
|
u64 *wp_ret)
|
|
|
|
{
|
|
|
|
bool empty[BTRFS_NR_SB_LOG_ZONES];
|
|
|
|
bool full[BTRFS_NR_SB_LOG_ZONES];
|
|
|
|
sector_t sector;
|
|
|
|
|
|
|
|
ASSERT(zones[0].type != BLK_ZONE_TYPE_CONVENTIONAL &&
|
|
|
|
zones[1].type != BLK_ZONE_TYPE_CONVENTIONAL);
|
|
|
|
|
|
|
|
empty[0] = (zones[0].cond == BLK_ZONE_COND_EMPTY);
|
|
|
|
empty[1] = (zones[1].cond == BLK_ZONE_COND_EMPTY);
|
|
|
|
full[0] = (zones[0].cond == BLK_ZONE_COND_FULL);
|
|
|
|
full[1] = (zones[1].cond == BLK_ZONE_COND_FULL);
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Possible states of log buffer zones
|
|
|
|
*
|
|
|
|
* Empty[0] In use[0] Full[0]
|
|
|
|
* Empty[1] * x 0
|
|
|
|
* In use[1] 0 x 0
|
|
|
|
* Full[1] 1 1 C
|
|
|
|
*
|
|
|
|
* Log position:
|
|
|
|
* *: Special case, no superblock is written
|
|
|
|
* 0: Use write pointer of zones[0]
|
|
|
|
* 1: Use write pointer of zones[1]
|
|
|
|
* C: Compare super blcoks from zones[0] and zones[1], use the latest
|
|
|
|
* one determined by generation
|
|
|
|
* x: Invalid state
|
|
|
|
*/
|
|
|
|
|
|
|
|
if (empty[0] && empty[1]) {
|
|
|
|
/* Special case to distinguish no superblock to read */
|
|
|
|
*wp_ret = zones[0].start << SECTOR_SHIFT;
|
|
|
|
return -ENOENT;
|
|
|
|
} else if (full[0] && full[1]) {
|
|
|
|
/* Compare two super blocks */
|
|
|
|
struct address_space *mapping = bdev->bd_inode->i_mapping;
|
|
|
|
struct page *page[BTRFS_NR_SB_LOG_ZONES];
|
|
|
|
struct btrfs_super_block *super[BTRFS_NR_SB_LOG_ZONES];
|
|
|
|
int i;
|
|
|
|
|
|
|
|
for (i = 0; i < BTRFS_NR_SB_LOG_ZONES; i++) {
|
|
|
|
u64 bytenr;
|
|
|
|
|
|
|
|
bytenr = ((zones[i].start + zones[i].len)
|
|
|
|
<< SECTOR_SHIFT) - BTRFS_SUPER_INFO_SIZE;
|
|
|
|
|
|
|
|
page[i] = read_cache_page_gfp(mapping,
|
|
|
|
bytenr >> PAGE_SHIFT, GFP_NOFS);
|
|
|
|
if (IS_ERR(page[i])) {
|
|
|
|
if (i == 1)
|
|
|
|
btrfs_release_disk_super(super[0]);
|
|
|
|
return PTR_ERR(page[i]);
|
|
|
|
}
|
|
|
|
super[i] = page_address(page[i]);
|
|
|
|
}
|
|
|
|
|
|
|
|
if (super[0]->generation > super[1]->generation)
|
|
|
|
sector = zones[1].start;
|
|
|
|
else
|
|
|
|
sector = zones[0].start;
|
|
|
|
|
|
|
|
for (i = 0; i < BTRFS_NR_SB_LOG_ZONES; i++)
|
|
|
|
btrfs_release_disk_super(super[i]);
|
|
|
|
} else if (!full[0] && (empty[1] || full[1])) {
|
|
|
|
sector = zones[0].wp;
|
|
|
|
} else if (full[0]) {
|
|
|
|
sector = zones[1].wp;
|
|
|
|
} else {
|
|
|
|
return -EUCLEAN;
|
|
|
|
}
|
|
|
|
*wp_ret = sector << SECTOR_SHIFT;
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* 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
|
|
|
|
* the following one
|
|
|
|
*/
|
|
|
|
static inline u32 sb_zone_number(int shift, int mirror)
|
|
|
|
{
|
|
|
|
ASSERT(mirror < BTRFS_SUPER_MIRROR_MAX);
|
|
|
|
|
|
|
|
switch (mirror) {
|
|
|
|
case 0: return 0;
|
|
|
|
case 1: return 16;
|
|
|
|
case 2: return min_t(u64, btrfs_sb_offset(mirror) >> shift, 1024);
|
|
|
|
}
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2021-02-04 13:21:47 +03:00
|
|
|
/*
|
|
|
|
* Emulate blkdev_report_zones() for a non-zoned device. It slices up the block
|
|
|
|
* device into static sized chunks and fake a conventional zone on each of
|
|
|
|
* them.
|
|
|
|
*/
|
|
|
|
static int emulate_report_zones(struct btrfs_device *device, u64 pos,
|
|
|
|
struct blk_zone *zones, unsigned int nr_zones)
|
|
|
|
{
|
|
|
|
const sector_t zone_sectors = device->fs_info->zone_size >> SECTOR_SHIFT;
|
|
|
|
sector_t bdev_size = bdev_nr_sectors(device->bdev);
|
|
|
|
unsigned int i;
|
|
|
|
|
|
|
|
pos >>= SECTOR_SHIFT;
|
|
|
|
for (i = 0; i < nr_zones; i++) {
|
|
|
|
zones[i].start = i * zone_sectors + pos;
|
|
|
|
zones[i].len = zone_sectors;
|
|
|
|
zones[i].capacity = zone_sectors;
|
|
|
|
zones[i].wp = zones[i].start + zone_sectors;
|
|
|
|
zones[i].type = BLK_ZONE_TYPE_CONVENTIONAL;
|
|
|
|
zones[i].cond = BLK_ZONE_COND_NOT_WP;
|
|
|
|
|
|
|
|
if (zones[i].wp >= bdev_size) {
|
|
|
|
i++;
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
return i;
|
|
|
|
}
|
|
|
|
|
2020-11-10 14:26:07 +03:00
|
|
|
static int btrfs_get_dev_zones(struct btrfs_device *device, u64 pos,
|
|
|
|
struct blk_zone *zones, unsigned int *nr_zones)
|
|
|
|
{
|
|
|
|
int ret;
|
|
|
|
|
|
|
|
if (!*nr_zones)
|
|
|
|
return 0;
|
|
|
|
|
2021-02-04 13:21:47 +03:00
|
|
|
if (!bdev_is_zoned(device->bdev)) {
|
|
|
|
ret = emulate_report_zones(device, pos, zones, *nr_zones);
|
|
|
|
*nr_zones = ret;
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2020-11-10 14:26:07 +03:00
|
|
|
ret = blkdev_report_zones(device->bdev, pos >> SECTOR_SHIFT, *nr_zones,
|
|
|
|
copy_zone_info_cb, zones);
|
|
|
|
if (ret < 0) {
|
|
|
|
btrfs_err_in_rcu(device->fs_info,
|
|
|
|
"zoned: failed to read zone %llu on %s (devid %llu)",
|
|
|
|
pos, rcu_str_deref(device->name),
|
|
|
|
device->devid);
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
*nr_zones = ret;
|
|
|
|
if (!ret)
|
|
|
|
return -EIO;
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2021-02-04 13:21:47 +03:00
|
|
|
/* The emulated zone size is determined from the size of device extent */
|
|
|
|
static int calculate_emulated_zone_size(struct btrfs_fs_info *fs_info)
|
|
|
|
{
|
|
|
|
struct btrfs_path *path;
|
|
|
|
struct btrfs_root *root = fs_info->dev_root;
|
|
|
|
struct btrfs_key key;
|
|
|
|
struct extent_buffer *leaf;
|
|
|
|
struct btrfs_dev_extent *dext;
|
|
|
|
int ret = 0;
|
|
|
|
|
|
|
|
key.objectid = 1;
|
|
|
|
key.type = BTRFS_DEV_EXTENT_KEY;
|
|
|
|
key.offset = 0;
|
|
|
|
|
|
|
|
path = btrfs_alloc_path();
|
|
|
|
if (!path)
|
|
|
|
return -ENOMEM;
|
|
|
|
|
|
|
|
ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
|
|
|
|
if (ret < 0)
|
|
|
|
goto out;
|
|
|
|
|
|
|
|
if (path->slots[0] >= btrfs_header_nritems(path->nodes[0])) {
|
|
|
|
ret = btrfs_next_item(root, path);
|
|
|
|
if (ret < 0)
|
|
|
|
goto out;
|
|
|
|
/* No dev extents at all? Not good */
|
|
|
|
if (ret > 0) {
|
|
|
|
ret = -EUCLEAN;
|
|
|
|
goto out;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
leaf = path->nodes[0];
|
|
|
|
dext = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_dev_extent);
|
|
|
|
fs_info->zone_size = btrfs_dev_extent_length(leaf, dext);
|
|
|
|
ret = 0;
|
|
|
|
|
|
|
|
out:
|
|
|
|
btrfs_free_path(path);
|
|
|
|
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
2021-02-04 13:21:42 +03:00
|
|
|
int btrfs_get_dev_zone_info_all_devices(struct btrfs_fs_info *fs_info)
|
|
|
|
{
|
|
|
|
struct btrfs_fs_devices *fs_devices = fs_info->fs_devices;
|
|
|
|
struct btrfs_device *device;
|
|
|
|
int ret = 0;
|
|
|
|
|
|
|
|
/* fs_info->zone_size might not set yet. Use the incomapt flag here. */
|
|
|
|
if (!btrfs_fs_incompat(fs_info, ZONED))
|
|
|
|
return 0;
|
|
|
|
|
|
|
|
mutex_lock(&fs_devices->device_list_mutex);
|
|
|
|
list_for_each_entry(device, &fs_devices->devices, dev_list) {
|
|
|
|
/* We can skip reading of zone info for missing devices */
|
|
|
|
if (!device->bdev)
|
|
|
|
continue;
|
|
|
|
|
|
|
|
ret = btrfs_get_dev_zone_info(device);
|
|
|
|
if (ret)
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
mutex_unlock(&fs_devices->device_list_mutex);
|
|
|
|
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
2020-11-10 14:26:07 +03:00
|
|
|
int btrfs_get_dev_zone_info(struct btrfs_device *device)
|
|
|
|
{
|
2021-02-04 13:21:47 +03:00
|
|
|
struct btrfs_fs_info *fs_info = device->fs_info;
|
2020-11-10 14:26:07 +03:00
|
|
|
struct btrfs_zoned_device_info *zone_info = NULL;
|
|
|
|
struct block_device *bdev = device->bdev;
|
2020-11-10 14:26:09 +03:00
|
|
|
struct request_queue *queue = bdev_get_queue(bdev);
|
2020-11-10 14:26:07 +03:00
|
|
|
sector_t nr_sectors;
|
|
|
|
sector_t sector = 0;
|
|
|
|
struct blk_zone *zones = NULL;
|
|
|
|
unsigned int i, nreported = 0, nr_zones;
|
|
|
|
unsigned int zone_sectors;
|
2021-02-04 13:21:47 +03:00
|
|
|
char *model, *emulated;
|
2020-11-10 14:26:07 +03:00
|
|
|
int ret;
|
|
|
|
|
2021-02-04 13:21:47 +03:00
|
|
|
/*
|
|
|
|
* Cannot use btrfs_is_zoned here, since fs_info::zone_size might not
|
|
|
|
* yet be set.
|
|
|
|
*/
|
|
|
|
if (!btrfs_fs_incompat(fs_info, ZONED))
|
2020-11-10 14:26:07 +03:00
|
|
|
return 0;
|
|
|
|
|
|
|
|
if (device->zone_info)
|
|
|
|
return 0;
|
|
|
|
|
|
|
|
zone_info = kzalloc(sizeof(*zone_info), GFP_KERNEL);
|
|
|
|
if (!zone_info)
|
|
|
|
return -ENOMEM;
|
|
|
|
|
2021-02-04 13:21:47 +03:00
|
|
|
if (!bdev_is_zoned(bdev)) {
|
|
|
|
if (!fs_info->zone_size) {
|
|
|
|
ret = calculate_emulated_zone_size(fs_info);
|
|
|
|
if (ret)
|
|
|
|
goto out;
|
|
|
|
}
|
|
|
|
|
|
|
|
ASSERT(fs_info->zone_size);
|
|
|
|
zone_sectors = fs_info->zone_size >> SECTOR_SHIFT;
|
|
|
|
} else {
|
|
|
|
zone_sectors = bdev_zone_sectors(bdev);
|
|
|
|
}
|
|
|
|
|
2020-12-16 23:57:51 +03:00
|
|
|
nr_sectors = bdev_nr_sectors(bdev);
|
2020-11-10 14:26:07 +03:00
|
|
|
/* Check if it's power of 2 (see is_power_of_2) */
|
|
|
|
ASSERT(zone_sectors != 0 && (zone_sectors & (zone_sectors - 1)) == 0);
|
|
|
|
zone_info->zone_size = zone_sectors << SECTOR_SHIFT;
|
|
|
|
zone_info->zone_size_shift = ilog2(zone_info->zone_size);
|
2020-11-10 14:26:09 +03:00
|
|
|
zone_info->max_zone_append_size =
|
|
|
|
(u64)queue_max_zone_append_sectors(queue) << SECTOR_SHIFT;
|
2020-11-10 14:26:07 +03:00
|
|
|
zone_info->nr_zones = nr_sectors >> ilog2(zone_sectors);
|
|
|
|
if (!IS_ALIGNED(nr_sectors, zone_sectors))
|
|
|
|
zone_info->nr_zones++;
|
|
|
|
|
|
|
|
zone_info->seq_zones = bitmap_zalloc(zone_info->nr_zones, GFP_KERNEL);
|
|
|
|
if (!zone_info->seq_zones) {
|
|
|
|
ret = -ENOMEM;
|
|
|
|
goto out;
|
|
|
|
}
|
|
|
|
|
|
|
|
zone_info->empty_zones = bitmap_zalloc(zone_info->nr_zones, GFP_KERNEL);
|
|
|
|
if (!zone_info->empty_zones) {
|
|
|
|
ret = -ENOMEM;
|
|
|
|
goto out;
|
|
|
|
}
|
|
|
|
|
|
|
|
zones = kcalloc(BTRFS_REPORT_NR_ZONES, sizeof(struct blk_zone), GFP_KERNEL);
|
|
|
|
if (!zones) {
|
|
|
|
ret = -ENOMEM;
|
|
|
|
goto out;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* Get zones type */
|
|
|
|
while (sector < nr_sectors) {
|
|
|
|
nr_zones = BTRFS_REPORT_NR_ZONES;
|
|
|
|
ret = btrfs_get_dev_zones(device, sector << SECTOR_SHIFT, zones,
|
|
|
|
&nr_zones);
|
|
|
|
if (ret)
|
|
|
|
goto out;
|
|
|
|
|
|
|
|
for (i = 0; i < nr_zones; i++) {
|
|
|
|
if (zones[i].type == BLK_ZONE_TYPE_SEQWRITE_REQ)
|
|
|
|
__set_bit(nreported, zone_info->seq_zones);
|
|
|
|
if (zones[i].cond == BLK_ZONE_COND_EMPTY)
|
|
|
|
__set_bit(nreported, zone_info->empty_zones);
|
|
|
|
nreported++;
|
|
|
|
}
|
|
|
|
sector = zones[nr_zones - 1].start + zones[nr_zones - 1].len;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (nreported != zone_info->nr_zones) {
|
|
|
|
btrfs_err_in_rcu(device->fs_info,
|
|
|
|
"inconsistent number of zones on %s (%u/%u)",
|
|
|
|
rcu_str_deref(device->name), nreported,
|
|
|
|
zone_info->nr_zones);
|
|
|
|
ret = -EIO;
|
|
|
|
goto out;
|
|
|
|
}
|
|
|
|
|
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 14:26:14 +03:00
|
|
|
/* Validate superblock log */
|
|
|
|
nr_zones = BTRFS_NR_SB_LOG_ZONES;
|
|
|
|
for (i = 0; i < BTRFS_SUPER_MIRROR_MAX; i++) {
|
|
|
|
u32 sb_zone;
|
|
|
|
u64 sb_wp;
|
|
|
|
int sb_pos = BTRFS_NR_SB_LOG_ZONES * i;
|
|
|
|
|
|
|
|
sb_zone = sb_zone_number(zone_info->zone_size_shift, i);
|
|
|
|
if (sb_zone + 1 >= zone_info->nr_zones)
|
|
|
|
continue;
|
|
|
|
|
|
|
|
sector = sb_zone << (zone_info->zone_size_shift - SECTOR_SHIFT);
|
|
|
|
ret = btrfs_get_dev_zones(device, sector << SECTOR_SHIFT,
|
|
|
|
&zone_info->sb_zones[sb_pos],
|
|
|
|
&nr_zones);
|
|
|
|
if (ret)
|
|
|
|
goto out;
|
|
|
|
|
|
|
|
if (nr_zones != BTRFS_NR_SB_LOG_ZONES) {
|
|
|
|
btrfs_err_in_rcu(device->fs_info,
|
|
|
|
"zoned: failed to read super block log zone info at devid %llu zone %u",
|
|
|
|
device->devid, sb_zone);
|
|
|
|
ret = -EUCLEAN;
|
|
|
|
goto out;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* If zones[0] is conventional, always use the beggining of the
|
|
|
|
* zone to record superblock. No need to validate in that case.
|
|
|
|
*/
|
|
|
|
if (zone_info->sb_zones[BTRFS_NR_SB_LOG_ZONES * i].type ==
|
|
|
|
BLK_ZONE_TYPE_CONVENTIONAL)
|
|
|
|
continue;
|
|
|
|
|
|
|
|
ret = sb_write_pointer(device->bdev,
|
|
|
|
&zone_info->sb_zones[sb_pos], &sb_wp);
|
|
|
|
if (ret != -ENOENT && ret) {
|
|
|
|
btrfs_err_in_rcu(device->fs_info,
|
|
|
|
"zoned: super block log zone corrupted devid %llu zone %u",
|
|
|
|
device->devid, sb_zone);
|
|
|
|
ret = -EUCLEAN;
|
|
|
|
goto out;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
|
2020-11-10 14:26:07 +03:00
|
|
|
kfree(zones);
|
|
|
|
|
|
|
|
device->zone_info = zone_info;
|
|
|
|
|
2021-02-04 13:21:47 +03:00
|
|
|
switch (bdev_zoned_model(bdev)) {
|
|
|
|
case BLK_ZONED_HM:
|
|
|
|
model = "host-managed zoned";
|
|
|
|
emulated = "";
|
|
|
|
break;
|
|
|
|
case BLK_ZONED_HA:
|
|
|
|
model = "host-aware zoned";
|
|
|
|
emulated = "";
|
|
|
|
break;
|
|
|
|
case BLK_ZONED_NONE:
|
|
|
|
model = "regular";
|
|
|
|
emulated = "emulated ";
|
|
|
|
break;
|
|
|
|
default:
|
|
|
|
/* Just in case */
|
|
|
|
btrfs_err_in_rcu(fs_info, "zoned: unsupported model %d on %s",
|
|
|
|
bdev_zoned_model(bdev),
|
|
|
|
rcu_str_deref(device->name));
|
|
|
|
ret = -EOPNOTSUPP;
|
|
|
|
goto out_free_zone_info;
|
|
|
|
}
|
|
|
|
|
|
|
|
btrfs_info_in_rcu(fs_info,
|
|
|
|
"%s block device %s, %u %szones of %llu bytes",
|
|
|
|
model, rcu_str_deref(device->name), zone_info->nr_zones,
|
|
|
|
emulated, zone_info->zone_size);
|
2020-11-10 14:26:07 +03:00
|
|
|
|
|
|
|
return 0;
|
|
|
|
|
|
|
|
out:
|
|
|
|
kfree(zones);
|
2021-02-04 13:21:47 +03:00
|
|
|
out_free_zone_info:
|
2020-11-10 14:26:07 +03:00
|
|
|
bitmap_free(zone_info->empty_zones);
|
|
|
|
bitmap_free(zone_info->seq_zones);
|
|
|
|
kfree(zone_info);
|
2021-02-04 13:21:47 +03:00
|
|
|
device->zone_info = NULL;
|
2020-11-10 14:26:07 +03:00
|
|
|
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
|
|
|
void btrfs_destroy_dev_zone_info(struct btrfs_device *device)
|
|
|
|
{
|
|
|
|
struct btrfs_zoned_device_info *zone_info = device->zone_info;
|
|
|
|
|
|
|
|
if (!zone_info)
|
|
|
|
return;
|
|
|
|
|
|
|
|
bitmap_free(zone_info->seq_zones);
|
|
|
|
bitmap_free(zone_info->empty_zones);
|
|
|
|
kfree(zone_info);
|
|
|
|
device->zone_info = NULL;
|
|
|
|
}
|
|
|
|
|
|
|
|
int btrfs_get_dev_zone(struct btrfs_device *device, u64 pos,
|
|
|
|
struct blk_zone *zone)
|
|
|
|
{
|
|
|
|
unsigned int nr_zones = 1;
|
|
|
|
int ret;
|
|
|
|
|
|
|
|
ret = btrfs_get_dev_zones(device, pos, zone, &nr_zones);
|
|
|
|
if (ret != 0 || !nr_zones)
|
|
|
|
return ret ? ret : -EIO;
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
2020-11-10 14:26:08 +03:00
|
|
|
|
|
|
|
int btrfs_check_zoned_mode(struct btrfs_fs_info *fs_info)
|
|
|
|
{
|
|
|
|
struct btrfs_fs_devices *fs_devices = fs_info->fs_devices;
|
|
|
|
struct btrfs_device *device;
|
|
|
|
u64 zoned_devices = 0;
|
|
|
|
u64 nr_devices = 0;
|
|
|
|
u64 zone_size = 0;
|
2020-11-10 14:26:09 +03:00
|
|
|
u64 max_zone_append_size = 0;
|
2021-02-04 13:21:47 +03:00
|
|
|
const bool incompat_zoned = btrfs_fs_incompat(fs_info, ZONED);
|
2020-11-10 14:26:08 +03:00
|
|
|
int ret = 0;
|
|
|
|
|
|
|
|
/* Count zoned devices */
|
|
|
|
list_for_each_entry(device, &fs_devices->devices, dev_list) {
|
|
|
|
enum blk_zoned_model model;
|
|
|
|
|
|
|
|
if (!device->bdev)
|
|
|
|
continue;
|
|
|
|
|
|
|
|
model = bdev_zoned_model(device->bdev);
|
2021-02-04 13:21:47 +03:00
|
|
|
/*
|
|
|
|
* A Host-Managed zoned device must be used as a zoned device.
|
|
|
|
* A Host-Aware zoned device and a non-zoned devices can be
|
|
|
|
* treated as a zoned device, if ZONED flag is enabled in the
|
|
|
|
* superblock.
|
|
|
|
*/
|
2020-11-10 14:26:08 +03:00
|
|
|
if (model == BLK_ZONED_HM ||
|
2021-02-04 13:21:47 +03:00
|
|
|
(model == BLK_ZONED_HA && incompat_zoned) ||
|
|
|
|
(model == BLK_ZONED_NONE && incompat_zoned)) {
|
|
|
|
struct btrfs_zoned_device_info *zone_info =
|
|
|
|
device->zone_info;
|
2020-11-10 14:26:09 +03:00
|
|
|
|
|
|
|
zone_info = device->zone_info;
|
2020-11-10 14:26:08 +03:00
|
|
|
zoned_devices++;
|
|
|
|
if (!zone_size) {
|
2020-11-10 14:26:09 +03:00
|
|
|
zone_size = zone_info->zone_size;
|
|
|
|
} else if (zone_info->zone_size != zone_size) {
|
2020-11-10 14:26:08 +03:00
|
|
|
btrfs_err(fs_info,
|
|
|
|
"zoned: unequal block device zone sizes: have %llu found %llu",
|
|
|
|
device->zone_info->zone_size,
|
|
|
|
zone_size);
|
|
|
|
ret = -EINVAL;
|
|
|
|
goto out;
|
|
|
|
}
|
2020-11-10 14:26:09 +03:00
|
|
|
if (!max_zone_append_size ||
|
|
|
|
(zone_info->max_zone_append_size &&
|
|
|
|
zone_info->max_zone_append_size < max_zone_append_size))
|
|
|
|
max_zone_append_size =
|
|
|
|
zone_info->max_zone_append_size;
|
2020-11-10 14:26:08 +03:00
|
|
|
}
|
|
|
|
nr_devices++;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (!zoned_devices && !incompat_zoned)
|
|
|
|
goto out;
|
|
|
|
|
|
|
|
if (!zoned_devices && incompat_zoned) {
|
|
|
|
/* No zoned block device found on ZONED filesystem */
|
|
|
|
btrfs_err(fs_info,
|
|
|
|
"zoned: no zoned devices found on a zoned filesystem");
|
|
|
|
ret = -EINVAL;
|
|
|
|
goto out;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (zoned_devices && !incompat_zoned) {
|
|
|
|
btrfs_err(fs_info,
|
|
|
|
"zoned: mode not enabled but zoned device found");
|
|
|
|
ret = -EINVAL;
|
|
|
|
goto out;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (zoned_devices != nr_devices) {
|
|
|
|
btrfs_err(fs_info,
|
|
|
|
"zoned: cannot mix zoned and regular devices");
|
|
|
|
ret = -EINVAL;
|
|
|
|
goto out;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* stripe_size is always aligned to BTRFS_STRIPE_LEN in
|
|
|
|
* __btrfs_alloc_chunk(). Since we want stripe_len == zone_size,
|
|
|
|
* check the alignment here.
|
|
|
|
*/
|
|
|
|
if (!IS_ALIGNED(zone_size, BTRFS_STRIPE_LEN)) {
|
|
|
|
btrfs_err(fs_info,
|
|
|
|
"zoned: zone size %llu not aligned to stripe %u",
|
|
|
|
zone_size, BTRFS_STRIPE_LEN);
|
|
|
|
ret = -EINVAL;
|
|
|
|
goto out;
|
|
|
|
}
|
|
|
|
|
2020-11-10 14:26:13 +03:00
|
|
|
if (btrfs_fs_incompat(fs_info, MIXED_GROUPS)) {
|
|
|
|
btrfs_err(fs_info, "zoned: mixed block groups not supported");
|
|
|
|
ret = -EINVAL;
|
|
|
|
goto out;
|
|
|
|
}
|
|
|
|
|
2020-11-10 14:26:08 +03:00
|
|
|
fs_info->zone_size = zone_size;
|
2020-11-10 14:26:09 +03:00
|
|
|
fs_info->max_zone_append_size = max_zone_append_size;
|
2021-02-04 13:21:48 +03:00
|
|
|
fs_info->fs_devices->chunk_alloc_policy = BTRFS_CHUNK_ALLOC_ZONED;
|
2020-11-10 14:26:08 +03:00
|
|
|
|
2021-02-04 13:21:45 +03:00
|
|
|
/*
|
|
|
|
* Check mount options here, because we might change fs_info->zoned
|
|
|
|
* from fs_info->zone_size.
|
|
|
|
*/
|
|
|
|
ret = btrfs_check_mountopts_zoned(fs_info);
|
|
|
|
if (ret)
|
|
|
|
goto out;
|
|
|
|
|
2020-11-10 14:26:08 +03:00
|
|
|
btrfs_info(fs_info, "zoned mode enabled with zone size %llu", zone_size);
|
|
|
|
out:
|
|
|
|
return ret;
|
|
|
|
}
|
2020-11-10 14:26:10 +03:00
|
|
|
|
|
|
|
int btrfs_check_mountopts_zoned(struct btrfs_fs_info *info)
|
|
|
|
{
|
|
|
|
if (!btrfs_is_zoned(info))
|
|
|
|
return 0;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Space cache writing is not COWed. Disable that to avoid write errors
|
|
|
|
* in sequential zones.
|
|
|
|
*/
|
|
|
|
if (btrfs_test_opt(info, SPACE_CACHE)) {
|
|
|
|
btrfs_err(info, "zoned: space cache v1 is not supported");
|
|
|
|
return -EINVAL;
|
|
|
|
}
|
|
|
|
|
2020-11-10 14:26:11 +03:00
|
|
|
if (btrfs_test_opt(info, NODATACOW)) {
|
|
|
|
btrfs_err(info, "zoned: NODATACOW not supported");
|
|
|
|
return -EINVAL;
|
|
|
|
}
|
|
|
|
|
2020-11-10 14:26:10 +03:00
|
|
|
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 14:26:14 +03:00
|
|
|
|
|
|
|
static int sb_log_location(struct block_device *bdev, struct blk_zone *zones,
|
|
|
|
int rw, u64 *bytenr_ret)
|
|
|
|
{
|
|
|
|
u64 wp;
|
|
|
|
int ret;
|
|
|
|
|
|
|
|
if (zones[0].type == BLK_ZONE_TYPE_CONVENTIONAL) {
|
|
|
|
*bytenr_ret = zones[0].start << SECTOR_SHIFT;
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
ret = sb_write_pointer(bdev, zones, &wp);
|
|
|
|
if (ret != -ENOENT && ret < 0)
|
|
|
|
return ret;
|
|
|
|
|
|
|
|
if (rw == WRITE) {
|
|
|
|
struct blk_zone *reset = NULL;
|
|
|
|
|
|
|
|
if (wp == zones[0].start << SECTOR_SHIFT)
|
|
|
|
reset = &zones[0];
|
|
|
|
else if (wp == zones[1].start << SECTOR_SHIFT)
|
|
|
|
reset = &zones[1];
|
|
|
|
|
|
|
|
if (reset && reset->cond != BLK_ZONE_COND_EMPTY) {
|
|
|
|
ASSERT(reset->cond == BLK_ZONE_COND_FULL);
|
|
|
|
|
|
|
|
ret = blkdev_zone_mgmt(bdev, REQ_OP_ZONE_RESET,
|
|
|
|
reset->start, reset->len,
|
|
|
|
GFP_NOFS);
|
|
|
|
if (ret)
|
|
|
|
return ret;
|
|
|
|
|
|
|
|
reset->cond = BLK_ZONE_COND_EMPTY;
|
|
|
|
reset->wp = reset->start;
|
|
|
|
}
|
|
|
|
} else if (ret != -ENOENT) {
|
|
|
|
/* For READ, we want the precious one */
|
|
|
|
if (wp == zones[0].start << SECTOR_SHIFT)
|
|
|
|
wp = (zones[1].start + zones[1].len) << SECTOR_SHIFT;
|
|
|
|
wp -= BTRFS_SUPER_INFO_SIZE;
|
|
|
|
}
|
|
|
|
|
|
|
|
*bytenr_ret = wp;
|
|
|
|
return 0;
|
|
|
|
|
|
|
|
}
|
|
|
|
|
|
|
|
int btrfs_sb_log_location_bdev(struct block_device *bdev, int mirror, int rw,
|
|
|
|
u64 *bytenr_ret)
|
|
|
|
{
|
|
|
|
struct blk_zone zones[BTRFS_NR_SB_LOG_ZONES];
|
|
|
|
unsigned int zone_sectors;
|
|
|
|
u32 sb_zone;
|
|
|
|
int ret;
|
|
|
|
u8 zone_sectors_shift;
|
|
|
|
sector_t nr_sectors;
|
|
|
|
u32 nr_zones;
|
|
|
|
|
|
|
|
if (!bdev_is_zoned(bdev)) {
|
|
|
|
*bytenr_ret = btrfs_sb_offset(mirror);
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
ASSERT(rw == READ || rw == WRITE);
|
|
|
|
|
|
|
|
zone_sectors = bdev_zone_sectors(bdev);
|
|
|
|
if (!is_power_of_2(zone_sectors))
|
|
|
|
return -EINVAL;
|
|
|
|
zone_sectors_shift = ilog2(zone_sectors);
|
2020-12-16 23:57:51 +03:00
|
|
|
nr_sectors = bdev_nr_sectors(bdev);
|
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 14:26:14 +03:00
|
|
|
nr_zones = nr_sectors >> zone_sectors_shift;
|
|
|
|
|
|
|
|
sb_zone = sb_zone_number(zone_sectors_shift + SECTOR_SHIFT, mirror);
|
|
|
|
if (sb_zone + 1 >= nr_zones)
|
|
|
|
return -ENOENT;
|
|
|
|
|
|
|
|
ret = blkdev_report_zones(bdev, sb_zone << zone_sectors_shift,
|
|
|
|
BTRFS_NR_SB_LOG_ZONES, copy_zone_info_cb,
|
|
|
|
zones);
|
|
|
|
if (ret < 0)
|
|
|
|
return ret;
|
|
|
|
if (ret != BTRFS_NR_SB_LOG_ZONES)
|
|
|
|
return -EIO;
|
|
|
|
|
|
|
|
return sb_log_location(bdev, zones, rw, bytenr_ret);
|
|
|
|
}
|
|
|
|
|
|
|
|
int btrfs_sb_log_location(struct btrfs_device *device, int mirror, int rw,
|
|
|
|
u64 *bytenr_ret)
|
|
|
|
{
|
|
|
|
struct btrfs_zoned_device_info *zinfo = device->zone_info;
|
|
|
|
u32 zone_num;
|
|
|
|
|
2021-02-04 13:21:43 +03:00
|
|
|
/*
|
|
|
|
* For a zoned filesystem on a non-zoned block device, use the same
|
|
|
|
* super block locations as regular filesystem. Doing so, the super
|
|
|
|
* block can always be retrieved and the zoned flag of the volume
|
|
|
|
* detected from the super block information.
|
|
|
|
*/
|
|
|
|
if (!bdev_is_zoned(device->bdev)) {
|
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 14:26:14 +03:00
|
|
|
*bytenr_ret = btrfs_sb_offset(mirror);
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
zone_num = sb_zone_number(zinfo->zone_size_shift, mirror);
|
|
|
|
if (zone_num + 1 >= zinfo->nr_zones)
|
|
|
|
return -ENOENT;
|
|
|
|
|
|
|
|
return sb_log_location(device->bdev,
|
|
|
|
&zinfo->sb_zones[BTRFS_NR_SB_LOG_ZONES * mirror],
|
|
|
|
rw, bytenr_ret);
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline bool is_sb_log_zone(struct btrfs_zoned_device_info *zinfo,
|
|
|
|
int mirror)
|
|
|
|
{
|
|
|
|
u32 zone_num;
|
|
|
|
|
|
|
|
if (!zinfo)
|
|
|
|
return false;
|
|
|
|
|
|
|
|
zone_num = sb_zone_number(zinfo->zone_size_shift, mirror);
|
|
|
|
if (zone_num + 1 >= zinfo->nr_zones)
|
|
|
|
return false;
|
|
|
|
|
|
|
|
if (!test_bit(zone_num, zinfo->seq_zones))
|
|
|
|
return false;
|
|
|
|
|
|
|
|
return true;
|
|
|
|
}
|
|
|
|
|
|
|
|
void btrfs_advance_sb_log(struct btrfs_device *device, int mirror)
|
|
|
|
{
|
|
|
|
struct btrfs_zoned_device_info *zinfo = device->zone_info;
|
|
|
|
struct blk_zone *zone;
|
|
|
|
|
|
|
|
if (!is_sb_log_zone(zinfo, mirror))
|
|
|
|
return;
|
|
|
|
|
|
|
|
zone = &zinfo->sb_zones[BTRFS_NR_SB_LOG_ZONES * mirror];
|
|
|
|
if (zone->cond != BLK_ZONE_COND_FULL) {
|
|
|
|
if (zone->cond == BLK_ZONE_COND_EMPTY)
|
|
|
|
zone->cond = BLK_ZONE_COND_IMP_OPEN;
|
|
|
|
|
|
|
|
zone->wp += (BTRFS_SUPER_INFO_SIZE >> SECTOR_SHIFT);
|
|
|
|
|
|
|
|
if (zone->wp == zone->start + zone->len)
|
|
|
|
zone->cond = BLK_ZONE_COND_FULL;
|
|
|
|
|
|
|
|
return;
|
|
|
|
}
|
|
|
|
|
|
|
|
zone++;
|
|
|
|
ASSERT(zone->cond != BLK_ZONE_COND_FULL);
|
|
|
|
if (zone->cond == BLK_ZONE_COND_EMPTY)
|
|
|
|
zone->cond = BLK_ZONE_COND_IMP_OPEN;
|
|
|
|
|
|
|
|
zone->wp += (BTRFS_SUPER_INFO_SIZE >> SECTOR_SHIFT);
|
|
|
|
|
|
|
|
if (zone->wp == zone->start + zone->len)
|
|
|
|
zone->cond = BLK_ZONE_COND_FULL;
|
|
|
|
}
|
|
|
|
|
|
|
|
int btrfs_reset_sb_log_zones(struct block_device *bdev, int mirror)
|
|
|
|
{
|
|
|
|
sector_t zone_sectors;
|
|
|
|
sector_t nr_sectors;
|
|
|
|
u8 zone_sectors_shift;
|
|
|
|
u32 sb_zone;
|
|
|
|
u32 nr_zones;
|
|
|
|
|
|
|
|
zone_sectors = bdev_zone_sectors(bdev);
|
|
|
|
zone_sectors_shift = ilog2(zone_sectors);
|
2020-12-16 23:57:51 +03:00
|
|
|
nr_sectors = bdev_nr_sectors(bdev);
|
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 14:26:14 +03:00
|
|
|
nr_zones = nr_sectors >> zone_sectors_shift;
|
|
|
|
|
|
|
|
sb_zone = sb_zone_number(zone_sectors_shift + SECTOR_SHIFT, mirror);
|
|
|
|
if (sb_zone + 1 >= nr_zones)
|
|
|
|
return -ENOENT;
|
|
|
|
|
|
|
|
return blkdev_zone_mgmt(bdev, REQ_OP_ZONE_RESET,
|
|
|
|
sb_zone << zone_sectors_shift,
|
|
|
|
zone_sectors * BTRFS_NR_SB_LOG_ZONES, GFP_NOFS);
|
|
|
|
}
|
2021-02-04 13:21:48 +03:00
|
|
|
|
|
|
|
/**
|
|
|
|
* btrfs_find_allocatable_zones - find allocatable zones within a given region
|
|
|
|
*
|
|
|
|
* @device: the device to allocate a region on
|
|
|
|
* @hole_start: the position of the hole to allocate the region
|
|
|
|
* @num_bytes: size of wanted region
|
|
|
|
* @hole_end: the end of the hole
|
|
|
|
* @return: position of allocatable zones
|
|
|
|
*
|
|
|
|
* Allocatable region should not contain any superblock locations.
|
|
|
|
*/
|
|
|
|
u64 btrfs_find_allocatable_zones(struct btrfs_device *device, u64 hole_start,
|
|
|
|
u64 hole_end, u64 num_bytes)
|
|
|
|
{
|
|
|
|
struct btrfs_zoned_device_info *zinfo = device->zone_info;
|
|
|
|
const u8 shift = zinfo->zone_size_shift;
|
|
|
|
u64 nzones = num_bytes >> shift;
|
|
|
|
u64 pos = hole_start;
|
|
|
|
u64 begin, end;
|
|
|
|
bool have_sb;
|
|
|
|
int i;
|
|
|
|
|
|
|
|
ASSERT(IS_ALIGNED(hole_start, zinfo->zone_size));
|
|
|
|
ASSERT(IS_ALIGNED(num_bytes, zinfo->zone_size));
|
|
|
|
|
|
|
|
while (pos < hole_end) {
|
|
|
|
begin = pos >> shift;
|
|
|
|
end = begin + nzones;
|
|
|
|
|
|
|
|
if (end > zinfo->nr_zones)
|
|
|
|
return hole_end;
|
|
|
|
|
|
|
|
/* Check if zones in the region are all empty */
|
|
|
|
if (btrfs_dev_is_sequential(device, pos) &&
|
|
|
|
find_next_zero_bit(zinfo->empty_zones, end, begin) != end) {
|
|
|
|
pos += zinfo->zone_size;
|
|
|
|
continue;
|
|
|
|
}
|
|
|
|
|
|
|
|
have_sb = false;
|
|
|
|
for (i = 0; i < BTRFS_SUPER_MIRROR_MAX; i++) {
|
|
|
|
u32 sb_zone;
|
|
|
|
u64 sb_pos;
|
|
|
|
|
|
|
|
sb_zone = sb_zone_number(shift, i);
|
|
|
|
if (!(end <= sb_zone ||
|
|
|
|
sb_zone + BTRFS_NR_SB_LOG_ZONES <= begin)) {
|
|
|
|
have_sb = true;
|
|
|
|
pos = ((u64)sb_zone + BTRFS_NR_SB_LOG_ZONES) << shift;
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* We also need to exclude regular superblock positions */
|
|
|
|
sb_pos = btrfs_sb_offset(i);
|
|
|
|
if (!(pos + num_bytes <= sb_pos ||
|
|
|
|
sb_pos + BTRFS_SUPER_INFO_SIZE <= pos)) {
|
|
|
|
have_sb = true;
|
|
|
|
pos = ALIGN(sb_pos + BTRFS_SUPER_INFO_SIZE,
|
|
|
|
zinfo->zone_size);
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
if (!have_sb)
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
|
|
|
|
return pos;
|
|
|
|
}
|
|
|
|
|
|
|
|
int btrfs_reset_device_zone(struct btrfs_device *device, u64 physical,
|
|
|
|
u64 length, u64 *bytes)
|
|
|
|
{
|
|
|
|
int ret;
|
|
|
|
|
|
|
|
*bytes = 0;
|
|
|
|
ret = blkdev_zone_mgmt(device->bdev, REQ_OP_ZONE_RESET,
|
|
|
|
physical >> SECTOR_SHIFT, length >> SECTOR_SHIFT,
|
|
|
|
GFP_NOFS);
|
|
|
|
if (ret)
|
|
|
|
return ret;
|
|
|
|
|
|
|
|
*bytes = length;
|
|
|
|
while (length) {
|
|
|
|
btrfs_dev_set_zone_empty(device, physical);
|
|
|
|
physical += device->zone_info->zone_size;
|
|
|
|
length -= device->zone_info->zone_size;
|
|
|
|
}
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
int btrfs_ensure_empty_zones(struct btrfs_device *device, u64 start, u64 size)
|
|
|
|
{
|
|
|
|
struct btrfs_zoned_device_info *zinfo = device->zone_info;
|
|
|
|
const u8 shift = zinfo->zone_size_shift;
|
|
|
|
unsigned long begin = start >> shift;
|
|
|
|
unsigned long end = (start + size) >> shift;
|
|
|
|
u64 pos;
|
|
|
|
int ret;
|
|
|
|
|
|
|
|
ASSERT(IS_ALIGNED(start, zinfo->zone_size));
|
|
|
|
ASSERT(IS_ALIGNED(size, zinfo->zone_size));
|
|
|
|
|
|
|
|
if (end > zinfo->nr_zones)
|
|
|
|
return -ERANGE;
|
|
|
|
|
|
|
|
/* All the zones are conventional */
|
|
|
|
if (find_next_bit(zinfo->seq_zones, begin, end) == end)
|
|
|
|
return 0;
|
|
|
|
|
|
|
|
/* All the zones are sequential and empty */
|
|
|
|
if (find_next_zero_bit(zinfo->seq_zones, begin, end) == end &&
|
|
|
|
find_next_zero_bit(zinfo->empty_zones, begin, end) == end)
|
|
|
|
return 0;
|
|
|
|
|
|
|
|
for (pos = start; pos < start + size; pos += zinfo->zone_size) {
|
|
|
|
u64 reset_bytes;
|
|
|
|
|
|
|
|
if (!btrfs_dev_is_sequential(device, pos) ||
|
|
|
|
btrfs_dev_is_empty_zone(device, pos))
|
|
|
|
continue;
|
|
|
|
|
|
|
|
/* Free regions should be empty */
|
|
|
|
btrfs_warn_in_rcu(
|
|
|
|
device->fs_info,
|
|
|
|
"zoned: resetting device %s (devid %llu) zone %llu for allocation",
|
|
|
|
rcu_str_deref(device->name), device->devid, pos >> shift);
|
|
|
|
WARN_ON_ONCE(1);
|
|
|
|
|
|
|
|
ret = btrfs_reset_device_zone(device, pos, zinfo->zone_size,
|
|
|
|
&reset_bytes);
|
|
|
|
if (ret)
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
2021-02-04 13:21:50 +03:00
|
|
|
|
|
|
|
int btrfs_load_block_group_zone_info(struct btrfs_block_group *cache)
|
|
|
|
{
|
|
|
|
struct btrfs_fs_info *fs_info = cache->fs_info;
|
|
|
|
struct extent_map_tree *em_tree = &fs_info->mapping_tree;
|
|
|
|
struct extent_map *em;
|
|
|
|
struct map_lookup *map;
|
|
|
|
struct btrfs_device *device;
|
|
|
|
u64 logical = cache->start;
|
|
|
|
u64 length = cache->length;
|
|
|
|
u64 physical = 0;
|
|
|
|
int ret;
|
|
|
|
int i;
|
|
|
|
unsigned int nofs_flag;
|
|
|
|
u64 *alloc_offsets = NULL;
|
|
|
|
u32 num_sequential = 0, num_conventional = 0;
|
|
|
|
|
|
|
|
if (!btrfs_is_zoned(fs_info))
|
|
|
|
return 0;
|
|
|
|
|
|
|
|
/* Sanity check */
|
|
|
|
if (!IS_ALIGNED(length, fs_info->zone_size)) {
|
|
|
|
btrfs_err(fs_info,
|
|
|
|
"zoned: block group %llu len %llu unaligned to zone size %llu",
|
|
|
|
logical, length, fs_info->zone_size);
|
|
|
|
return -EIO;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* Get the chunk mapping */
|
|
|
|
read_lock(&em_tree->lock);
|
|
|
|
em = lookup_extent_mapping(em_tree, logical, length);
|
|
|
|
read_unlock(&em_tree->lock);
|
|
|
|
|
|
|
|
if (!em)
|
|
|
|
return -EINVAL;
|
|
|
|
|
|
|
|
map = em->map_lookup;
|
|
|
|
|
|
|
|
alloc_offsets = kcalloc(map->num_stripes, sizeof(*alloc_offsets), GFP_NOFS);
|
|
|
|
if (!alloc_offsets) {
|
|
|
|
free_extent_map(em);
|
|
|
|
return -ENOMEM;
|
|
|
|
}
|
|
|
|
|
|
|
|
for (i = 0; i < map->num_stripes; i++) {
|
|
|
|
bool is_sequential;
|
|
|
|
struct blk_zone zone;
|
|
|
|
|
|
|
|
device = map->stripes[i].dev;
|
|
|
|
physical = map->stripes[i].physical;
|
|
|
|
|
|
|
|
if (device->bdev == NULL) {
|
|
|
|
alloc_offsets[i] = WP_MISSING_DEV;
|
|
|
|
continue;
|
|
|
|
}
|
|
|
|
|
|
|
|
is_sequential = btrfs_dev_is_sequential(device, physical);
|
|
|
|
if (is_sequential)
|
|
|
|
num_sequential++;
|
|
|
|
else
|
|
|
|
num_conventional++;
|
|
|
|
|
|
|
|
if (!is_sequential) {
|
|
|
|
alloc_offsets[i] = WP_CONVENTIONAL;
|
|
|
|
continue;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* This zone will be used for allocation, so mark this zone
|
|
|
|
* non-empty.
|
|
|
|
*/
|
|
|
|
btrfs_dev_clear_zone_empty(device, physical);
|
|
|
|
|
|
|
|
/*
|
|
|
|
* The group is mapped to a sequential zone. Get the zone write
|
|
|
|
* pointer to determine the allocation offset within the zone.
|
|
|
|
*/
|
|
|
|
WARN_ON(!IS_ALIGNED(physical, fs_info->zone_size));
|
|
|
|
nofs_flag = memalloc_nofs_save();
|
|
|
|
ret = btrfs_get_dev_zone(device, physical, &zone);
|
|
|
|
memalloc_nofs_restore(nofs_flag);
|
|
|
|
if (ret == -EIO || ret == -EOPNOTSUPP) {
|
|
|
|
ret = 0;
|
|
|
|
alloc_offsets[i] = WP_MISSING_DEV;
|
|
|
|
continue;
|
|
|
|
} else if (ret) {
|
|
|
|
goto out;
|
|
|
|
}
|
|
|
|
|
|
|
|
switch (zone.cond) {
|
|
|
|
case BLK_ZONE_COND_OFFLINE:
|
|
|
|
case BLK_ZONE_COND_READONLY:
|
|
|
|
btrfs_err(fs_info,
|
|
|
|
"zoned: offline/readonly zone %llu on device %s (devid %llu)",
|
|
|
|
physical >> device->zone_info->zone_size_shift,
|
|
|
|
rcu_str_deref(device->name), device->devid);
|
|
|
|
alloc_offsets[i] = WP_MISSING_DEV;
|
|
|
|
break;
|
|
|
|
case BLK_ZONE_COND_EMPTY:
|
|
|
|
alloc_offsets[i] = 0;
|
|
|
|
break;
|
|
|
|
case BLK_ZONE_COND_FULL:
|
|
|
|
alloc_offsets[i] = fs_info->zone_size;
|
|
|
|
break;
|
|
|
|
default:
|
|
|
|
/* Partially used zone */
|
|
|
|
alloc_offsets[i] =
|
|
|
|
((zone.wp - zone.start) << SECTOR_SHIFT);
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
if (num_conventional > 0) {
|
|
|
|
/*
|
|
|
|
* Since conventional zones do not have a write pointer, we
|
|
|
|
* cannot determine alloc_offset from the pointer
|
|
|
|
*/
|
|
|
|
ret = -EINVAL;
|
|
|
|
goto out;
|
|
|
|
}
|
|
|
|
|
|
|
|
switch (map->type & BTRFS_BLOCK_GROUP_PROFILE_MASK) {
|
|
|
|
case 0: /* single */
|
|
|
|
cache->alloc_offset = alloc_offsets[0];
|
|
|
|
break;
|
|
|
|
case BTRFS_BLOCK_GROUP_DUP:
|
|
|
|
case BTRFS_BLOCK_GROUP_RAID1:
|
|
|
|
case BTRFS_BLOCK_GROUP_RAID0:
|
|
|
|
case BTRFS_BLOCK_GROUP_RAID10:
|
|
|
|
case BTRFS_BLOCK_GROUP_RAID5:
|
|
|
|
case BTRFS_BLOCK_GROUP_RAID6:
|
|
|
|
/* non-single profiles are not supported yet */
|
|
|
|
default:
|
|
|
|
btrfs_err(fs_info, "zoned: profile %s not yet supported",
|
|
|
|
btrfs_bg_type_to_raid_name(map->type));
|
|
|
|
ret = -EINVAL;
|
|
|
|
goto out;
|
|
|
|
}
|
|
|
|
|
|
|
|
out:
|
|
|
|
kfree(alloc_offsets);
|
|
|
|
free_extent_map(em);
|
|
|
|
|
|
|
|
return ret;
|
|
|
|
}
|