#include <linux/bitops.h>
#include <linux/slab.h>
#include <linux/blkdev.h>
#include <linux/sched/mm.h>
#include <linux/atomic.h>
#include <linux/vmalloc.h>
#include "ctree.h"
#include "volumes.h"
#include "zoned.h"
#include "rcu-string.h"
#include "disk-io.h"
#include "block-group.h"
#include "transaction.h"
#include "dev-replace.h"
#include "space-info.h"
#include "super.h"
#include "fs.h"
#include "accessors.h"
#include "bio.h"
#define BTRFS_REPORT_NR_ZONES 4096
#define WP_MISSING_DEV ((u64)-1)
#define WP_CONVENTIONAL ((u64)-2)
#define BTRFS_SB_LOG_PRIMARY_OFFSET (0ULL)
#define BTRFS_SB_LOG_FIRST_OFFSET (512ULL * SZ_1G)
#define BTRFS_SB_LOG_SECOND_OFFSET (4096ULL * SZ_1G)
#define BTRFS_SB_LOG_FIRST_SHIFT const_ilog2(BTRFS_SB_LOG_FIRST_OFFSET)
#define BTRFS_SB_LOG_SECOND_SHIFT const_ilog2(BTRFS_SB_LOG_SECOND_OFFSET)
#define BTRFS_NR_SB_LOG_ZONES 2
#define BTRFS_MIN_ACTIVE_ZONES (BTRFS_SUPER_MIRROR_MAX + 5)
#define BTRFS_MAX_ZONE_SIZE SZ_8G
#define BTRFS_MIN_ZONE_SIZE SZ_4M
#define SUPER_INFO_SECTORS ((u64)BTRFS_SUPER_INFO_SIZE >> SECTOR_SHIFT)
static void wait_eb_writebacks(struct btrfs_block_group *block_group);
static int do_zone_finish(struct btrfs_block_group *block_group, bool fully_written);
static inline bool sb_zone_is_full(const struct blk_zone *zone)
{
return (zone->cond == BLK_ZONE_COND_FULL) ||
(zone->wp + SUPER_INFO_SECTORS > zone->start + zone->capacity);
}
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;
}
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;
int i;
for (i = 0; i < BTRFS_NR_SB_LOG_ZONES; i++) {
ASSERT(zones[i].type != BLK_ZONE_TYPE_CONVENTIONAL);
empty[i] = (zones[i].cond == BLK_ZONE_COND_EMPTY);
full[i] = sb_zone_is_full(&zones[i]);
}
if (empty[0] && empty[1]) {
*wp_ret = zones[0].start << SECTOR_SHIFT;
return -ENOENT;
} else if (full[0] && full[1]) {
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 zone_end = (zones[i].start + zones[i].capacity) << SECTOR_SHIFT;
u64 bytenr = ALIGN_DOWN(zone_end, BTRFS_SUPER_INFO_SIZE) -
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 (btrfs_super_generation(super[0]) >
btrfs_super_generation(super[1]))
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;
}
static inline u32 sb_zone_number(int shift, int mirror)
{
u64 zone = U64_MAX;
ASSERT(mirror < BTRFS_SUPER_MIRROR_MAX);
switch (mirror) {
case 0: zone = 0; break;
case 1: zone = 1ULL << (BTRFS_SB_LOG_FIRST_SHIFT - shift); break;
case 2: zone = 1ULL << (BTRFS_SB_LOG_SECOND_SHIFT - shift); break;
}
ASSERT(zone <= U32_MAX);
return (u32)zone;
}
static inline sector_t zone_start_sector(u32 zone_number,
struct block_device *bdev)
{
return (sector_t)zone_number << ilog2(bdev_zone_sectors(bdev));
}
static inline u64 zone_start_physical(u32 zone_number,
struct btrfs_zoned_device_info *zone_info)
{
return (u64)zone_number << zone_info->zone_size_shift;
}
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;
}
static int btrfs_get_dev_zones(struct btrfs_device *device, u64 pos,
struct blk_zone *zones, unsigned int *nr_zones)
{
struct btrfs_zoned_device_info *zinfo = device->zone_info;
int ret;
if (!*nr_zones)
return 0;
if (!bdev_is_zoned(device->bdev)) {
ret = emulate_report_zones(device, pos, zones, *nr_zones);
*nr_zones = ret;
return 0;
}
if (zinfo->zone_cache) {
unsigned int i;
u32 zno;
ASSERT(IS_ALIGNED(pos, zinfo->zone_size));
zno = pos >> zinfo->zone_size_shift;
*nr_zones = min_t(u32, *nr_zones, zinfo->nr_zones - zno);
for (i = 0; i < *nr_zones; i++) {
struct blk_zone *zone_info;
zone_info = &zinfo->zone_cache[zno + i];
if (!zone_info->len)
break;
}
if (i == *nr_zones) {
memcpy(zones, zinfo->zone_cache + zno,
sizeof(*zinfo->zone_cache) * *nr_zones);
return 0;
}
}
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;
if (zinfo->zone_cache) {
u32 zno = pos >> zinfo->zone_size_shift;
memcpy(zinfo->zone_cache + zno, zones,
sizeof(*zinfo->zone_cache) * *nr_zones);
}
return 0;
}
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_leaf(root, path);
if (ret < 0)
goto out;
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;
}
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;
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) {
if (!device->bdev)
continue;
ret = btrfs_get_dev_zone_info(device, true);
if (ret)
break;
}
mutex_unlock(&fs_devices->device_list_mutex);
return ret;
}
int btrfs_get_dev_zone_info(struct btrfs_device *device, bool populate_cache)
{
struct btrfs_fs_info *fs_info = device->fs_info;
struct btrfs_zoned_device_info *zone_info = NULL;
struct block_device *bdev = device->bdev;
unsigned int max_active_zones;
unsigned int nactive;
sector_t nr_sectors;
sector_t sector = 0;
struct blk_zone *zones = NULL;
unsigned int i, nreported = 0, nr_zones;
sector_t zone_sectors;
char *model, *emulated;
int ret;
if (!btrfs_fs_incompat(fs_info, ZONED))
return 0;
if (device->zone_info)
return 0;
zone_info = kzalloc(sizeof(*zone_info), GFP_KERNEL);
if (!zone_info)
return -ENOMEM;
device->zone_info = zone_info;
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);
}
ASSERT(is_power_of_two_u64(zone_sectors));
zone_info->zone_size = zone_sectors << SECTOR_SHIFT;
if (zone_info->zone_size > BTRFS_MAX_ZONE_SIZE) {
btrfs_err_in_rcu(fs_info,
"zoned: %s: zone size %llu larger than supported maximum %llu",
rcu_str_deref(device->name),
zone_info->zone_size, BTRFS_MAX_ZONE_SIZE);
ret = -EINVAL;
goto out;
} else if (zone_info->zone_size < BTRFS_MIN_ZONE_SIZE) {
btrfs_err_in_rcu(fs_info,
"zoned: %s: zone size %llu smaller than supported minimum %u",
rcu_str_deref(device->name),
zone_info->zone_size, BTRFS_MIN_ZONE_SIZE);
ret = -EINVAL;
goto out;
}
nr_sectors = bdev_nr_sectors(bdev);
zone_info->zone_size_shift = ilog2(zone_info->zone_size);
zone_info->nr_zones = nr_sectors >> ilog2(zone_sectors);
if (!IS_ALIGNED(nr_sectors, zone_sectors))
zone_info->nr_zones++;
max_active_zones = bdev_max_active_zones(bdev);
if (max_active_zones && max_active_zones < BTRFS_MIN_ACTIVE_ZONES) {
btrfs_err_in_rcu(fs_info,
"zoned: %s: max active zones %u is too small, need at least %u active zones",
rcu_str_deref(device->name), max_active_zones,
BTRFS_MIN_ACTIVE_ZONES);
ret = -EINVAL;
goto out;
}
zone_info->max_active_zones = max_active_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;
}
zone_info->active_zones = bitmap_zalloc(zone_info->nr_zones, GFP_KERNEL);
if (!zone_info->active_zones) {
ret = -ENOMEM;
goto out;
}
zones = kvcalloc(BTRFS_REPORT_NR_ZONES, sizeof(struct blk_zone), GFP_KERNEL);
if (!zones) {
ret = -ENOMEM;
goto out;
}
if (populate_cache && bdev_is_zoned(device->bdev)) {
zone_info->zone_cache = vcalloc(zone_info->nr_zones,
sizeof(struct blk_zone));
if (!zone_info->zone_cache) {
btrfs_err_in_rcu(device->fs_info,
"zoned: failed to allocate zone cache for %s",
rcu_str_deref(device->name));
ret = -ENOMEM;
goto out;
}
}
nactive = 0;
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);
switch (zones[i].cond) {
case BLK_ZONE_COND_EMPTY:
__set_bit(nreported, zone_info->empty_zones);
break;
case BLK_ZONE_COND_IMP_OPEN:
case BLK_ZONE_COND_EXP_OPEN:
case BLK_ZONE_COND_CLOSED:
__set_bit(nreported, zone_info->active_zones);
nactive++;
break;
}
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;
}
if (max_active_zones) {
if (nactive > max_active_zones) {
btrfs_err_in_rcu(device->fs_info,
"zoned: %u active zones on %s exceeds max_active_zones %u",
nactive, rcu_str_deref(device->name),
max_active_zones);
ret = -EIO;
goto out;
}
atomic_set(&zone_info->active_zones_left,
max_active_zones - nactive);
set_bit(BTRFS_FS_ACTIVE_ZONE_TRACKING, &fs_info->flags);
}
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;
ret = btrfs_get_dev_zones(device,
zone_start_physical(sb_zone, zone_info),
&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 (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;
}
}
kvfree(zones);
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:
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);
return 0;
out:
kvfree(zones);
out_free_zone_info:
btrfs_destroy_dev_zone_info(device);
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->active_zones);
bitmap_free(zone_info->seq_zones);
bitmap_free(zone_info->empty_zones);
vfree(zone_info->zone_cache);
kfree(zone_info);
device->zone_info = NULL;
}
struct btrfs_zoned_device_info *btrfs_clone_dev_zone_info(struct btrfs_device *orig_dev)
{
struct btrfs_zoned_device_info *zone_info;
zone_info = kmemdup(orig_dev->zone_info, sizeof(*zone_info), GFP_KERNEL);
if (!zone_info)
return NULL;
zone_info->seq_zones = bitmap_zalloc(zone_info->nr_zones, GFP_KERNEL);
if (!zone_info->seq_zones)
goto out;
bitmap_copy(zone_info->seq_zones, orig_dev->zone_info->seq_zones,
zone_info->nr_zones);
zone_info->empty_zones = bitmap_zalloc(zone_info->nr_zones, GFP_KERNEL);
if (!zone_info->empty_zones)
goto out;
bitmap_copy(zone_info->empty_zones, orig_dev->zone_info->empty_zones,
zone_info->nr_zones);
zone_info->active_zones = bitmap_zalloc(zone_info->nr_zones, GFP_KERNEL);
if (!zone_info->active_zones)
goto out;
bitmap_copy(zone_info->active_zones, orig_dev->zone_info->active_zones,
zone_info->nr_zones);
zone_info->zone_cache = NULL;
return zone_info;
out:
bitmap_free(zone_info->seq_zones);
bitmap_free(zone_info->empty_zones);
bitmap_free(zone_info->active_zones);
kfree(zone_info);
return 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;
}
static int btrfs_check_for_zoned_device(struct btrfs_fs_info *fs_info)
{
struct btrfs_device *device;
list_for_each_entry(device, &fs_info->fs_devices->devices, dev_list) {
if (device->bdev &&
bdev_zoned_model(device->bdev) == BLK_ZONED_HM) {
btrfs_err(fs_info,
"zoned: mode not enabled but zoned device found: %pg",
device->bdev);
return -EINVAL;
}
}
return 0;
}
int btrfs_check_zoned_mode(struct btrfs_fs_info *fs_info)
{
struct queue_limits *lim = &fs_info->limits;
struct btrfs_device *device;
u64 zone_size = 0;
int ret;
if (!btrfs_fs_incompat(fs_info, ZONED))
return btrfs_check_for_zoned_device(fs_info);
blk_set_stacking_limits(lim);
list_for_each_entry(device, &fs_info->fs_devices->devices, dev_list) {
struct btrfs_zoned_device_info *zone_info = device->zone_info;
if (!device->bdev)
continue;
if (!zone_size) {
zone_size = zone_info->zone_size;
} else if (zone_info->zone_size != zone_size) {
btrfs_err(fs_info,
"zoned: unequal block device zone sizes: have %llu found %llu",
zone_info->zone_size, zone_size);
return -EINVAL;
}
if (bdev_is_zoned(device->bdev)) {
blk_stack_limits(lim,
&bdev_get_queue(device->bdev)->limits,
0);
}
}
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);
return -EINVAL;
}
if (btrfs_fs_incompat(fs_info, MIXED_GROUPS)) {
btrfs_err(fs_info, "zoned: mixed block groups not supported");
return -EINVAL;
}
fs_info->zone_size = zone_size;
fs_info->max_zone_append_size = ALIGN_DOWN(
min3((u64)lim->max_zone_append_sectors << SECTOR_SHIFT,
(u64)lim->max_sectors << SECTOR_SHIFT,
(u64)lim->max_segments << PAGE_SHIFT),
fs_info->sectorsize);
fs_info->fs_devices->chunk_alloc_policy = BTRFS_CHUNK_ALLOC_ZONED;
if (fs_info->max_zone_append_size < fs_info->max_extent_size)
fs_info->max_extent_size = fs_info->max_zone_append_size;
ret = btrfs_check_mountopts_zoned(fs_info);
if (ret)
return ret;
btrfs_info(fs_info, "zoned mode enabled with zone size %llu", zone_size);
return 0;
}
int btrfs_check_mountopts_zoned(struct btrfs_fs_info *info)
{
if (!btrfs_is_zoned(info))
return 0;
if (btrfs_test_opt(info, SPACE_CACHE)) {
btrfs_err(info, "zoned: space cache v1 is not supported");
return -EINVAL;
}
if (btrfs_test_opt(info, NODATACOW)) {
btrfs_err(info, "zoned: NODATACOW not supported");
return -EINVAL;
}
btrfs_clear_and_info(info, DISCARD_ASYNC,
"zoned: async discard ignored and disabled for zoned mode");
return 0;
}
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(sb_zone_is_full(reset));
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) {
u64 zone_end = 0;
if (wp == zones[0].start << SECTOR_SHIFT)
zone_end = zones[1].start + zones[1].capacity;
else if (wp == zones[1].start << SECTOR_SHIFT)
zone_end = zones[0].start + zones[0].capacity;
if (zone_end)
wp = ALIGN_DOWN(zone_end << SECTOR_SHIFT,
BTRFS_SUPER_INFO_SIZE);
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];
sector_t 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);
nr_sectors = bdev_nr_sectors(bdev);
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, zone_start_sector(sb_zone, bdev),
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;
if (!bdev_is_zoned(device->bdev)) {
*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;
}
int btrfs_advance_sb_log(struct btrfs_device *device, int mirror)
{
struct btrfs_zoned_device_info *zinfo = device->zone_info;
struct blk_zone *zone;
int i;
if (!is_sb_log_zone(zinfo, mirror))
return 0;
zone = &zinfo->sb_zones[BTRFS_NR_SB_LOG_ZONES * mirror];
for (i = 0; i < BTRFS_NR_SB_LOG_ZONES; i++) {
if (zone->cond == BLK_ZONE_COND_FULL) {
zone++;
continue;
}
if (zone->cond == BLK_ZONE_COND_EMPTY)
zone->cond = BLK_ZONE_COND_IMP_OPEN;
zone->wp += SUPER_INFO_SECTORS;
if (sb_zone_is_full(zone)) {
if (zone->wp != zone->start + zone->capacity) {
int ret;
ret = blkdev_zone_mgmt(device->bdev,
REQ_OP_ZONE_FINISH, zone->start,
zone->len, GFP_NOFS);
if (ret)
return ret;
}
zone->wp = zone->start + zone->len;
zone->cond = BLK_ZONE_COND_FULL;
}
return 0;
}
ASSERT(0);
return -EIO;
}
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);
nr_sectors = bdev_nr_sectors(bdev);
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,
zone_start_sector(sb_zone, bdev),
zone_sectors * BTRFS_NR_SB_LOG_ZONES, GFP_NOFS);
}
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;
if (btrfs_dev_is_sequential(device, pos) &&
!bitmap_test_range_all_set(zinfo->empty_zones, begin, nzones)) {
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 = zone_start_physical(
sb_zone + BTRFS_NR_SB_LOG_ZONES, zinfo);
break;
}
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;
}
static bool btrfs_dev_set_active_zone(struct btrfs_device *device, u64 pos)
{
struct btrfs_zoned_device_info *zone_info = device->zone_info;
unsigned int zno = (pos >> zone_info->zone_size_shift);
if (zone_info->max_active_zones == 0)
return true;
if (!test_bit(zno, zone_info->active_zones)) {
if (atomic_dec_if_positive(&zone_info->active_zones_left) < 0)
return false;
if (test_and_set_bit(zno, zone_info->active_zones)) {
atomic_inc(&zone_info->active_zones_left);
}
}
return true;
}
static void btrfs_dev_clear_active_zone(struct btrfs_device *device, u64 pos)
{
struct btrfs_zoned_device_info *zone_info = device->zone_info;
unsigned int zno = (pos >> zone_info->zone_size_shift);
if (zone_info->max_active_zones == 0)
return;
if (test_and_clear_bit(zno, zone_info->active_zones))
atomic_inc(&zone_info->active_zones_left);
}
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);
btrfs_dev_clear_active_zone(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 nbits = size >> shift;
u64 pos;
int ret;
ASSERT(IS_ALIGNED(start, zinfo->zone_size));
ASSERT(IS_ALIGNED(size, zinfo->zone_size));
if (begin + nbits > zinfo->nr_zones)
return -ERANGE;
if (bitmap_test_range_all_zero(zinfo->seq_zones, begin, nbits))
return 0;
if (bitmap_test_range_all_set(zinfo->seq_zones, begin, nbits) &&
bitmap_test_range_all_set(zinfo->empty_zones, begin, nbits))
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;
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;
}
static int calculate_alloc_pointer(struct btrfs_block_group *cache,
u64 *offset_ret, bool new)
{
struct btrfs_fs_info *fs_info = cache->fs_info;
struct btrfs_root *root;
struct btrfs_path *path;
struct btrfs_key key;
struct btrfs_key found_key;
int ret;
u64 length;
if (new) {
*offset_ret = 0;
return 0;
}
path = btrfs_alloc_path();
if (!path)
return -ENOMEM;
key.objectid = cache->start + cache->length;
key.type = 0;
key.offset = 0;
root = btrfs_extent_root(fs_info, key.objectid);
ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
if (!ret)
ret = -EUCLEAN;
if (ret < 0)
goto out;
ret = btrfs_previous_extent_item(root, path, cache->start);
if (ret) {
if (ret == 1) {
ret = 0;
*offset_ret = 0;
}
goto out;
}
btrfs_item_key_to_cpu(path->nodes[0], &found_key, path->slots[0]);
if (found_key.type == BTRFS_EXTENT_ITEM_KEY)
length = found_key.offset;
else
length = fs_info->nodesize;
if (!(found_key.objectid >= cache->start &&
found_key.objectid + length <= cache->start + cache->length)) {
ret = -EUCLEAN;
goto out;
}
*offset_ret = found_key.objectid + length - cache->start;
ret = 0;
out:
btrfs_free_path(path);
return ret;
}
int btrfs_load_block_group_zone_info(struct btrfs_block_group *cache, bool new)
{
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;
int ret;
int i;
unsigned int nofs_flag;
u64 *alloc_offsets = NULL;
u64 *caps = NULL;
u64 *physical = NULL;
unsigned long *active = NULL;
u64 last_alloc = 0;
u32 num_sequential = 0, num_conventional = 0;
if (!btrfs_is_zoned(fs_info))
return 0;
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;
}
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;
cache->physical_map = kmemdup(map, map_lookup_size(map->num_stripes), GFP_NOFS);
if (!cache->physical_map) {
ret = -ENOMEM;
goto out;
}
alloc_offsets = kcalloc(map->num_stripes, sizeof(*alloc_offsets), GFP_NOFS);
if (!alloc_offsets) {
ret = -ENOMEM;
goto out;
}
caps = kcalloc(map->num_stripes, sizeof(*caps), GFP_NOFS);
if (!caps) {
ret = -ENOMEM;
goto out;
}
physical = kcalloc(map->num_stripes, sizeof(*physical), GFP_NOFS);
if (!physical) {
ret = -ENOMEM;
goto out;
}
active = bitmap_zalloc(map->num_stripes, GFP_NOFS);
if (!active) {
ret = -ENOMEM;
goto out;
}
for (i = 0; i < map->num_stripes; i++) {
bool is_sequential;
struct blk_zone zone;
struct btrfs_dev_replace *dev_replace = &fs_info->dev_replace;
int dev_replace_is_ongoing = 0;
device = map->stripes[i].dev;
physical[i] = map->stripes[i].physical;
if (device->bdev == NULL) {
alloc_offsets[i] = WP_MISSING_DEV;
continue;
}
is_sequential = btrfs_dev_is_sequential(device, physical[i]);
if (is_sequential)
num_sequential++;
else
num_conventional++;
if (!device->zone_info->max_active_zones)
__set_bit(i, active);
if (!is_sequential) {
alloc_offsets[i] = WP_CONVENTIONAL;
continue;
}
btrfs_dev_clear_zone_empty(device, physical[i]);
down_read(&dev_replace->rwsem);
dev_replace_is_ongoing = btrfs_dev_replace_is_ongoing(dev_replace);
if (dev_replace_is_ongoing && dev_replace->tgtdev != NULL)
btrfs_dev_clear_zone_empty(dev_replace->tgtdev, physical[i]);
up_read(&dev_replace->rwsem);
WARN_ON(!IS_ALIGNED(physical[i], fs_info->zone_size));
nofs_flag = memalloc_nofs_save();
ret = btrfs_get_dev_zone(device, physical[i], &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;
}
if (zone.type == BLK_ZONE_TYPE_CONVENTIONAL) {
btrfs_err_in_rcu(fs_info,
"zoned: unexpected conventional zone %llu on device %s (devid %llu)",
zone.start << SECTOR_SHIFT,
rcu_str_deref(device->name), device->devid);
ret = -EIO;
goto out;
}
caps[i] = (zone.capacity << SECTOR_SHIFT);
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[i] >> 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] = caps[i];
break;
default:
alloc_offsets[i] =
((zone.wp - zone.start) << SECTOR_SHIFT);
__set_bit(i, active);
break;
}
}
if (num_sequential > 0)
set_bit(BLOCK_GROUP_FLAG_SEQUENTIAL_ZONE, &cache->runtime_flags);
if (num_conventional > 0) {
cache->zone_capacity = cache->length;
ret = calculate_alloc_pointer(cache, &last_alloc, new);
if (ret) {
btrfs_err(fs_info,
"zoned: failed to determine allocation offset of bg %llu",
cache->start);
goto out;
} else if (map->num_stripes == num_conventional) {
cache->alloc_offset = last_alloc;
set_bit(BLOCK_GROUP_FLAG_ZONE_IS_ACTIVE, &cache->runtime_flags);
goto out;
}
}
switch (map->type & BTRFS_BLOCK_GROUP_PROFILE_MASK) {
case 0:
if (alloc_offsets[0] == WP_MISSING_DEV) {
btrfs_err(fs_info,
"zoned: cannot recover write pointer for zone %llu",
physical[0]);
ret = -EIO;
goto out;
}
cache->alloc_offset = alloc_offsets[0];
cache->zone_capacity = caps[0];
if (test_bit(0, active))
set_bit(BLOCK_GROUP_FLAG_ZONE_IS_ACTIVE, &cache->runtime_flags);
break;
case BTRFS_BLOCK_GROUP_DUP:
if (map->type & BTRFS_BLOCK_GROUP_DATA) {
btrfs_err(fs_info, "zoned: profile DUP not yet supported on data bg");
ret = -EINVAL;
goto out;
}
if (alloc_offsets[0] == WP_MISSING_DEV) {
btrfs_err(fs_info,
"zoned: cannot recover write pointer for zone %llu",
physical[0]);
ret = -EIO;
goto out;
}
if (alloc_offsets[1] == WP_MISSING_DEV) {
btrfs_err(fs_info,
"zoned: cannot recover write pointer for zone %llu",
physical[1]);
ret = -EIO;
goto out;
}
if (alloc_offsets[0] != alloc_offsets[1]) {
btrfs_err(fs_info,
"zoned: write pointer offset mismatch of zones in DUP profile");
ret = -EIO;
goto out;
}
if (test_bit(0, active) != test_bit(1, active)) {
if (!btrfs_zone_activate(cache)) {
ret = -EIO;
goto out;
}
} else {
if (test_bit(0, active))
set_bit(BLOCK_GROUP_FLAG_ZONE_IS_ACTIVE,
&cache->runtime_flags);
}
cache->alloc_offset = alloc_offsets[0];
cache->zone_capacity = min(caps[0], caps[1]);
break;
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:
default:
btrfs_err(fs_info, "zoned: profile %s not yet supported",
btrfs_bg_type_to_raid_name(map->type));
ret = -EINVAL;
goto out;
}
out:
if (cache->alloc_offset > fs_info->zone_size) {
btrfs_err(fs_info,
"zoned: invalid write pointer %llu in block group %llu",
cache->alloc_offset, cache->start);
ret = -EIO;
}
if (cache->alloc_offset > cache->zone_capacity) {
btrfs_err(fs_info,
"zoned: invalid write pointer %llu (larger than zone capacity %llu) in block group %llu",
cache->alloc_offset, cache->zone_capacity,
cache->start);
ret = -EIO;
}
if (!ret && num_conventional && last_alloc > cache->alloc_offset) {
btrfs_err(fs_info,
"zoned: got wrong write pointer in BG %llu: %llu > %llu",
logical, last_alloc, cache->alloc_offset);
ret = -EIO;
}
if (!ret) {
cache->meta_write_pointer = cache->alloc_offset + cache->start;
if (test_bit(BLOCK_GROUP_FLAG_ZONE_IS_ACTIVE, &cache->runtime_flags)) {
btrfs_get_block_group(cache);
spin_lock(&fs_info->zone_active_bgs_lock);
list_add_tail(&cache->active_bg_list,
&fs_info->zone_active_bgs);
spin_unlock(&fs_info->zone_active_bgs_lock);
}
} else {
kfree(cache->physical_map);
cache->physical_map = NULL;
}
bitmap_free(active);
kfree(physical);
kfree(caps);
kfree(alloc_offsets);
free_extent_map(em);
return ret;
}
void btrfs_calc_zone_unusable(struct btrfs_block_group *cache)
{
u64 unusable, free;
if (!btrfs_is_zoned(cache->fs_info))
return;
WARN_ON(cache->bytes_super != 0);
unusable = (cache->alloc_offset - cache->used) +
(cache->length - cache->zone_capacity);
free = cache->zone_capacity - cache->alloc_offset;
cache->cached = BTRFS_CACHE_FINISHED;
cache->free_space_ctl->free_space = free;
cache->zone_unusable = unusable;
}
void btrfs_redirty_list_add(struct btrfs_transaction *trans,
struct extent_buffer *eb)
{
if (!btrfs_is_zoned(eb->fs_info) ||
btrfs_header_flag(eb, BTRFS_HEADER_FLAG_WRITTEN))
return;
ASSERT(!test_bit(EXTENT_BUFFER_DIRTY, &eb->bflags));
memzero_extent_buffer(eb, 0, eb->len);
set_bit(EXTENT_BUFFER_NO_CHECK, &eb->bflags);
set_extent_buffer_dirty(eb);
set_extent_bit(&trans->dirty_pages, eb->start, eb->start + eb->len - 1,
EXTENT_DIRTY | EXTENT_NOWAIT, NULL);
}
bool btrfs_use_zone_append(struct btrfs_bio *bbio)
{
u64 start = (bbio->bio.bi_iter.bi_sector << SECTOR_SHIFT);
struct btrfs_inode *inode = bbio->inode;
struct btrfs_fs_info *fs_info = bbio->fs_info;
struct btrfs_block_group *cache;
bool ret = false;
if (!btrfs_is_zoned(fs_info))
return false;
if (!inode || !is_data_inode(&inode->vfs_inode))
return false;
if (btrfs_op(&bbio->bio) != BTRFS_MAP_WRITE)
return false;
if (btrfs_is_data_reloc_root(inode->root))
return false;
cache = btrfs_lookup_block_group(fs_info, start);
ASSERT(cache);
if (!cache)
return false;
ret = !!test_bit(BLOCK_GROUP_FLAG_SEQUENTIAL_ZONE, &cache->runtime_flags);
btrfs_put_block_group(cache);
return ret;
}
void btrfs_record_physical_zoned(struct btrfs_bio *bbio)
{
const u64 physical = bbio->bio.bi_iter.bi_sector << SECTOR_SHIFT;
struct btrfs_ordered_sum *sum = bbio->sums;
if (physical < bbio->orig_physical)
sum->logical -= bbio->orig_physical - physical;
else
sum->logical += physical - bbio->orig_physical;
}
static void btrfs_rewrite_logical_zoned(struct btrfs_ordered_extent *ordered,
u64 logical)
{
struct extent_map_tree *em_tree = &BTRFS_I(ordered->inode)->extent_tree;
struct extent_map *em;
ordered->disk_bytenr = logical;
write_lock(&em_tree->lock);
em = search_extent_mapping(em_tree, ordered->file_offset,
ordered->num_bytes);
em->block_start = logical;
free_extent_map(em);
write_unlock(&em_tree->lock);
}
static bool btrfs_zoned_split_ordered(struct btrfs_ordered_extent *ordered,
u64 logical, u64 len)
{
struct btrfs_ordered_extent *new;
if (!test_bit(BTRFS_ORDERED_NOCOW, &ordered->flags) &&
split_extent_map(BTRFS_I(ordered->inode), ordered->file_offset,
ordered->num_bytes, len, logical))
return false;
new = btrfs_split_ordered_extent(ordered, len);
if (IS_ERR(new))
return false;
new->disk_bytenr = logical;
btrfs_finish_one_ordered(new);
return true;
}
void btrfs_finish_ordered_zoned(struct btrfs_ordered_extent *ordered)
{
struct btrfs_inode *inode = BTRFS_I(ordered->inode);
struct btrfs_fs_info *fs_info = inode->root->fs_info;
struct btrfs_ordered_sum *sum;
u64 logical, len;
if (test_bit(BTRFS_ORDERED_PREALLOC, &ordered->flags))
return;
ASSERT(!list_empty(&ordered->list));
sum = list_first_entry(&ordered->list, struct btrfs_ordered_sum, list);
logical = sum->logical;
len = sum->len;
while (len < ordered->disk_num_bytes) {
sum = list_next_entry(sum, list);
if (sum->logical == logical + len) {
len += sum->len;
continue;
}
if (!btrfs_zoned_split_ordered(ordered, logical, len)) {
set_bit(BTRFS_ORDERED_IOERR, &ordered->flags);
btrfs_err(fs_info, "failed to split ordered extent");
goto out;
}
logical = sum->logical;
len = sum->len;
}
if (ordered->disk_bytenr != logical)
btrfs_rewrite_logical_zoned(ordered, logical);
out:
if ((inode->flags & BTRFS_INODE_NODATASUM) ||
test_bit(BTRFS_FS_STATE_NO_CSUMS, &fs_info->fs_state)) {
while ((sum = list_first_entry_or_null(&ordered->list,
typeof(*sum), list))) {
list_del(&sum->list);
kfree(sum);
}
}
}
static bool check_bg_is_active(struct btrfs_eb_write_context *ctx,
struct btrfs_block_group **active_bg)
{
const struct writeback_control *wbc = ctx->wbc;
struct btrfs_block_group *block_group = ctx->zoned_bg;
struct btrfs_fs_info *fs_info = block_group->fs_info;
if (test_bit(BLOCK_GROUP_FLAG_ZONE_IS_ACTIVE, &block_group->runtime_flags))
return true;
if (fs_info->treelog_bg == block_group->start) {
if (!btrfs_zone_activate(block_group)) {
int ret_fin = btrfs_zone_finish_one_bg(fs_info);
if (ret_fin != 1 || !btrfs_zone_activate(block_group))
return false;
}
} else if (*active_bg != block_group) {
struct btrfs_block_group *tgt = *active_bg;
lockdep_assert_held(&fs_info->zoned_meta_io_lock);
if (tgt) {
if (tgt->meta_write_pointer < tgt->start + tgt->alloc_offset) {
if (wbc->sync_mode == WB_SYNC_NONE ||
(wbc->sync_mode == WB_SYNC_ALL && !wbc->for_sync))
return false;
}
btrfs_zoned_meta_io_unlock(fs_info);
wait_eb_writebacks(tgt);
do_zone_finish(tgt, true);
btrfs_zoned_meta_io_lock(fs_info);
if (*active_bg == tgt) {
btrfs_put_block_group(tgt);
*active_bg = NULL;
}
}
if (!btrfs_zone_activate(block_group))
return false;
if (*active_bg != block_group) {
ASSERT(*active_bg == NULL);
*active_bg = block_group;
btrfs_get_block_group(block_group);
}
}
return true;
}
int btrfs_check_meta_write_pointer(struct btrfs_fs_info *fs_info,
struct btrfs_eb_write_context *ctx)
{
const struct writeback_control *wbc = ctx->wbc;
const struct extent_buffer *eb = ctx->eb;
struct btrfs_block_group *block_group = ctx->zoned_bg;
if (!btrfs_is_zoned(fs_info))
return 0;
if (block_group) {
if (block_group->start > eb->start ||
block_group->start + block_group->length <= eb->start) {
btrfs_put_block_group(block_group);
block_group = NULL;
ctx->zoned_bg = NULL;
}
}
if (!block_group) {
block_group = btrfs_lookup_block_group(fs_info, eb->start);
if (!block_group)
return 0;
ctx->zoned_bg = block_group;
}
if (block_group->meta_write_pointer == eb->start) {
struct btrfs_block_group **tgt;
if (!test_bit(BTRFS_FS_ACTIVE_ZONE_TRACKING, &fs_info->flags))
return 0;
if (block_group->flags & BTRFS_BLOCK_GROUP_SYSTEM)
tgt = &fs_info->active_system_bg;
else
tgt = &fs_info->active_meta_bg;
if (check_bg_is_active(ctx, tgt))
return 0;
}
if (block_group->meta_write_pointer > eb->start)
return -EBUSY;
if (wbc->sync_mode == WB_SYNC_ALL && !wbc->for_sync)
return -EAGAIN;
return -EBUSY;
}
int btrfs_zoned_issue_zeroout(struct btrfs_device *device, u64 physical, u64 length)
{
if (!btrfs_dev_is_sequential(device, physical))
return -EOPNOTSUPP;
return blkdev_issue_zeroout(device->bdev, physical >> SECTOR_SHIFT,
length >> SECTOR_SHIFT, GFP_NOFS, 0);
}
static int read_zone_info(struct btrfs_fs_info *fs_info, u64 logical,
struct blk_zone *zone)
{
struct btrfs_io_context *bioc = NULL;
u64 mapped_length = PAGE_SIZE;
unsigned int nofs_flag;
int nmirrors;
int i, ret;
ret = btrfs_map_block(fs_info, BTRFS_MAP_GET_READ_MIRRORS, logical,
&mapped_length, &bioc, NULL, NULL, 1);
if (ret || !bioc || mapped_length < PAGE_SIZE) {
ret = -EIO;
goto out_put_bioc;
}
if (bioc->map_type & BTRFS_BLOCK_GROUP_RAID56_MASK) {
ret = -EINVAL;
goto out_put_bioc;
}
nofs_flag = memalloc_nofs_save();
nmirrors = (int)bioc->num_stripes;
for (i = 0; i < nmirrors; i++) {
u64 physical = bioc->stripes[i].physical;
struct btrfs_device *dev = bioc->stripes[i].dev;
if (!dev->bdev)
continue;
ret = btrfs_get_dev_zone(dev, physical, zone);
if (ret == -EIO || ret == -EOPNOTSUPP)
continue;
break;
}
memalloc_nofs_restore(nofs_flag);
out_put_bioc:
btrfs_put_bioc(bioc);
return ret;
}
int btrfs_sync_zone_write_pointer(struct btrfs_device *tgt_dev, u64 logical,
u64 physical_start, u64 physical_pos)
{
struct btrfs_fs_info *fs_info = tgt_dev->fs_info;
struct blk_zone zone;
u64 length;
u64 wp;
int ret;
if (!btrfs_dev_is_sequential(tgt_dev, physical_pos))
return 0;
ret = read_zone_info(fs_info, logical, &zone);
if (ret)
return ret;
wp = physical_start + ((zone.wp - zone.start) << SECTOR_SHIFT);
if (physical_pos == wp)
return 0;
if (physical_pos > wp)
return -EUCLEAN;
length = wp - physical_pos;
return btrfs_zoned_issue_zeroout(tgt_dev, physical_pos, length);
}
bool btrfs_zone_activate(struct btrfs_block_group *block_group)
{
struct btrfs_fs_info *fs_info = block_group->fs_info;
struct map_lookup *map;
struct btrfs_device *device;
u64 physical;
const bool is_data = (block_group->flags & BTRFS_BLOCK_GROUP_DATA);
bool ret;
int i;
if (!btrfs_is_zoned(block_group->fs_info))
return true;
map = block_group->physical_map;
spin_lock(&block_group->lock);
if (test_bit(BLOCK_GROUP_FLAG_ZONE_IS_ACTIVE, &block_group->runtime_flags)) {
ret = true;
goto out_unlock;
}
if (btrfs_zoned_bg_is_full(block_group)) {
ret = false;
goto out_unlock;
}
spin_lock(&fs_info->zone_active_bgs_lock);
for (i = 0; i < map->num_stripes; i++) {
struct btrfs_zoned_device_info *zinfo;
int reserved = 0;
device = map->stripes[i].dev;
physical = map->stripes[i].physical;
zinfo = device->zone_info;
if (zinfo->max_active_zones == 0)
continue;
if (is_data)
reserved = zinfo->reserved_active_zones;
if (atomic_read(&zinfo->active_zones_left) <= reserved) {
ret = false;
spin_unlock(&fs_info->zone_active_bgs_lock);
goto out_unlock;
}
if (!btrfs_dev_set_active_zone(device, physical)) {
ret = false;
spin_unlock(&fs_info->zone_active_bgs_lock);
goto out_unlock;
}
if (!is_data)
zinfo->reserved_active_zones--;
}
spin_unlock(&fs_info->zone_active_bgs_lock);
set_bit(BLOCK_GROUP_FLAG_ZONE_IS_ACTIVE, &block_group->runtime_flags);
spin_unlock(&block_group->lock);
btrfs_get_block_group(block_group);
spin_lock(&fs_info->zone_active_bgs_lock);
list_add_tail(&block_group->active_bg_list, &fs_info->zone_active_bgs);
spin_unlock(&fs_info->zone_active_bgs_lock);
return true;
out_unlock:
spin_unlock(&block_group->lock);
return ret;
}
static void wait_eb_writebacks(struct btrfs_block_group *block_group)
{
struct btrfs_fs_info *fs_info = block_group->fs_info;
const u64 end = block_group->start + block_group->length;
struct radix_tree_iter iter;
struct extent_buffer *eb;
void __rcu **slot;
rcu_read_lock();
radix_tree_for_each_slot(slot, &fs_info->buffer_radix, &iter,
block_group->start >> fs_info->sectorsize_bits) {
eb = radix_tree_deref_slot(slot);
if (!eb)
continue;
if (radix_tree_deref_retry(eb)) {
slot = radix_tree_iter_retry(&iter);
continue;
}
if (eb->start < block_group->start)
continue;
if (eb->start >= end)
break;
slot = radix_tree_iter_resume(slot, &iter);
rcu_read_unlock();
wait_on_extent_buffer_writeback(eb);
rcu_read_lock();
}
rcu_read_unlock();
}
static int do_zone_finish(struct btrfs_block_group *block_group, bool fully_written)
{
struct btrfs_fs_info *fs_info = block_group->fs_info;
struct map_lookup *map;
const bool is_metadata = (block_group->flags &
(BTRFS_BLOCK_GROUP_METADATA | BTRFS_BLOCK_GROUP_SYSTEM));
int ret = 0;
int i;
spin_lock(&block_group->lock);
if (!test_bit(BLOCK_GROUP_FLAG_ZONE_IS_ACTIVE, &block_group->runtime_flags)) {
spin_unlock(&block_group->lock);
return 0;
}
if (is_metadata &&
block_group->start + block_group->alloc_offset > block_group->meta_write_pointer) {
spin_unlock(&block_group->lock);
return -EAGAIN;
}
if (!fully_written) {
if (test_bit(BLOCK_GROUP_FLAG_ZONED_DATA_RELOC, &block_group->runtime_flags)) {
spin_unlock(&block_group->lock);
return -EAGAIN;
}
spin_unlock(&block_group->lock);
ret = btrfs_inc_block_group_ro(block_group, false);
if (ret)
return ret;
btrfs_wait_block_group_reservations(block_group);
btrfs_wait_ordered_roots(fs_info, U64_MAX, block_group->start,
block_group->length);
if (is_metadata)
wait_eb_writebacks(block_group);
spin_lock(&block_group->lock);
if (!test_bit(BLOCK_GROUP_FLAG_ZONE_IS_ACTIVE,
&block_group->runtime_flags)) {
spin_unlock(&block_group->lock);
btrfs_dec_block_group_ro(block_group);
return 0;
}
if (block_group->reserved ||
test_bit(BLOCK_GROUP_FLAG_ZONED_DATA_RELOC,
&block_group->runtime_flags)) {
spin_unlock(&block_group->lock);
btrfs_dec_block_group_ro(block_group);
return -EAGAIN;
}
}
clear_bit(BLOCK_GROUP_FLAG_ZONE_IS_ACTIVE, &block_group->runtime_flags);
block_group->alloc_offset = block_group->zone_capacity;
if (block_group->flags & (BTRFS_BLOCK_GROUP_METADATA | BTRFS_BLOCK_GROUP_SYSTEM))
block_group->meta_write_pointer = block_group->start +
block_group->zone_capacity;
block_group->free_space_ctl->free_space = 0;
btrfs_clear_treelog_bg(block_group);
btrfs_clear_data_reloc_bg(block_group);
spin_unlock(&block_group->lock);
map = block_group->physical_map;
for (i = 0; i < map->num_stripes; i++) {
struct btrfs_device *device = map->stripes[i].dev;
const u64 physical = map->stripes[i].physical;
struct btrfs_zoned_device_info *zinfo = device->zone_info;
if (zinfo->max_active_zones == 0)
continue;
ret = blkdev_zone_mgmt(device->bdev, REQ_OP_ZONE_FINISH,
physical >> SECTOR_SHIFT,
zinfo->zone_size >> SECTOR_SHIFT,
GFP_NOFS);
if (ret)
return ret;
if (!(block_group->flags & BTRFS_BLOCK_GROUP_DATA))
zinfo->reserved_active_zones++;
btrfs_dev_clear_active_zone(device, physical);
}
if (!fully_written)
btrfs_dec_block_group_ro(block_group);
spin_lock(&fs_info->zone_active_bgs_lock);
ASSERT(!list_empty(&block_group->active_bg_list));
list_del_init(&block_group->active_bg_list);
spin_unlock(&fs_info->zone_active_bgs_lock);
btrfs_put_block_group(block_group);
clear_and_wake_up_bit(BTRFS_FS_NEED_ZONE_FINISH, &fs_info->flags);
return 0;
}
int btrfs_zone_finish(struct btrfs_block_group *block_group)
{
if (!btrfs_is_zoned(block_group->fs_info))
return 0;
return do_zone_finish(block_group, false);
}
bool btrfs_can_activate_zone(struct btrfs_fs_devices *fs_devices, u64 flags)
{
struct btrfs_fs_info *fs_info = fs_devices->fs_info;
struct btrfs_device *device;
bool ret = false;
if (!btrfs_is_zoned(fs_info))
return true;
mutex_lock(&fs_info->chunk_mutex);
spin_lock(&fs_info->zone_active_bgs_lock);
list_for_each_entry(device, &fs_devices->alloc_list, dev_alloc_list) {
struct btrfs_zoned_device_info *zinfo = device->zone_info;
int reserved = 0;
if (!device->bdev)
continue;
if (!zinfo->max_active_zones) {
ret = true;
break;
}
if (flags & BTRFS_BLOCK_GROUP_DATA)
reserved = zinfo->reserved_active_zones;
switch (flags & BTRFS_BLOCK_GROUP_PROFILE_MASK) {
case 0:
ret = (atomic_read(&zinfo->active_zones_left) >= (1 + reserved));
break;
case BTRFS_BLOCK_GROUP_DUP:
ret = (atomic_read(&zinfo->active_zones_left) >= (2 + reserved));
break;
}
if (ret)
break;
}
spin_unlock(&fs_info->zone_active_bgs_lock);
mutex_unlock(&fs_info->chunk_mutex);
if (!ret)
set_bit(BTRFS_FS_NEED_ZONE_FINISH, &fs_info->flags);
return ret;
}
void btrfs_zone_finish_endio(struct btrfs_fs_info *fs_info, u64 logical, u64 length)
{
struct btrfs_block_group *block_group;
u64 min_alloc_bytes;
if (!btrfs_is_zoned(fs_info))
return;
block_group = btrfs_lookup_block_group(fs_info, logical);
ASSERT(block_group);
if (block_group->flags & BTRFS_BLOCK_GROUP_DATA)
min_alloc_bytes = fs_info->sectorsize;
else
min_alloc_bytes = fs_info->nodesize;
if (logical + length + min_alloc_bytes <=
block_group->start + block_group->zone_capacity)
goto out;
do_zone_finish(block_group, true);
out:
btrfs_put_block_group(block_group);
}
static void btrfs_zone_finish_endio_workfn(struct work_struct *work)
{
struct btrfs_block_group *bg =
container_of(work, struct btrfs_block_group, zone_finish_work);
wait_on_extent_buffer_writeback(bg->last_eb);
free_extent_buffer(bg->last_eb);
btrfs_zone_finish_endio(bg->fs_info, bg->start, bg->length);
btrfs_put_block_group(bg);
}
void btrfs_schedule_zone_finish_bg(struct btrfs_block_group *bg,
struct extent_buffer *eb)
{
if (!test_bit(BLOCK_GROUP_FLAG_SEQUENTIAL_ZONE, &bg->runtime_flags) ||
eb->start + eb->len * 2 <= bg->start + bg->zone_capacity)
return;
if (WARN_ON(bg->zone_finish_work.func == btrfs_zone_finish_endio_workfn)) {
btrfs_err(bg->fs_info, "double scheduling of bg %llu zone finishing",
bg->start);
return;
}
btrfs_get_block_group(bg);
atomic_inc(&eb->refs);
bg->last_eb = eb;
INIT_WORK(&bg->zone_finish_work, btrfs_zone_finish_endio_workfn);
queue_work(system_unbound_wq, &bg->zone_finish_work);
}
void btrfs_clear_data_reloc_bg(struct btrfs_block_group *bg)
{
struct btrfs_fs_info *fs_info = bg->fs_info;
spin_lock(&fs_info->relocation_bg_lock);
if (fs_info->data_reloc_bg == bg->start)
fs_info->data_reloc_bg = 0;
spin_unlock(&fs_info->relocation_bg_lock);
}
void btrfs_free_zone_cache(struct btrfs_fs_info *fs_info)
{
struct btrfs_fs_devices *fs_devices = fs_info->fs_devices;
struct btrfs_device *device;
if (!btrfs_is_zoned(fs_info))
return;
mutex_lock(&fs_devices->device_list_mutex);
list_for_each_entry(device, &fs_devices->devices, dev_list) {
if (device->zone_info) {
vfree(device->zone_info->zone_cache);
device->zone_info->zone_cache = NULL;
}
}
mutex_unlock(&fs_devices->device_list_mutex);
}
bool btrfs_zoned_should_reclaim(struct btrfs_fs_info *fs_info)
{
struct btrfs_fs_devices *fs_devices = fs_info->fs_devices;
struct btrfs_device *device;
u64 used = 0;
u64 total = 0;
u64 factor;
ASSERT(btrfs_is_zoned(fs_info));
if (fs_info->bg_reclaim_threshold == 0)
return false;
mutex_lock(&fs_devices->device_list_mutex);
list_for_each_entry(device, &fs_devices->devices, dev_list) {
if (!device->bdev)
continue;
total += device->disk_total_bytes;
used += device->bytes_used;
}
mutex_unlock(&fs_devices->device_list_mutex);
factor = div64_u64(used * 100, total);
return factor >= fs_info->bg_reclaim_threshold;
}
void btrfs_zoned_release_data_reloc_bg(struct btrfs_fs_info *fs_info, u64 logical,
u64 length)
{
struct btrfs_block_group *block_group;
if (!btrfs_is_zoned(fs_info))
return;
block_group = btrfs_lookup_block_group(fs_info, logical);
ASSERT(block_group && (block_group->flags & BTRFS_BLOCK_GROUP_DATA));
spin_lock(&block_group->lock);
if (!test_bit(BLOCK_GROUP_FLAG_ZONED_DATA_RELOC, &block_group->runtime_flags))
goto out;
if (block_group->start + block_group->alloc_offset == logical + length) {
clear_bit(BLOCK_GROUP_FLAG_ZONED_DATA_RELOC,
&block_group->runtime_flags);
}
out:
spin_unlock(&block_group->lock);
btrfs_put_block_group(block_group);
}
int btrfs_zone_finish_one_bg(struct btrfs_fs_info *fs_info)
{
struct btrfs_block_group *block_group;
struct btrfs_block_group *min_bg = NULL;
u64 min_avail = U64_MAX;
int ret;
spin_lock(&fs_info->zone_active_bgs_lock);
list_for_each_entry(block_group, &fs_info->zone_active_bgs,
active_bg_list) {
u64 avail;
spin_lock(&block_group->lock);
if (block_group->reserved || block_group->alloc_offset == 0 ||
(block_group->flags & BTRFS_BLOCK_GROUP_SYSTEM) ||
test_bit(BLOCK_GROUP_FLAG_ZONED_DATA_RELOC, &block_group->runtime_flags)) {
spin_unlock(&block_group->lock);
continue;
}
avail = block_group->zone_capacity - block_group->alloc_offset;
if (min_avail > avail) {
if (min_bg)
btrfs_put_block_group(min_bg);
min_bg = block_group;
min_avail = avail;
btrfs_get_block_group(min_bg);
}
spin_unlock(&block_group->lock);
}
spin_unlock(&fs_info->zone_active_bgs_lock);
if (!min_bg)
return 0;
ret = btrfs_zone_finish(min_bg);
btrfs_put_block_group(min_bg);
return ret < 0 ? ret : 1;
}
int btrfs_zoned_activate_one_bg(struct btrfs_fs_info *fs_info,
struct btrfs_space_info *space_info,
bool do_finish)
{
struct btrfs_block_group *bg;
int index;
if (!btrfs_is_zoned(fs_info) || (space_info->flags & BTRFS_BLOCK_GROUP_DATA))
return 0;
for (;;) {
int ret;
bool need_finish = false;
down_read(&space_info->groups_sem);
for (index = 0; index < BTRFS_NR_RAID_TYPES; index++) {
list_for_each_entry(bg, &space_info->block_groups[index],
list) {
if (!spin_trylock(&bg->lock))
continue;
if (btrfs_zoned_bg_is_full(bg) ||
test_bit(BLOCK_GROUP_FLAG_ZONE_IS_ACTIVE,
&bg->runtime_flags)) {
spin_unlock(&bg->lock);
continue;
}
spin_unlock(&bg->lock);
if (btrfs_zone_activate(bg)) {
up_read(&space_info->groups_sem);
return 1;
}
need_finish = true;
}
}
up_read(&space_info->groups_sem);
if (!do_finish || !need_finish)
break;
ret = btrfs_zone_finish_one_bg(fs_info);
if (ret == 0)
break;
if (ret < 0)
return ret;
}
return 0;
}
void btrfs_check_active_zone_reservation(struct btrfs_fs_info *fs_info)
{
struct btrfs_fs_devices *fs_devices = fs_info->fs_devices;
struct btrfs_block_group *block_group;
struct btrfs_device *device;
unsigned int metadata_reserve = 2;
unsigned int system_reserve = 1;
if (!test_bit(BTRFS_FS_ACTIVE_ZONE_TRACKING, &fs_info->flags))
return;
if (fs_info->avail_metadata_alloc_bits & BTRFS_BLOCK_GROUP_DUP)
metadata_reserve = 4;
if (fs_info->avail_system_alloc_bits & BTRFS_BLOCK_GROUP_DUP)
system_reserve = 2;
mutex_lock(&fs_devices->device_list_mutex);
list_for_each_entry(device, &fs_devices->devices, dev_list) {
if (!device->bdev)
continue;
device->zone_info->reserved_active_zones =
metadata_reserve + system_reserve;
}
mutex_unlock(&fs_devices->device_list_mutex);
spin_lock(&fs_info->zone_active_bgs_lock);
list_for_each_entry(block_group, &fs_info->zone_active_bgs, active_bg_list) {
struct map_lookup *map = block_group->physical_map;
if (!(block_group->flags &
(BTRFS_BLOCK_GROUP_METADATA | BTRFS_BLOCK_GROUP_SYSTEM)))
continue;
for (int i = 0; i < map->num_stripes; i++)
map->stripes[i].dev->zone_info->reserved_active_zones--;
}
spin_unlock(&fs_info->zone_active_bgs_lock);
}