blob: a0ce3d080f80a1662fe6444c99cfe2e991e5184e [file] [log] [blame]
// SPDX-License-Identifier: GPL-2.0
/*
* fs/f2fs/segment.c
*
* Copyright (c) 2012 Samsung Electronics Co., Ltd.
* http://www.samsung.com/
*/
#include <linux/fs.h>
#include <linux/f2fs_fs.h>
#include <linux/bio.h>
#include <linux/blkdev.h>
#include <linux/sched/mm.h>
#include <linux/prefetch.h>
#include <linux/kthread.h>
#include <linux/swap.h>
#include <linux/timer.h>
#include <linux/freezer.h>
#include <linux/sched/signal.h>
#include <linux/random.h>
#include "f2fs.h"
#include "segment.h"
#include "node.h"
#include "gc.h"
#include "iostat.h"
#include <trace/events/f2fs.h>
#define __reverse_ffz(x) __reverse_ffs(~(x))
static struct kmem_cache *discard_entry_slab;
static struct kmem_cache *discard_cmd_slab;
static struct kmem_cache *sit_entry_set_slab;
static struct kmem_cache *revoke_entry_slab;
static unsigned long __reverse_ulong(unsigned char *str)
{
unsigned long tmp = 0;
int shift = 24, idx = 0;
#if BITS_PER_LONG == 64
shift = 56;
#endif
while (shift >= 0) {
tmp |= (unsigned long)str[idx++] << shift;
shift -= BITS_PER_BYTE;
}
return tmp;
}
/*
* __reverse_ffs is copied from include/asm-generic/bitops/__ffs.h since
* MSB and LSB are reversed in a byte by f2fs_set_bit.
*/
static inline unsigned long __reverse_ffs(unsigned long word)
{
int num = 0;
#if BITS_PER_LONG == 64
if ((word & 0xffffffff00000000UL) == 0)
num += 32;
else
word >>= 32;
#endif
if ((word & 0xffff0000) == 0)
num += 16;
else
word >>= 16;
if ((word & 0xff00) == 0)
num += 8;
else
word >>= 8;
if ((word & 0xf0) == 0)
num += 4;
else
word >>= 4;
if ((word & 0xc) == 0)
num += 2;
else
word >>= 2;
if ((word & 0x2) == 0)
num += 1;
return num;
}
/*
* __find_rev_next(_zero)_bit is copied from lib/find_next_bit.c because
* f2fs_set_bit makes MSB and LSB reversed in a byte.
* @size must be integral times of unsigned long.
* Example:
* MSB <--> LSB
* f2fs_set_bit(0, bitmap) => 1000 0000
* f2fs_set_bit(7, bitmap) => 0000 0001
*/
static unsigned long __find_rev_next_bit(const unsigned long *addr,
unsigned long size, unsigned long offset)
{
const unsigned long *p = addr + BIT_WORD(offset);
unsigned long result = size;
unsigned long tmp;
if (offset >= size)
return size;
size -= (offset & ~(BITS_PER_LONG - 1));
offset %= BITS_PER_LONG;
while (1) {
if (*p == 0)
goto pass;
tmp = __reverse_ulong((unsigned char *)p);
tmp &= ~0UL >> offset;
if (size < BITS_PER_LONG)
tmp &= (~0UL << (BITS_PER_LONG - size));
if (tmp)
goto found;
pass:
if (size <= BITS_PER_LONG)
break;
size -= BITS_PER_LONG;
offset = 0;
p++;
}
return result;
found:
return result - size + __reverse_ffs(tmp);
}
static unsigned long __find_rev_next_zero_bit(const unsigned long *addr,
unsigned long size, unsigned long offset)
{
const unsigned long *p = addr + BIT_WORD(offset);
unsigned long result = size;
unsigned long tmp;
if (offset >= size)
return size;
size -= (offset & ~(BITS_PER_LONG - 1));
offset %= BITS_PER_LONG;
while (1) {
if (*p == ~0UL)
goto pass;
tmp = __reverse_ulong((unsigned char *)p);
if (offset)
tmp |= ~0UL << (BITS_PER_LONG - offset);
if (size < BITS_PER_LONG)
tmp |= ~0UL >> size;
if (tmp != ~0UL)
goto found;
pass:
if (size <= BITS_PER_LONG)
break;
size -= BITS_PER_LONG;
offset = 0;
p++;
}
return result;
found:
return result - size + __reverse_ffz(tmp);
}
bool f2fs_need_SSR(struct f2fs_sb_info *sbi)
{
int node_secs = get_blocktype_secs(sbi, F2FS_DIRTY_NODES);
int dent_secs = get_blocktype_secs(sbi, F2FS_DIRTY_DENTS);
int imeta_secs = get_blocktype_secs(sbi, F2FS_DIRTY_IMETA);
if (f2fs_lfs_mode(sbi))
return false;
if (sbi->gc_mode == GC_URGENT_HIGH)
return true;
if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED)))
return true;
return free_sections(sbi) <= (node_secs + 2 * dent_secs + imeta_secs +
SM_I(sbi)->min_ssr_sections + reserved_sections(sbi));
}
void f2fs_abort_atomic_write(struct inode *inode, bool clean)
{
struct f2fs_inode_info *fi = F2FS_I(inode);
if (!f2fs_is_atomic_file(inode))
return;
if (clean)
truncate_inode_pages_final(inode->i_mapping);
release_atomic_write_cnt(inode);
clear_inode_flag(inode, FI_ATOMIC_COMMITTED);
clear_inode_flag(inode, FI_ATOMIC_REPLACE);
clear_inode_flag(inode, FI_ATOMIC_FILE);
stat_dec_atomic_inode(inode);
F2FS_I(inode)->atomic_write_task = NULL;
if (clean) {
f2fs_i_size_write(inode, fi->original_i_size);
fi->original_i_size = 0;
}
/* avoid stale dirty inode during eviction */
sync_inode_metadata(inode, 0);
}
static int __replace_atomic_write_block(struct inode *inode, pgoff_t index,
block_t new_addr, block_t *old_addr, bool recover)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct dnode_of_data dn;
struct node_info ni;
int err;
retry:
set_new_dnode(&dn, inode, NULL, NULL, 0);
err = f2fs_get_dnode_of_data(&dn, index, ALLOC_NODE);
if (err) {
if (err == -ENOMEM) {
f2fs_io_schedule_timeout(DEFAULT_IO_TIMEOUT);
goto retry;
}
return err;
}
err = f2fs_get_node_info(sbi, dn.nid, &ni, false);
if (err) {
f2fs_put_dnode(&dn);
return err;
}
if (recover) {
/* dn.data_blkaddr is always valid */
if (!__is_valid_data_blkaddr(new_addr)) {
if (new_addr == NULL_ADDR)
dec_valid_block_count(sbi, inode, 1);
f2fs_invalidate_blocks(sbi, dn.data_blkaddr);
f2fs_update_data_blkaddr(&dn, new_addr);
} else {
f2fs_replace_block(sbi, &dn, dn.data_blkaddr,
new_addr, ni.version, true, true);
}
} else {
blkcnt_t count = 1;
err = inc_valid_block_count(sbi, inode, &count, true);
if (err) {
f2fs_put_dnode(&dn);
return err;
}
*old_addr = dn.data_blkaddr;
f2fs_truncate_data_blocks_range(&dn, 1);
dec_valid_block_count(sbi, F2FS_I(inode)->cow_inode, count);
f2fs_replace_block(sbi, &dn, dn.data_blkaddr, new_addr,
ni.version, true, false);
}
f2fs_put_dnode(&dn);
trace_f2fs_replace_atomic_write_block(inode, F2FS_I(inode)->cow_inode,
index, old_addr ? *old_addr : 0, new_addr, recover);
return 0;
}
static void __complete_revoke_list(struct inode *inode, struct list_head *head,
bool revoke)
{
struct revoke_entry *cur, *tmp;
pgoff_t start_index = 0;
bool truncate = is_inode_flag_set(inode, FI_ATOMIC_REPLACE);
list_for_each_entry_safe(cur, tmp, head, list) {
if (revoke) {
__replace_atomic_write_block(inode, cur->index,
cur->old_addr, NULL, true);
} else if (truncate) {
f2fs_truncate_hole(inode, start_index, cur->index);
start_index = cur->index + 1;
}
list_del(&cur->list);
kmem_cache_free(revoke_entry_slab, cur);
}
if (!revoke && truncate)
f2fs_do_truncate_blocks(inode, start_index * PAGE_SIZE, false);
}
static int __f2fs_commit_atomic_write(struct inode *inode)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct f2fs_inode_info *fi = F2FS_I(inode);
struct inode *cow_inode = fi->cow_inode;
struct revoke_entry *new;
struct list_head revoke_list;
block_t blkaddr;
struct dnode_of_data dn;
pgoff_t len = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE);
pgoff_t off = 0, blen, index;
int ret = 0, i;
INIT_LIST_HEAD(&revoke_list);
while (len) {
blen = min_t(pgoff_t, ADDRS_PER_BLOCK(cow_inode), len);
set_new_dnode(&dn, cow_inode, NULL, NULL, 0);
ret = f2fs_get_dnode_of_data(&dn, off, LOOKUP_NODE_RA);
if (ret && ret != -ENOENT) {
goto out;
} else if (ret == -ENOENT) {
ret = 0;
if (dn.max_level == 0)
goto out;
goto next;
}
blen = min((pgoff_t)ADDRS_PER_PAGE(dn.node_page, cow_inode),
len);
index = off;
for (i = 0; i < blen; i++, dn.ofs_in_node++, index++) {
blkaddr = f2fs_data_blkaddr(&dn);
if (!__is_valid_data_blkaddr(blkaddr)) {
continue;
} else if (!f2fs_is_valid_blkaddr(sbi, blkaddr,
DATA_GENERIC_ENHANCE)) {
f2fs_put_dnode(&dn);
ret = -EFSCORRUPTED;
goto out;
}
new = f2fs_kmem_cache_alloc(revoke_entry_slab, GFP_NOFS,
true, NULL);
ret = __replace_atomic_write_block(inode, index, blkaddr,
&new->old_addr, false);
if (ret) {
f2fs_put_dnode(&dn);
kmem_cache_free(revoke_entry_slab, new);
goto out;
}
f2fs_update_data_blkaddr(&dn, NULL_ADDR);
new->index = index;
list_add_tail(&new->list, &revoke_list);
}
f2fs_put_dnode(&dn);
next:
off += blen;
len -= blen;
}
out:
if (ret) {
sbi->revoked_atomic_block += fi->atomic_write_cnt;
} else {
sbi->committed_atomic_block += fi->atomic_write_cnt;
set_inode_flag(inode, FI_ATOMIC_COMMITTED);
}
__complete_revoke_list(inode, &revoke_list, ret ? true : false);
return ret;
}
int f2fs_commit_atomic_write(struct inode *inode)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct f2fs_inode_info *fi = F2FS_I(inode);
int err;
err = filemap_write_and_wait_range(inode->i_mapping, 0, LLONG_MAX);
if (err)
return err;
f2fs_down_write(&fi->i_gc_rwsem[WRITE]);
f2fs_lock_op(sbi);
err = __f2fs_commit_atomic_write(inode);
f2fs_unlock_op(sbi);
f2fs_up_write(&fi->i_gc_rwsem[WRITE]);
return err;
}
/*
* This function balances dirty node and dentry pages.
* In addition, it controls garbage collection.
*/
void f2fs_balance_fs(struct f2fs_sb_info *sbi, bool need)
{
if (f2fs_cp_error(sbi))
return;
if (time_to_inject(sbi, FAULT_CHECKPOINT))
f2fs_stop_checkpoint(sbi, false, STOP_CP_REASON_FAULT_INJECT);
/* balance_fs_bg is able to be pending */
if (need && excess_cached_nats(sbi))
f2fs_balance_fs_bg(sbi, false);
if (!f2fs_is_checkpoint_ready(sbi))
return;
/*
* We should do GC or end up with checkpoint, if there are so many dirty
* dir/node pages without enough free segments.
*/
if (has_enough_free_secs(sbi, 0, 0))
return;
if (test_opt(sbi, GC_MERGE) && sbi->gc_thread &&
sbi->gc_thread->f2fs_gc_task) {
DEFINE_WAIT(wait);
prepare_to_wait(&sbi->gc_thread->fggc_wq, &wait,
TASK_UNINTERRUPTIBLE);
wake_up(&sbi->gc_thread->gc_wait_queue_head);
io_schedule();
finish_wait(&sbi->gc_thread->fggc_wq, &wait);
} else {
struct f2fs_gc_control gc_control = {
.victim_segno = NULL_SEGNO,
.init_gc_type = BG_GC,
.no_bg_gc = true,
.should_migrate_blocks = false,
.err_gc_skipped = false,
.nr_free_secs = 1 };
f2fs_down_write(&sbi->gc_lock);
stat_inc_gc_call_count(sbi, FOREGROUND);
f2fs_gc(sbi, &gc_control);
}
}
static inline bool excess_dirty_threshold(struct f2fs_sb_info *sbi)
{
int factor = f2fs_rwsem_is_locked(&sbi->cp_rwsem) ? 3 : 2;
unsigned int dents = get_pages(sbi, F2FS_DIRTY_DENTS);
unsigned int qdata = get_pages(sbi, F2FS_DIRTY_QDATA);
unsigned int nodes = get_pages(sbi, F2FS_DIRTY_NODES);
unsigned int meta = get_pages(sbi, F2FS_DIRTY_META);
unsigned int imeta = get_pages(sbi, F2FS_DIRTY_IMETA);
unsigned int threshold =
SEGS_TO_BLKS(sbi, (factor * DEFAULT_DIRTY_THRESHOLD));
unsigned int global_threshold = threshold * 3 / 2;
if (dents >= threshold || qdata >= threshold ||
nodes >= threshold || meta >= threshold ||
imeta >= threshold)
return true;
return dents + qdata + nodes + meta + imeta > global_threshold;
}
void f2fs_balance_fs_bg(struct f2fs_sb_info *sbi, bool from_bg)
{
if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING)))
return;
/* try to shrink extent cache when there is no enough memory */
if (!f2fs_available_free_memory(sbi, READ_EXTENT_CACHE))
f2fs_shrink_read_extent_tree(sbi,
READ_EXTENT_CACHE_SHRINK_NUMBER);
/* try to shrink age extent cache when there is no enough memory */
if (!f2fs_available_free_memory(sbi, AGE_EXTENT_CACHE))
f2fs_shrink_age_extent_tree(sbi,
AGE_EXTENT_CACHE_SHRINK_NUMBER);
/* check the # of cached NAT entries */
if (!f2fs_available_free_memory(sbi, NAT_ENTRIES))
f2fs_try_to_free_nats(sbi, NAT_ENTRY_PER_BLOCK);
if (!f2fs_available_free_memory(sbi, FREE_NIDS))
f2fs_try_to_free_nids(sbi, MAX_FREE_NIDS);
else
f2fs_build_free_nids(sbi, false, false);
if (excess_dirty_nats(sbi) || excess_dirty_threshold(sbi) ||
excess_prefree_segs(sbi) || !f2fs_space_for_roll_forward(sbi))
goto do_sync;
/* there is background inflight IO or foreground operation recently */
if (is_inflight_io(sbi, REQ_TIME) ||
(!f2fs_time_over(sbi, REQ_TIME) && f2fs_rwsem_is_locked(&sbi->cp_rwsem)))
return;
/* exceed periodical checkpoint timeout threshold */
if (f2fs_time_over(sbi, CP_TIME))
goto do_sync;
/* checkpoint is the only way to shrink partial cached entries */
if (f2fs_available_free_memory(sbi, NAT_ENTRIES) &&
f2fs_available_free_memory(sbi, INO_ENTRIES))
return;
do_sync:
if (test_opt(sbi, DATA_FLUSH) && from_bg) {
struct blk_plug plug;
mutex_lock(&sbi->flush_lock);
blk_start_plug(&plug);
f2fs_sync_dirty_inodes(sbi, FILE_INODE, false);
blk_finish_plug(&plug);
mutex_unlock(&sbi->flush_lock);
}
stat_inc_cp_call_count(sbi, BACKGROUND);
f2fs_sync_fs(sbi->sb, 1);
}
static int __submit_flush_wait(struct f2fs_sb_info *sbi,
struct block_device *bdev)
{
int ret = blkdev_issue_flush(bdev);
trace_f2fs_issue_flush(bdev, test_opt(sbi, NOBARRIER),
test_opt(sbi, FLUSH_MERGE), ret);
if (!ret)
f2fs_update_iostat(sbi, NULL, FS_FLUSH_IO, 0);
return ret;
}
static int submit_flush_wait(struct f2fs_sb_info *sbi, nid_t ino)
{
int ret = 0;
int i;
if (!f2fs_is_multi_device(sbi))
return __submit_flush_wait(sbi, sbi->sb->s_bdev);
for (i = 0; i < sbi->s_ndevs; i++) {
if (!f2fs_is_dirty_device(sbi, ino, i, FLUSH_INO))
continue;
ret = __submit_flush_wait(sbi, FDEV(i).bdev);
if (ret)
break;
}
return ret;
}
static int issue_flush_thread(void *data)
{
struct f2fs_sb_info *sbi = data;
struct flush_cmd_control *fcc = SM_I(sbi)->fcc_info;
wait_queue_head_t *q = &fcc->flush_wait_queue;
repeat:
if (kthread_should_stop())
return 0;
if (!llist_empty(&fcc->issue_list)) {
struct flush_cmd *cmd, *next;
int ret;
fcc->dispatch_list = llist_del_all(&fcc->issue_list);
fcc->dispatch_list = llist_reverse_order(fcc->dispatch_list);
cmd = llist_entry(fcc->dispatch_list, struct flush_cmd, llnode);
ret = submit_flush_wait(sbi, cmd->ino);
atomic_inc(&fcc->issued_flush);
llist_for_each_entry_safe(cmd, next,
fcc->dispatch_list, llnode) {
cmd->ret = ret;
complete(&cmd->wait);
}
fcc->dispatch_list = NULL;
}
wait_event_interruptible(*q,
kthread_should_stop() || !llist_empty(&fcc->issue_list));
goto repeat;
}
int f2fs_issue_flush(struct f2fs_sb_info *sbi, nid_t ino)
{
struct flush_cmd_control *fcc = SM_I(sbi)->fcc_info;
struct flush_cmd cmd;
int ret;
if (test_opt(sbi, NOBARRIER))
return 0;
if (!test_opt(sbi, FLUSH_MERGE)) {
atomic_inc(&fcc->queued_flush);
ret = submit_flush_wait(sbi, ino);
atomic_dec(&fcc->queued_flush);
atomic_inc(&fcc->issued_flush);
return ret;
}
if (atomic_inc_return(&fcc->queued_flush) == 1 ||
f2fs_is_multi_device(sbi)) {
ret = submit_flush_wait(sbi, ino);
atomic_dec(&fcc->queued_flush);
atomic_inc(&fcc->issued_flush);
return ret;
}
cmd.ino = ino;
init_completion(&cmd.wait);
llist_add(&cmd.llnode, &fcc->issue_list);
/*
* update issue_list before we wake up issue_flush thread, this
* smp_mb() pairs with another barrier in ___wait_event(), see
* more details in comments of waitqueue_active().
*/
smp_mb();
if (waitqueue_active(&fcc->flush_wait_queue))
wake_up(&fcc->flush_wait_queue);
if (fcc->f2fs_issue_flush) {
wait_for_completion(&cmd.wait);
atomic_dec(&fcc->queued_flush);
} else {
struct llist_node *list;
list = llist_del_all(&fcc->issue_list);
if (!list) {
wait_for_completion(&cmd.wait);
atomic_dec(&fcc->queued_flush);
} else {
struct flush_cmd *tmp, *next;
ret = submit_flush_wait(sbi, ino);
llist_for_each_entry_safe(tmp, next, list, llnode) {
if (tmp == &cmd) {
cmd.ret = ret;
atomic_dec(&fcc->queued_flush);
continue;
}
tmp->ret = ret;
complete(&tmp->wait);
}
}
}
return cmd.ret;
}
int f2fs_create_flush_cmd_control(struct f2fs_sb_info *sbi)
{
dev_t dev = sbi->sb->s_bdev->bd_dev;
struct flush_cmd_control *fcc;
if (SM_I(sbi)->fcc_info) {
fcc = SM_I(sbi)->fcc_info;
if (fcc->f2fs_issue_flush)
return 0;
goto init_thread;
}
fcc = f2fs_kzalloc(sbi, sizeof(struct flush_cmd_control), GFP_KERNEL);
if (!fcc)
return -ENOMEM;
atomic_set(&fcc->issued_flush, 0);
atomic_set(&fcc->queued_flush, 0);
init_waitqueue_head(&fcc->flush_wait_queue);
init_llist_head(&fcc->issue_list);
SM_I(sbi)->fcc_info = fcc;
if (!test_opt(sbi, FLUSH_MERGE))
return 0;
init_thread:
fcc->f2fs_issue_flush = kthread_run(issue_flush_thread, sbi,
"f2fs_flush-%u:%u", MAJOR(dev), MINOR(dev));
if (IS_ERR(fcc->f2fs_issue_flush)) {
int err = PTR_ERR(fcc->f2fs_issue_flush);
fcc->f2fs_issue_flush = NULL;
return err;
}
return 0;
}
void f2fs_destroy_flush_cmd_control(struct f2fs_sb_info *sbi, bool free)
{
struct flush_cmd_control *fcc = SM_I(sbi)->fcc_info;
if (fcc && fcc->f2fs_issue_flush) {
struct task_struct *flush_thread = fcc->f2fs_issue_flush;
fcc->f2fs_issue_flush = NULL;
kthread_stop(flush_thread);
}
if (free) {
kfree(fcc);
SM_I(sbi)->fcc_info = NULL;
}
}
int f2fs_flush_device_cache(struct f2fs_sb_info *sbi)
{
int ret = 0, i;
if (!f2fs_is_multi_device(sbi))
return 0;
if (test_opt(sbi, NOBARRIER))
return 0;
for (i = 1; i < sbi->s_ndevs; i++) {
int count = DEFAULT_RETRY_IO_COUNT;
if (!f2fs_test_bit(i, (char *)&sbi->dirty_device))
continue;
do {
ret = __submit_flush_wait(sbi, FDEV(i).bdev);
if (ret)
f2fs_io_schedule_timeout(DEFAULT_IO_TIMEOUT);
} while (ret && --count);
if (ret) {
f2fs_stop_checkpoint(sbi, false,
STOP_CP_REASON_FLUSH_FAIL);
break;
}
spin_lock(&sbi->dev_lock);
f2fs_clear_bit(i, (char *)&sbi->dirty_device);
spin_unlock(&sbi->dev_lock);
}
return ret;
}
static void __locate_dirty_segment(struct f2fs_sb_info *sbi, unsigned int segno,
enum dirty_type dirty_type)
{
struct dirty_seglist_info *dirty_i = DIRTY_I(sbi);
/* need not be added */
if (IS_CURSEG(sbi, segno))
return;
if (!test_and_set_bit(segno, dirty_i->dirty_segmap[dirty_type]))
dirty_i->nr_dirty[dirty_type]++;
if (dirty_type == DIRTY) {
struct seg_entry *sentry = get_seg_entry(sbi, segno);
enum dirty_type t = sentry->type;
if (unlikely(t >= DIRTY)) {
f2fs_bug_on(sbi, 1);
return;
}
if (!test_and_set_bit(segno, dirty_i->dirty_segmap[t]))
dirty_i->nr_dirty[t]++;
if (__is_large_section(sbi)) {
unsigned int secno = GET_SEC_FROM_SEG(sbi, segno);
block_t valid_blocks =
get_valid_blocks(sbi, segno, true);
f2fs_bug_on(sbi,
(!is_sbi_flag_set(sbi, SBI_CP_DISABLED) &&
!valid_blocks) ||
valid_blocks == CAP_BLKS_PER_SEC(sbi));
if (!IS_CURSEC(sbi, secno))
set_bit(secno, dirty_i->dirty_secmap);
}
}
}
static void __remove_dirty_segment(struct f2fs_sb_info *sbi, unsigned int segno,
enum dirty_type dirty_type)
{
struct dirty_seglist_info *dirty_i = DIRTY_I(sbi);
block_t valid_blocks;
if (test_and_clear_bit(segno, dirty_i->dirty_segmap[dirty_type]))
dirty_i->nr_dirty[dirty_type]--;
if (dirty_type == DIRTY) {
struct seg_entry *sentry = get_seg_entry(sbi, segno);
enum dirty_type t = sentry->type;
if (test_and_clear_bit(segno, dirty_i->dirty_segmap[t]))
dirty_i->nr_dirty[t]--;
valid_blocks = get_valid_blocks(sbi, segno, true);
if (valid_blocks == 0) {
clear_bit(GET_SEC_FROM_SEG(sbi, segno),
dirty_i->victim_secmap);
#ifdef CONFIG_F2FS_CHECK_FS
clear_bit(segno, SIT_I(sbi)->invalid_segmap);
#endif
}
if (__is_large_section(sbi)) {
unsigned int secno = GET_SEC_FROM_SEG(sbi, segno);
if (!valid_blocks ||
valid_blocks == CAP_BLKS_PER_SEC(sbi)) {
clear_bit(secno, dirty_i->dirty_secmap);
return;
}
if (!IS_CURSEC(sbi, secno))
set_bit(secno, dirty_i->dirty_secmap);
}
}
}
/*
* Should not occur error such as -ENOMEM.
* Adding dirty entry into seglist is not critical operation.
* If a given segment is one of current working segments, it won't be added.
*/
static void locate_dirty_segment(struct f2fs_sb_info *sbi, unsigned int segno)
{
struct dirty_seglist_info *dirty_i = DIRTY_I(sbi);
unsigned short valid_blocks, ckpt_valid_blocks;
unsigned int usable_blocks;
if (segno == NULL_SEGNO || IS_CURSEG(sbi, segno))
return;
usable_blocks = f2fs_usable_blks_in_seg(sbi, segno);
mutex_lock(&dirty_i->seglist_lock);
valid_blocks = get_valid_blocks(sbi, segno, false);
ckpt_valid_blocks = get_ckpt_valid_blocks(sbi, segno, false);
if (valid_blocks == 0 && (!is_sbi_flag_set(sbi, SBI_CP_DISABLED) ||
ckpt_valid_blocks == usable_blocks)) {
__locate_dirty_segment(sbi, segno, PRE);
__remove_dirty_segment(sbi, segno, DIRTY);
} else if (valid_blocks < usable_blocks) {
__locate_dirty_segment(sbi, segno, DIRTY);
} else {
/* Recovery routine with SSR needs this */
__remove_dirty_segment(sbi, segno, DIRTY);
}
mutex_unlock(&dirty_i->seglist_lock);
}
/* This moves currently empty dirty blocks to prefree. Must hold seglist_lock */
void f2fs_dirty_to_prefree(struct f2fs_sb_info *sbi)
{
struct dirty_seglist_info *dirty_i = DIRTY_I(sbi);
unsigned int segno;
mutex_lock(&dirty_i->seglist_lock);
for_each_set_bit(segno, dirty_i->dirty_segmap[DIRTY], MAIN_SEGS(sbi)) {
if (get_valid_blocks(sbi, segno, false))
continue;
if (IS_CURSEG(sbi, segno))
continue;
__locate_dirty_segment(sbi, segno, PRE);
__remove_dirty_segment(sbi, segno, DIRTY);
}
mutex_unlock(&dirty_i->seglist_lock);
}
block_t f2fs_get_unusable_blocks(struct f2fs_sb_info *sbi)
{
int ovp_hole_segs =
(overprovision_segments(sbi) - reserved_segments(sbi));
block_t ovp_holes = SEGS_TO_BLKS(sbi, ovp_hole_segs);
struct dirty_seglist_info *dirty_i = DIRTY_I(sbi);
block_t holes[2] = {0, 0}; /* DATA and NODE */
block_t unusable;
struct seg_entry *se;
unsigned int segno;
mutex_lock(&dirty_i->seglist_lock);
for_each_set_bit(segno, dirty_i->dirty_segmap[DIRTY], MAIN_SEGS(sbi)) {
se = get_seg_entry(sbi, segno);
if (IS_NODESEG(se->type))
holes[NODE] += f2fs_usable_blks_in_seg(sbi, segno) -
se->valid_blocks;
else
holes[DATA] += f2fs_usable_blks_in_seg(sbi, segno) -
se->valid_blocks;
}
mutex_unlock(&dirty_i->seglist_lock);
unusable = max(holes[DATA], holes[NODE]);
if (unusable > ovp_holes)
return unusable - ovp_holes;
return 0;
}
int f2fs_disable_cp_again(struct f2fs_sb_info *sbi, block_t unusable)
{
int ovp_hole_segs =
(overprovision_segments(sbi) - reserved_segments(sbi));
if (F2FS_OPTION(sbi).unusable_cap_perc == 100)
return 0;
if (unusable > F2FS_OPTION(sbi).unusable_cap)
return -EAGAIN;
if (is_sbi_flag_set(sbi, SBI_CP_DISABLED_QUICK) &&
dirty_segments(sbi) > ovp_hole_segs)
return -EAGAIN;
if (has_not_enough_free_secs(sbi, 0, 0))
return -EAGAIN;
return 0;
}
/* This is only used by SBI_CP_DISABLED */
static unsigned int get_free_segment(struct f2fs_sb_info *sbi)
{
struct dirty_seglist_info *dirty_i = DIRTY_I(sbi);
unsigned int segno = 0;
mutex_lock(&dirty_i->seglist_lock);
for_each_set_bit(segno, dirty_i->dirty_segmap[DIRTY], MAIN_SEGS(sbi)) {
if (get_valid_blocks(sbi, segno, false))
continue;
if (get_ckpt_valid_blocks(sbi, segno, false))
continue;
mutex_unlock(&dirty_i->seglist_lock);
return segno;
}
mutex_unlock(&dirty_i->seglist_lock);
return NULL_SEGNO;
}
static struct discard_cmd *__create_discard_cmd(struct f2fs_sb_info *sbi,
struct block_device *bdev, block_t lstart,
block_t start, block_t len)
{
struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
struct list_head *pend_list;
struct discard_cmd *dc;
f2fs_bug_on(sbi, !len);
pend_list = &dcc->pend_list[plist_idx(len)];
dc = f2fs_kmem_cache_alloc(discard_cmd_slab, GFP_NOFS, true, NULL);
INIT_LIST_HEAD(&dc->list);
dc->bdev = bdev;
dc->di.lstart = lstart;
dc->di.start = start;
dc->di.len = len;
dc->ref = 0;
dc->state = D_PREP;
dc->queued = 0;
dc->error = 0;
init_completion(&dc->wait);
list_add_tail(&dc->list, pend_list);
spin_lock_init(&dc->lock);
dc->bio_ref = 0;
atomic_inc(&dcc->discard_cmd_cnt);
dcc->undiscard_blks += len;
return dc;
}
static bool f2fs_check_discard_tree(struct f2fs_sb_info *sbi)
{
#ifdef CONFIG_F2FS_CHECK_FS
struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
struct rb_node *cur = rb_first_cached(&dcc->root), *next;
struct discard_cmd *cur_dc, *next_dc;
while (cur) {
next = rb_next(cur);
if (!next)
return true;
cur_dc = rb_entry(cur, struct discard_cmd, rb_node);
next_dc = rb_entry(next, struct discard_cmd, rb_node);
if (cur_dc->di.lstart + cur_dc->di.len > next_dc->di.lstart) {
f2fs_info(sbi, "broken discard_rbtree, "
"cur(%u, %u) next(%u, %u)",
cur_dc->di.lstart, cur_dc->di.len,
next_dc->di.lstart, next_dc->di.len);
return false;
}
cur = next;
}
#endif
return true;
}
static struct discard_cmd *__lookup_discard_cmd(struct f2fs_sb_info *sbi,
block_t blkaddr)
{
struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
struct rb_node *node = dcc->root.rb_root.rb_node;
struct discard_cmd *dc;
while (node) {
dc = rb_entry(node, struct discard_cmd, rb_node);
if (blkaddr < dc->di.lstart)
node = node->rb_left;
else if (blkaddr >= dc->di.lstart + dc->di.len)
node = node->rb_right;
else
return dc;
}
return NULL;
}
static struct discard_cmd *__lookup_discard_cmd_ret(struct rb_root_cached *root,
block_t blkaddr,
struct discard_cmd **prev_entry,
struct discard_cmd **next_entry,
struct rb_node ***insert_p,
struct rb_node **insert_parent)
{
struct rb_node **pnode = &root->rb_root.rb_node;
struct rb_node *parent = NULL, *tmp_node;
struct discard_cmd *dc;
*insert_p = NULL;
*insert_parent = NULL;
*prev_entry = NULL;
*next_entry = NULL;
if (RB_EMPTY_ROOT(&root->rb_root))
return NULL;
while (*pnode) {
parent = *pnode;
dc = rb_entry(*pnode, struct discard_cmd, rb_node);
if (blkaddr < dc->di.lstart)
pnode = &(*pnode)->rb_left;
else if (blkaddr >= dc->di.lstart + dc->di.len)
pnode = &(*pnode)->rb_right;
else
goto lookup_neighbors;
}
*insert_p = pnode;
*insert_parent = parent;
dc = rb_entry(parent, struct discard_cmd, rb_node);
tmp_node = parent;
if (parent && blkaddr > dc->di.lstart)
tmp_node = rb_next(parent);
*next_entry = rb_entry_safe(tmp_node, struct discard_cmd, rb_node);
tmp_node = parent;
if (parent && blkaddr < dc->di.lstart)
tmp_node = rb_prev(parent);
*prev_entry = rb_entry_safe(tmp_node, struct discard_cmd, rb_node);
return NULL;
lookup_neighbors:
/* lookup prev node for merging backward later */
tmp_node = rb_prev(&dc->rb_node);
*prev_entry = rb_entry_safe(tmp_node, struct discard_cmd, rb_node);
/* lookup next node for merging frontward later */
tmp_node = rb_next(&dc->rb_node);
*next_entry = rb_entry_safe(tmp_node, struct discard_cmd, rb_node);
return dc;
}
static void __detach_discard_cmd(struct discard_cmd_control *dcc,
struct discard_cmd *dc)
{
if (dc->state == D_DONE)
atomic_sub(dc->queued, &dcc->queued_discard);
list_del(&dc->list);
rb_erase_cached(&dc->rb_node, &dcc->root);
dcc->undiscard_blks -= dc->di.len;
kmem_cache_free(discard_cmd_slab, dc);
atomic_dec(&dcc->discard_cmd_cnt);
}
static void __remove_discard_cmd(struct f2fs_sb_info *sbi,
struct discard_cmd *dc)
{
struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
unsigned long flags;
trace_f2fs_remove_discard(dc->bdev, dc->di.start, dc->di.len);
spin_lock_irqsave(&dc->lock, flags);
if (dc->bio_ref) {
spin_unlock_irqrestore(&dc->lock, flags);
return;
}
spin_unlock_irqrestore(&dc->lock, flags);
f2fs_bug_on(sbi, dc->ref);
if (dc->error == -EOPNOTSUPP)
dc->error = 0;
if (dc->error)
f2fs_info_ratelimited(sbi,
"Issue discard(%u, %u, %u) failed, ret: %d",
dc->di.lstart, dc->di.start, dc->di.len, dc->error);
__detach_discard_cmd(dcc, dc);
}
static void f2fs_submit_discard_endio(struct bio *bio)
{
struct discard_cmd *dc = (struct discard_cmd *)bio->bi_private;
unsigned long flags;
spin_lock_irqsave(&dc->lock, flags);
if (!dc->error)
dc->error = blk_status_to_errno(bio->bi_status);
dc->bio_ref--;
if (!dc->bio_ref && dc->state == D_SUBMIT) {
dc->state = D_DONE;
complete_all(&dc->wait);
}
spin_unlock_irqrestore(&dc->lock, flags);
bio_put(bio);
}
static void __check_sit_bitmap(struct f2fs_sb_info *sbi,
block_t start, block_t end)
{
#ifdef CONFIG_F2FS_CHECK_FS
struct seg_entry *sentry;
unsigned int segno;
block_t blk = start;
unsigned long offset, size, *map;
while (blk < end) {
segno = GET_SEGNO(sbi, blk);
sentry = get_seg_entry(sbi, segno);
offset = GET_BLKOFF_FROM_SEG0(sbi, blk);
if (end < START_BLOCK(sbi, segno + 1))
size = GET_BLKOFF_FROM_SEG0(sbi, end);
else
size = BLKS_PER_SEG(sbi);
map = (unsigned long *)(sentry->cur_valid_map);
offset = __find_rev_next_bit(map, size, offset);
f2fs_bug_on(sbi, offset != size);
blk = START_BLOCK(sbi, segno + 1);
}
#endif
}
static void __init_discard_policy(struct f2fs_sb_info *sbi,
struct discard_policy *dpolicy,
int discard_type, unsigned int granularity)
{
struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
/* common policy */
dpolicy->type = discard_type;
dpolicy->sync = true;
dpolicy->ordered = false;
dpolicy->granularity = granularity;
dpolicy->max_requests = dcc->max_discard_request;
dpolicy->io_aware_gran = dcc->discard_io_aware_gran;
dpolicy->timeout = false;
if (discard_type == DPOLICY_BG) {
dpolicy->min_interval = dcc->min_discard_issue_time;
dpolicy->mid_interval = dcc->mid_discard_issue_time;
dpolicy->max_interval = dcc->max_discard_issue_time;
if (dcc->discard_io_aware == DPOLICY_IO_AWARE_ENABLE)
dpolicy->io_aware = true;
else if (dcc->discard_io_aware == DPOLICY_IO_AWARE_DISABLE)
dpolicy->io_aware = false;
dpolicy->sync = false;
dpolicy->ordered = true;
if (utilization(sbi) > dcc->discard_urgent_util) {
dpolicy->granularity = MIN_DISCARD_GRANULARITY;
if (atomic_read(&dcc->discard_cmd_cnt))
dpolicy->max_interval =
dcc->min_discard_issue_time;
}
} else if (discard_type == DPOLICY_FORCE) {
dpolicy->min_interval = dcc->min_discard_issue_time;
dpolicy->mid_interval = dcc->mid_discard_issue_time;
dpolicy->max_interval = dcc->max_discard_issue_time;
dpolicy->io_aware = false;
} else if (discard_type == DPOLICY_FSTRIM) {
dpolicy->io_aware = false;
} else if (discard_type == DPOLICY_UMOUNT) {
dpolicy->io_aware = false;
/* we need to issue all to keep CP_TRIMMED_FLAG */
dpolicy->granularity = MIN_DISCARD_GRANULARITY;
dpolicy->timeout = true;
}
}
static void __update_discard_tree_range(struct f2fs_sb_info *sbi,
struct block_device *bdev, block_t lstart,
block_t start, block_t len);
#ifdef CONFIG_BLK_DEV_ZONED
static void __submit_zone_reset_cmd(struct f2fs_sb_info *sbi,
struct discard_cmd *dc, blk_opf_t flag,
struct list_head *wait_list,
unsigned int *issued)
{
struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
struct block_device *bdev = dc->bdev;
struct bio *bio = bio_alloc(bdev, 0, REQ_OP_ZONE_RESET | flag, GFP_NOFS);
unsigned long flags;
trace_f2fs_issue_reset_zone(bdev, dc->di.start);
spin_lock_irqsave(&dc->lock, flags);
dc->state = D_SUBMIT;
dc->bio_ref++;
spin_unlock_irqrestore(&dc->lock, flags);
if (issued)
(*issued)++;
atomic_inc(&dcc->queued_discard);
dc->queued++;
list_move_tail(&dc->list, wait_list);
/* sanity check on discard range */
__check_sit_bitmap(sbi, dc->di.lstart, dc->di.lstart + dc->di.len);
bio->bi_iter.bi_sector = SECTOR_FROM_BLOCK(dc->di.start);
bio->bi_private = dc;
bio->bi_end_io = f2fs_submit_discard_endio;
submit_bio(bio);
atomic_inc(&dcc->issued_discard);
f2fs_update_iostat(sbi, NULL, FS_ZONE_RESET_IO, dc->di.len * F2FS_BLKSIZE);
}
#endif
/* this function is copied from blkdev_issue_discard from block/blk-lib.c */
static int __submit_discard_cmd(struct f2fs_sb_info *sbi,
struct discard_policy *dpolicy,
struct discard_cmd *dc, int *issued)
{
struct block_device *bdev = dc->bdev;
unsigned int max_discard_blocks =
SECTOR_TO_BLOCK(bdev_max_discard_sectors(bdev));
struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
struct list_head *wait_list = (dpolicy->type == DPOLICY_FSTRIM) ?
&(dcc->fstrim_list) : &(dcc->wait_list);
blk_opf_t flag = dpolicy->sync ? REQ_SYNC : 0;
block_t lstart, start, len, total_len;
int err = 0;
if (dc->state != D_PREP)
return 0;
if (is_sbi_flag_set(sbi, SBI_NEED_FSCK))
return 0;
#ifdef CONFIG_BLK_DEV_ZONED
if (f2fs_sb_has_blkzoned(sbi) && bdev_is_zoned(bdev)) {
int devi = f2fs_bdev_index(sbi, bdev);
if (devi < 0)
return -EINVAL;
if (f2fs_blkz_is_seq(sbi, devi, dc->di.start)) {
__submit_zone_reset_cmd(sbi, dc, flag,
wait_list, issued);
return 0;
}
}
#endif
trace_f2fs_issue_discard(bdev, dc->di.start, dc->di.len);
lstart = dc->di.lstart;
start = dc->di.start;
len = dc->di.len;
total_len = len;
dc->di.len = 0;
while (total_len && *issued < dpolicy->max_requests && !err) {
struct bio *bio = NULL;
unsigned long flags;
bool last = true;
if (len > max_discard_blocks) {
len = max_discard_blocks;
last = false;
}
(*issued)++;
if (*issued == dpolicy->max_requests)
last = true;
dc->di.len += len;
if (time_to_inject(sbi, FAULT_DISCARD)) {
err = -EIO;
} else {
err = __blkdev_issue_discard(bdev,
SECTOR_FROM_BLOCK(start),
SECTOR_FROM_BLOCK(len),
GFP_NOFS, &bio);
}
if (err) {
spin_lock_irqsave(&dc->lock, flags);
if (dc->state == D_PARTIAL)
dc->state = D_SUBMIT;
spin_unlock_irqrestore(&dc->lock, flags);
break;
}
f2fs_bug_on(sbi, !bio);
/*
* should keep before submission to avoid D_DONE
* right away
*/
spin_lock_irqsave(&dc->lock, flags);
if (last)
dc->state = D_SUBMIT;
else
dc->state = D_PARTIAL;
dc->bio_ref++;
spin_unlock_irqrestore(&dc->lock, flags);
atomic_inc(&dcc->queued_discard);
dc->queued++;
list_move_tail(&dc->list, wait_list);
/* sanity check on discard range */
__check_sit_bitmap(sbi, lstart, lstart + len);
bio->bi_private = dc;
bio->bi_end_io = f2fs_submit_discard_endio;
bio->bi_opf |= flag;
submit_bio(bio);
atomic_inc(&dcc->issued_discard);
f2fs_update_iostat(sbi, NULL, FS_DISCARD_IO, len * F2FS_BLKSIZE);
lstart += len;
start += len;
total_len -= len;
len = total_len;
}
if (!err && len) {
dcc->undiscard_blks -= len;
__update_discard_tree_range(sbi, bdev, lstart, start, len);
}
return err;
}
static void __insert_discard_cmd(struct f2fs_sb_info *sbi,
struct block_device *bdev, block_t lstart,
block_t start, block_t len)
{
struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
struct rb_node **p = &dcc->root.rb_root.rb_node;
struct rb_node *parent = NULL;
struct discard_cmd *dc;
bool leftmost = true;
/* look up rb tree to find parent node */
while (*p) {
parent = *p;
dc = rb_entry(parent, struct discard_cmd, rb_node);
if (lstart < dc->di.lstart) {
p = &(*p)->rb_left;
} else if (lstart >= dc->di.lstart + dc->di.len) {
p = &(*p)->rb_right;
leftmost = false;
} else {
/* Let's skip to add, if exists */
return;
}
}
dc = __create_discard_cmd(sbi, bdev, lstart, start, len);
rb_link_node(&dc->rb_node, parent, p);
rb_insert_color_cached(&dc->rb_node, &dcc->root, leftmost);
}
static void __relocate_discard_cmd(struct discard_cmd_control *dcc,
struct discard_cmd *dc)
{
list_move_tail(&dc->list, &dcc->pend_list[plist_idx(dc->di.len)]);
}
static void __punch_discard_cmd(struct f2fs_sb_info *sbi,
struct discard_cmd *dc, block_t blkaddr)
{
struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
struct discard_info di = dc->di;
bool modified = false;
if (dc->state == D_DONE || dc->di.len == 1) {
__remove_discard_cmd(sbi, dc);
return;
}
dcc->undiscard_blks -= di.len;
if (blkaddr > di.lstart) {
dc->di.len = blkaddr - dc->di.lstart;
dcc->undiscard_blks += dc->di.len;
__relocate_discard_cmd(dcc, dc);
modified = true;
}
if (blkaddr < di.lstart + di.len - 1) {
if (modified) {
__insert_discard_cmd(sbi, dc->bdev, blkaddr + 1,
di.start + blkaddr + 1 - di.lstart,
di.lstart + di.len - 1 - blkaddr);
} else {
dc->di.lstart++;
dc->di.len--;
dc->di.start++;
dcc->undiscard_blks += dc->di.len;
__relocate_discard_cmd(dcc, dc);
}
}
}
static void __update_discard_tree_range(struct f2fs_sb_info *sbi,
struct block_device *bdev, block_t lstart,
block_t start, block_t len)
{
struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
struct discard_cmd *prev_dc = NULL, *next_dc = NULL;
struct discard_cmd *dc;
struct discard_info di = {0};
struct rb_node **insert_p = NULL, *insert_parent = NULL;
unsigned int max_discard_blocks =
SECTOR_TO_BLOCK(bdev_max_discard_sectors(bdev));
block_t end = lstart + len;
dc = __lookup_discard_cmd_ret(&dcc->root, lstart,
&prev_dc, &next_dc, &insert_p, &insert_parent);
if (dc)
prev_dc = dc;
if (!prev_dc) {
di.lstart = lstart;
di.len = next_dc ? next_dc->di.lstart - lstart : len;
di.len = min(di.len, len);
di.start = start;
}
while (1) {
struct rb_node *node;
bool merged = false;
struct discard_cmd *tdc = NULL;
if (prev_dc) {
di.lstart = prev_dc->di.lstart + prev_dc->di.len;
if (di.lstart < lstart)
di.lstart = lstart;
if (di.lstart >= end)
break;
if (!next_dc || next_dc->di.lstart > end)
di.len = end - di.lstart;
else
di.len = next_dc->di.lstart - di.lstart;
di.start = start + di.lstart - lstart;
}
if (!di.len)
goto next;
if (prev_dc && prev_dc->state == D_PREP &&
prev_dc->bdev == bdev &&
__is_discard_back_mergeable(&di, &prev_dc->di,
max_discard_blocks)) {
prev_dc->di.len += di.len;
dcc->undiscard_blks += di.len;
__relocate_discard_cmd(dcc, prev_dc);
di = prev_dc->di;
tdc = prev_dc;
merged = true;
}
if (next_dc && next_dc->state == D_PREP &&
next_dc->bdev == bdev &&
__is_discard_front_mergeable(&di, &next_dc->di,
max_discard_blocks)) {
next_dc->di.lstart = di.lstart;
next_dc->di.len += di.len;
next_dc->di.start = di.start;
dcc->undiscard_blks += di.len;
__relocate_discard_cmd(dcc, next_dc);
if (tdc)
__remove_discard_cmd(sbi, tdc);
merged = true;
}
if (!merged)
__insert_discard_cmd(sbi, bdev,
di.lstart, di.start, di.len);
next:
prev_dc = next_dc;
if (!prev_dc)
break;
node = rb_next(&prev_dc->rb_node);
next_dc = rb_entry_safe(node, struct discard_cmd, rb_node);
}
}
#ifdef CONFIG_BLK_DEV_ZONED
static void __queue_zone_reset_cmd(struct f2fs_sb_info *sbi,
struct block_device *bdev, block_t blkstart, block_t lblkstart,
block_t blklen)
{
trace_f2fs_queue_reset_zone(bdev, blkstart);
mutex_lock(&SM_I(sbi)->dcc_info->cmd_lock);
__insert_discard_cmd(sbi, bdev, lblkstart, blkstart, blklen);
mutex_unlock(&SM_I(sbi)->dcc_info->cmd_lock);
}
#endif
static void __queue_discard_cmd(struct f2fs_sb_info *sbi,
struct block_device *bdev, block_t blkstart, block_t blklen)
{
block_t lblkstart = blkstart;
if (!f2fs_bdev_support_discard(bdev))
return;
trace_f2fs_queue_discard(bdev, blkstart, blklen);
if (f2fs_is_multi_device(sbi)) {
int devi = f2fs_target_device_index(sbi, blkstart);
blkstart -= FDEV(devi).start_blk;
}
mutex_lock(&SM_I(sbi)->dcc_info->cmd_lock);
__update_discard_tree_range(sbi, bdev, lblkstart, blkstart, blklen);
mutex_unlock(&SM_I(sbi)->dcc_info->cmd_lock);
}
static void __issue_discard_cmd_orderly(struct f2fs_sb_info *sbi,
struct discard_policy *dpolicy, int *issued)
{
struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
struct discard_cmd *prev_dc = NULL, *next_dc = NULL;
struct rb_node **insert_p = NULL, *insert_parent = NULL;
struct discard_cmd *dc;
struct blk_plug plug;
bool io_interrupted = false;
mutex_lock(&dcc->cmd_lock);
dc = __lookup_discard_cmd_ret(&dcc->root, dcc->next_pos,
&prev_dc, &next_dc, &insert_p, &insert_parent);
if (!dc)
dc = next_dc;
blk_start_plug(&plug);
while (dc) {
struct rb_node *node;
int err = 0;
if (dc->state != D_PREP)
goto next;
if (dpolicy->io_aware && !is_idle(sbi, DISCARD_TIME)) {
io_interrupted = true;
break;
}
dcc->next_pos = dc->di.lstart + dc->di.len;
err = __submit_discard_cmd(sbi, dpolicy, dc, issued);
if (*issued >= dpolicy->max_requests)
break;
next:
node = rb_next(&dc->rb_node);
if (err)
__remove_discard_cmd(sbi, dc);
dc = rb_entry_safe(node, struct discard_cmd, rb_node);
}
blk_finish_plug(&plug);
if (!dc)
dcc->next_pos = 0;
mutex_unlock(&dcc->cmd_lock);
if (!(*issued) && io_interrupted)
*issued = -1;
}
static unsigned int __wait_all_discard_cmd(struct f2fs_sb_info *sbi,
struct discard_policy *dpolicy);
static int __issue_discard_cmd(struct f2fs_sb_info *sbi,
struct discard_policy *dpolicy)
{
struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
struct list_head *pend_list;
struct discard_cmd *dc, *tmp;
struct blk_plug plug;
int i, issued;
bool io_interrupted = false;
if (dpolicy->timeout)
f2fs_update_time(sbi, UMOUNT_DISCARD_TIMEOUT);
retry:
issued = 0;
for (i = MAX_PLIST_NUM - 1; i >= 0; i--) {
if (dpolicy->timeout &&
f2fs_time_over(sbi, UMOUNT_DISCARD_TIMEOUT))
break;
if (i + 1 < dpolicy->granularity)
break;
if (i + 1 < dcc->max_ordered_discard && dpolicy->ordered) {
__issue_discard_cmd_orderly(sbi, dpolicy, &issued);
return issued;
}
pend_list = &dcc->pend_list[i];
mutex_lock(&dcc->cmd_lock);
if (list_empty(pend_list))
goto next;
if (unlikely(dcc->rbtree_check))
f2fs_bug_on(sbi, !f2fs_check_discard_tree(sbi));
blk_start_plug(&plug);
list_for_each_entry_safe(dc, tmp, pend_list, list) {
f2fs_bug_on(sbi, dc->state != D_PREP);
if (dpolicy->timeout &&
f2fs_time_over(sbi, UMOUNT_DISCARD_TIMEOUT))
break;
if (dpolicy->io_aware && i < dpolicy->io_aware_gran &&
!is_idle(sbi, DISCARD_TIME)) {
io_interrupted = true;
break;
}
__submit_discard_cmd(sbi, dpolicy, dc, &issued);
if (issued >= dpolicy->max_requests)
break;
}
blk_finish_plug(&plug);
next:
mutex_unlock(&dcc->cmd_lock);
if (issued >= dpolicy->max_requests || io_interrupted)
break;
}
if (dpolicy->type == DPOLICY_UMOUNT && issued) {
__wait_all_discard_cmd(sbi, dpolicy);
goto retry;
}
if (!issued && io_interrupted)
issued = -1;
return issued;
}
static bool __drop_discard_cmd(struct f2fs_sb_info *sbi)
{
struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
struct list_head *pend_list;
struct discard_cmd *dc, *tmp;
int i;
bool dropped = false;
mutex_lock(&dcc->cmd_lock);
for (i = MAX_PLIST_NUM - 1; i >= 0; i--) {
pend_list = &dcc->pend_list[i];
list_for_each_entry_safe(dc, tmp, pend_list, list) {
f2fs_bug_on(sbi, dc->state != D_PREP);
__remove_discard_cmd(sbi, dc);
dropped = true;
}
}
mutex_unlock(&dcc->cmd_lock);
return dropped;
}
void f2fs_drop_discard_cmd(struct f2fs_sb_info *sbi)
{
__drop_discard_cmd(sbi);
}
static unsigned int __wait_one_discard_bio(struct f2fs_sb_info *sbi,
struct discard_cmd *dc)
{
struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
unsigned int len = 0;
wait_for_completion_io(&dc->wait);
mutex_lock(&dcc->cmd_lock);
f2fs_bug_on(sbi, dc->state != D_DONE);
dc->ref--;
if (!dc->ref) {
if (!dc->error)
len = dc->di.len;
__remove_discard_cmd(sbi, dc);
}
mutex_unlock(&dcc->cmd_lock);
return len;
}
static unsigned int __wait_discard_cmd_range(struct f2fs_sb_info *sbi,
struct discard_policy *dpolicy,
block_t start, block_t end)
{
struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
struct list_head *wait_list = (dpolicy->type == DPOLICY_FSTRIM) ?
&(dcc->fstrim_list) : &(dcc->wait_list);
struct discard_cmd *dc = NULL, *iter, *tmp;
unsigned int trimmed = 0;
next:
dc = NULL;
mutex_lock(&dcc->cmd_lock);
list_for_each_entry_safe(iter, tmp, wait_list, list) {
if (iter->di.lstart + iter->di.len <= start ||
end <= iter->di.lstart)
continue;
if (iter->di.len < dpolicy->granularity)
continue;
if (iter->state == D_DONE && !iter->ref) {
wait_for_completion_io(&iter->wait);
if (!iter->error)
trimmed += iter->di.len;
__remove_discard_cmd(sbi, iter);
} else {
iter->ref++;
dc = iter;
break;
}
}
mutex_unlock(&dcc->cmd_lock);
if (dc) {
trimmed += __wait_one_discard_bio(sbi, dc);
goto next;
}
return trimmed;
}
static unsigned int __wait_all_discard_cmd(struct f2fs_sb_info *sbi,
struct discard_policy *dpolicy)
{
struct discard_policy dp;
unsigned int discard_blks;
if (dpolicy)
return __wait_discard_cmd_range(sbi, dpolicy, 0, UINT_MAX);
/* wait all */
__init_discard_policy(sbi, &dp, DPOLICY_FSTRIM, MIN_DISCARD_GRANULARITY);
discard_blks = __wait_discard_cmd_range(sbi, &dp, 0, UINT_MAX);
__init_discard_policy(sbi, &dp, DPOLICY_UMOUNT, MIN_DISCARD_GRANULARITY);
discard_blks += __wait_discard_cmd_range(sbi, &dp, 0, UINT_MAX);
return discard_blks;
}
/* This should be covered by global mutex, &sit_i->sentry_lock */
static void f2fs_wait_discard_bio(struct f2fs_sb_info *sbi, block_t blkaddr)
{
struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
struct discard_cmd *dc;
bool need_wait = false;
mutex_lock(&dcc->cmd_lock);
dc = __lookup_discard_cmd(sbi, blkaddr);
#ifdef CONFIG_BLK_DEV_ZONED
if (dc && f2fs_sb_has_blkzoned(sbi) && bdev_is_zoned(dc->bdev)) {
int devi = f2fs_bdev_index(sbi, dc->bdev);
if (devi < 0) {
mutex_unlock(&dcc->cmd_lock);
return;
}
if (f2fs_blkz_is_seq(sbi, devi, dc->di.start)) {
/* force submit zone reset */
if (dc->state == D_PREP)
__submit_zone_reset_cmd(sbi, dc, REQ_SYNC,
&dcc->wait_list, NULL);
dc->ref++;
mutex_unlock(&dcc->cmd_lock);
/* wait zone reset */
__wait_one_discard_bio(sbi, dc);
return;
}
}
#endif
if (dc) {
if (dc->state == D_PREP) {
__punch_discard_cmd(sbi, dc, blkaddr);
} else {
dc->ref++;
need_wait = true;
}
}
mutex_unlock(&dcc->cmd_lock);
if (need_wait)
__wait_one_discard_bio(sbi, dc);
}
void f2fs_stop_discard_thread(struct f2fs_sb_info *sbi)
{
struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
if (dcc && dcc->f2fs_issue_discard) {
struct task_struct *discard_thread = dcc->f2fs_issue_discard;
dcc->f2fs_issue_discard = NULL;
kthread_stop(discard_thread);
}
}
/**
* f2fs_issue_discard_timeout() - Issue all discard cmd within UMOUNT_DISCARD_TIMEOUT
* @sbi: the f2fs_sb_info data for discard cmd to issue
*
* When UMOUNT_DISCARD_TIMEOUT is exceeded, all remaining discard commands will be dropped
*
* Return true if issued all discard cmd or no discard cmd need issue, otherwise return false.
*/
bool f2fs_issue_discard_timeout(struct f2fs_sb_info *sbi)
{
struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
struct discard_policy dpolicy;
bool dropped;
if (!atomic_read(&dcc->discard_cmd_cnt))
return true;
__init_discard_policy(sbi, &dpolicy, DPOLICY_UMOUNT,
dcc->discard_granularity);
__issue_discard_cmd(sbi, &dpolicy);
dropped = __drop_discard_cmd(sbi);
/* just to make sure there is no pending discard commands */
__wait_all_discard_cmd(sbi, NULL);
f2fs_bug_on(sbi, atomic_read(&dcc->discard_cmd_cnt));
return !dropped;
}
static int issue_discard_thread(void *data)
{
struct f2fs_sb_info *sbi = data;
struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
wait_queue_head_t *q = &dcc->discard_wait_queue;
struct discard_policy dpolicy;
unsigned int wait_ms = dcc->min_discard_issue_time;
int issued;
set_freezable();
do {
wait_event_freezable_timeout(*q,
kthread_should_stop() || dcc->discard_wake,
msecs_to_jiffies(wait_ms));
if (sbi->gc_mode == GC_URGENT_HIGH ||
!f2fs_available_free_memory(sbi, DISCARD_CACHE))
__init_discard_policy(sbi, &dpolicy, DPOLICY_FORCE,
MIN_DISCARD_GRANULARITY);
else
__init_discard_policy(sbi, &dpolicy, DPOLICY_BG,
dcc->discard_granularity);
if (dcc->discard_wake)
dcc->discard_wake = false;
/* clean up pending candidates before going to sleep */
if (atomic_read(&dcc->queued_discard))
__wait_all_discard_cmd(sbi, NULL);
if (f2fs_readonly(sbi->sb))
continue;
if (kthread_should_stop())
return 0;
if (is_sbi_flag_set(sbi, SBI_NEED_FSCK) ||
!atomic_read(&dcc->discard_cmd_cnt)) {
wait_ms = dpolicy.max_interval;
continue;
}
sb_start_intwrite(sbi->sb);
issued = __issue_discard_cmd(sbi, &dpolicy);
if (issued > 0) {
__wait_all_discard_cmd(sbi, &dpolicy);
wait_ms = dpolicy.min_interval;
} else if (issued == -1) {
wait_ms = f2fs_time_to_wait(sbi, DISCARD_TIME);
if (!wait_ms)
wait_ms = dpolicy.mid_interval;
} else {
wait_ms = dpolicy.max_interval;
}
if (!atomic_read(&dcc->discard_cmd_cnt))
wait_ms = dpolicy.max_interval;
sb_end_intwrite(sbi->sb);
} while (!kthread_should_stop());
return 0;
}
#ifdef CONFIG_BLK_DEV_ZONED
static int __f2fs_issue_discard_zone(struct f2fs_sb_info *sbi,
struct block_device *bdev, block_t blkstart, block_t blklen)
{
sector_t sector, nr_sects;
block_t lblkstart = blkstart;
int devi = 0;
u64 remainder = 0;
if (f2fs_is_multi_device(sbi)) {
devi = f2fs_target_device_index(sbi, blkstart);
if (blkstart < FDEV(devi).start_blk ||
blkstart > FDEV(devi).end_blk) {
f2fs_err(sbi, "Invalid block %x", blkstart);
return -EIO;
}
blkstart -= FDEV(devi).start_blk;
}
/* For sequential zones, reset the zone write pointer */
if (f2fs_blkz_is_seq(sbi, devi, blkstart)) {
sector = SECTOR_FROM_BLOCK(blkstart);
nr_sects = SECTOR_FROM_BLOCK(blklen);
div64_u64_rem(sector, bdev_zone_sectors(bdev), &remainder);
if (remainder || nr_sects != bdev_zone_sectors(bdev)) {
f2fs_err(sbi, "(%d) %s: Unaligned zone reset attempted (block %x + %x)",
devi, sbi->s_ndevs ? FDEV(devi).path : "",
blkstart, blklen);
return -EIO;
}
if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING))) {
unsigned int nofs_flags;
int ret;
trace_f2fs_issue_reset_zone(bdev, blkstart);
nofs_flags = memalloc_nofs_save();
ret = blkdev_zone_mgmt(bdev, REQ_OP_ZONE_RESET,
sector, nr_sects);
memalloc_nofs_restore(nofs_flags);
return ret;
}
__queue_zone_reset_cmd(sbi, bdev, blkstart, lblkstart, blklen);
return 0;
}
/* For conventional zones, use regular discard if supported */
__queue_discard_cmd(sbi, bdev, lblkstart, blklen);
return 0;
}
#endif
static int __issue_discard_async(struct f2fs_sb_info *sbi,
struct block_device *bdev, block_t blkstart, block_t blklen)
{
#ifdef CONFIG_BLK_DEV_ZONED
if (f2fs_sb_has_blkzoned(sbi) && bdev_is_zoned(bdev))
return __f2fs_issue_discard_zone(sbi, bdev, blkstart, blklen);
#endif
__queue_discard_cmd(sbi, bdev, blkstart, blklen);
return 0;
}
static int f2fs_issue_discard(struct f2fs_sb_info *sbi,
block_t blkstart, block_t blklen)
{
sector_t start = blkstart, len = 0;
struct block_device *bdev;
struct seg_entry *se;
unsigned int offset;
block_t i;
int err = 0;
bdev = f2fs_target_device(sbi, blkstart, NULL);
for (i = blkstart; i < blkstart + blklen; i++, len++) {
if (i != start) {
struct block_device *bdev2 =
f2fs_target_device(sbi, i, NULL);
if (bdev2 != bdev) {
err = __issue_discard_async(sbi, bdev,
start, len);
if (err)
return err;
bdev = bdev2;
start = i;
len = 0;
}
}
se = get_seg_entry(sbi, GET_SEGNO(sbi, i));
offset = GET_BLKOFF_FROM_SEG0(sbi, i);
if (f2fs_block_unit_discard(sbi) &&
!f2fs_test_and_set_bit(offset, se->discard_map))
sbi->discard_blks--;
}
if (len)
err = __issue_discard_async(sbi, bdev, start, len);
return err;
}
static bool add_discard_addrs(struct f2fs_sb_info *sbi, struct cp_control *cpc,
bool check_only)
{
int entries = SIT_VBLOCK_MAP_SIZE / sizeof(unsigned long);
struct seg_entry *se = get_seg_entry(sbi, cpc->trim_start);
unsigned long *cur_map = (unsigned long *)se->cur_valid_map;
unsigned long *ckpt_map = (unsigned long *)se->ckpt_valid_map;
unsigned long *discard_map = (unsigned long *)se->discard_map;
unsigned long *dmap = SIT_I(sbi)->tmp_map;
unsigned int start = 0, end = -1;
bool force = (cpc->reason & CP_DISCARD);
struct discard_entry *de = NULL;
struct list_head *head = &SM_I(sbi)->dcc_info->entry_list;
int i;
if (se->valid_blocks == BLKS_PER_SEG(sbi) ||
!f2fs_hw_support_discard(sbi) ||
!f2fs_block_unit_discard(sbi))
return false;
if (!force) {
if (!f2fs_realtime_discard_enable(sbi) || !se->valid_blocks ||
SM_I(sbi)->dcc_info->nr_discards >=
SM_I(sbi)->dcc_info->max_discards)
return false;
}
/* SIT_VBLOCK_MAP_SIZE should be multiple of sizeof(unsigned long) */
for (i = 0; i < entries; i++)
dmap[i] = force ? ~ckpt_map[i] & ~discard_map[i] :
(cur_map[i] ^ ckpt_map[i]) & ckpt_map[i];
while (force || SM_I(sbi)->dcc_info->nr_discards <=
SM_I(sbi)->dcc_info->max_discards) {
start = __find_rev_next_bit(dmap, BLKS_PER_SEG(sbi), end + 1);
if (start >= BLKS_PER_SEG(sbi))
break;
end = __find_rev_next_zero_bit(dmap,
BLKS_PER_SEG(sbi), start + 1);
if (force && start && end != BLKS_PER_SEG(sbi) &&
(end - start) < cpc->trim_minlen)
continue;
if (check_only)
return true;
if (!de) {
de = f2fs_kmem_cache_alloc(discard_entry_slab,
GFP_F2FS_ZERO, true, NULL);
de->start_blkaddr = START_BLOCK(sbi, cpc->trim_start);
list_add_tail(&de->list, head);
}
for (i = start; i < end; i++)
__set_bit_le(i, (void *)de->discard_map);
SM_I(sbi)->dcc_info->nr_discards += end - start;
}
return false;
}
static void release_discard_addr(struct discard_entry *entry)
{
list_del(&entry->list);
kmem_cache_free(discard_entry_slab, entry);
}
void f2fs_release_discard_addrs(struct f2fs_sb_info *sbi)
{
struct list_head *head = &(SM_I(sbi)->dcc_info->entry_list);
struct discard_entry *entry, *this;
/* drop caches */
list_for_each_entry_safe(entry, this, head, list)
release_discard_addr(entry);
}
/*
* Should call f2fs_clear_prefree_segments after checkpoint is done.
*/
static void set_prefree_as_free_segments(struct f2fs_sb_info *sbi)
{
struct dirty_seglist_info *dirty_i = DIRTY_I(sbi);
unsigned int segno;
mutex_lock(&dirty_i->seglist_lock);
for_each_set_bit(segno, dirty_i->dirty_segmap[PRE], MAIN_SEGS(sbi))
__set_test_and_free(sbi, segno, false);
mutex_unlock(&dirty_i->seglist_lock);
}
void f2fs_clear_prefree_segments(struct f2fs_sb_info *sbi,
struct cp_control *cpc)
{
struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
struct list_head *head = &dcc->entry_list;
struct discard_entry *entry, *this;
struct dirty_seglist_info *dirty_i = DIRTY_I(sbi);
unsigned long *prefree_map = dirty_i->dirty_segmap[PRE];
unsigned int start = 0, end = -1;
unsigned int secno, start_segno;
bool force = (cpc->reason & CP_DISCARD);
bool section_alignment = F2FS_OPTION(sbi).discard_unit ==
DISCARD_UNIT_SECTION;
if (f2fs_lfs_mode(sbi) && __is_large_section(sbi))
section_alignment = true;
mutex_lock(&dirty_i->seglist_lock);
while (1) {
int i;
if (section_alignment && end != -1)
end--;
start = find_next_bit(prefree_map, MAIN_SEGS(sbi), end + 1);
if (start >= MAIN_SEGS(sbi))
break;
end = find_next_zero_bit(prefree_map, MAIN_SEGS(sbi),
start + 1);
if (section_alignment) {
start = rounddown(start, SEGS_PER_SEC(sbi));
end = roundup(end, SEGS_PER_SEC(sbi));
}
for (i = start; i < end; i++) {
if (test_and_clear_bit(i, prefree_map))
dirty_i->nr_dirty[PRE]--;
}
if (!f2fs_realtime_discard_enable(sbi))
continue;
if (force && start >= cpc->trim_start &&
(end - 1) <= cpc->trim_end)
continue;
/* Should cover 2MB zoned device for zone-based reset */
if (!f2fs_sb_has_blkzoned(sbi) &&
(!f2fs_lfs_mode(sbi) || !__is_large_section(sbi))) {
f2fs_issue_discard(sbi, START_BLOCK(sbi, start),
SEGS_TO_BLKS(sbi, end - start));
continue;
}
next:
secno = GET_SEC_FROM_SEG(sbi, start);
start_segno = GET_SEG_FROM_SEC(sbi, secno);
if (!IS_CURSEC(sbi, secno) &&
!get_valid_blocks(sbi, start, true))
f2fs_issue_discard(sbi, START_BLOCK(sbi, start_segno),
BLKS_PER_SEC(sbi));
start = start_segno + SEGS_PER_SEC(sbi);
if (start < end)
goto next;
else
end = start - 1;
}
mutex_unlock(&dirty_i->seglist_lock);
if (!f2fs_block_unit_discard(sbi))
goto wakeup;
/* send small discards */
list_for_each_entry_safe(entry, this, head, list) {
unsigned int cur_pos = 0, next_pos, len, total_len = 0;
bool is_valid = test_bit_le(0, entry->discard_map);
find_next:
if (is_valid) {
next_pos = find_next_zero_bit_le(entry->discard_map,
BLKS_PER_SEG(sbi), cur_pos);
len = next_pos - cur_pos;
if (f2fs_sb_has_blkzoned(sbi) ||
(force && len < cpc->trim_minlen))
goto skip;
f2fs_issue_discard(sbi, entry->start_blkaddr + cur_pos,
len);
total_len += len;
} else {
next_pos = find_next_bit_le(entry->discard_map,
BLKS_PER_SEG(sbi), cur_pos);
}
skip:
cur_pos = next_pos;
is_valid = !is_valid;
if (cur_pos < BLKS_PER_SEG(sbi))
goto find_next;
release_discard_addr(entry);
dcc->nr_discards -= total_len;
}
wakeup:
wake_up_discard_thread(sbi, false);
}
int f2fs_start_discard_thread(struct f2fs_sb_info *sbi)
{
dev_t dev = sbi->sb->s_bdev->bd_dev;
struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
int err = 0;
if (f2fs_sb_has_readonly(sbi)) {
f2fs_info(sbi,
"Skip to start discard thread for readonly image");
return 0;
}
if (!f2fs_realtime_discard_enable(sbi))
return 0;
dcc->f2fs_issue_discard = kthread_run(issue_discard_thread, sbi,
"f2fs_discard-%u:%u", MAJOR(dev), MINOR(dev));
if (IS_ERR(dcc->f2fs_issue_discard)) {
err = PTR_ERR(dcc->f2fs_issue_discard);
dcc->f2fs_issue_discard = NULL;
}
return err;
}
static int create_discard_cmd_control(struct f2fs_sb_info *sbi)
{
struct discard_cmd_control *dcc;
int err = 0, i;
if (SM_I(sbi)->dcc_info) {
dcc = SM_I(sbi)->dcc_info;
goto init_thread;
}
dcc = f2fs_kzalloc(sbi, sizeof(struct discard_cmd_control), GFP_KERNEL);
if (!dcc)
return -ENOMEM;
dcc->discard_io_aware_gran = MAX_PLIST_NUM;
dcc->discard_granularity = DEFAULT_DISCARD_GRANULARITY;
dcc->max_ordered_discard = DEFAULT_MAX_ORDERED_DISCARD_GRANULARITY;
dcc->discard_io_aware = DPOLICY_IO_AWARE_ENABLE;
if (F2FS_OPTION(sbi).discard_unit == DISCARD_UNIT_SEGMENT)
dcc->discard_granularity = BLKS_PER_SEG(sbi);
else if (F2FS_OPTION(sbi).discard_unit == DISCARD_UNIT_SECTION)
dcc->discard_granularity = BLKS_PER_SEC(sbi);
INIT_LIST_HEAD(&dcc->entry_list);
for (i = 0; i < MAX_PLIST_NUM; i++)
INIT_LIST_HEAD(&dcc->pend_list[i]);
INIT_LIST_HEAD(&dcc->wait_list);
INIT_LIST_HEAD(&dcc->fstrim_list);
mutex_init(&dcc->cmd_lock);
atomic_set(&dcc->issued_discard, 0);
atomic_set(&dcc->queued_discard, 0);
atomic_set(&dcc->discard_cmd_cnt, 0);
dcc->nr_discards = 0;
dcc->max_discards = SEGS_TO_BLKS(sbi, MAIN_SEGS(sbi));
dcc->max_discard_request = DEF_MAX_DISCARD_REQUEST;
dcc->min_discard_issue_time = DEF_MIN_DISCARD_ISSUE_TIME;
dcc->mid_discard_issue_time = DEF_MID_DISCARD_ISSUE_TIME;
dcc->max_discard_issue_time = DEF_MAX_DISCARD_ISSUE_TIME;
dcc->discard_urgent_util = DEF_DISCARD_URGENT_UTIL;
dcc->undiscard_blks = 0;
dcc->next_pos = 0;
dcc->root = RB_ROOT_CACHED;
dcc->rbtree_check = false;
init_waitqueue_head(&dcc->discard_wait_queue);
SM_I(sbi)->dcc_info = dcc;
init_thread:
err = f2fs_start_discard_thread(sbi);
if (err) {
kfree(dcc);
SM_I(sbi)->dcc_info = NULL;
}
return err;
}
static void destroy_discard_cmd_control(struct f2fs_sb_info *sbi)
{
struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
if (!dcc)
return;
f2fs_stop_discard_thread(sbi);
/*
* Recovery can cache discard commands, so in error path of
* fill_super(), it needs to give a chance to handle them.
*/
f2fs_issue_discard_timeout(sbi);
kfree(dcc);
SM_I(sbi)->dcc_info = NULL;
}
static bool __mark_sit_entry_dirty(struct f2fs_sb_info *sbi, unsigned int segno)
{
struct sit_info *sit_i = SIT_I(sbi);
if (!__test_and_set_bit(segno, sit_i->dirty_sentries_bitmap)) {
sit_i->dirty_sentries++;
return false;
}
return true;
}
static void __set_sit_entry_type(struct f2fs_sb_info *sbi, int type,
unsigned int segno, int modified)
{
struct seg_entry *se = get_seg_entry(sbi, segno);
se->type = type;
if (modified)
__mark_sit_entry_dirty(sbi, segno);
}
static inline unsigned long long get_segment_mtime(struct f2fs_sb_info *sbi,
block_t blkaddr)
{
unsigned int segno = GET_SEGNO(sbi, blkaddr);
if (segno == NULL_SEGNO)
return 0;
return get_seg_entry(sbi, segno)->mtime;
}
static void update_segment_mtime(struct f2fs_sb_info *sbi, block_t blkaddr,
unsigned long long old_mtime)
{
struct seg_entry *se;
unsigned int segno = GET_SEGNO(sbi, blkaddr);
unsigned long long ctime = get_mtime(sbi, false);
unsigned long long mtime = old_mtime ? old_mtime : ctime;
if (segno == NULL_SEGNO)
return;
se = get_seg_entry(sbi, segno);
if (!se->mtime)
se->mtime = mtime;
else
se->mtime = div_u64(se->mtime * se->valid_blocks + mtime,
se->valid_blocks + 1);
if (ctime > SIT_I(sbi)->max_mtime)
SIT_I(sbi)->max_mtime = ctime;
}
static void update_sit_entry(struct f2fs_sb_info *sbi, block_t blkaddr, int del)
{
struct seg_entry *se;
unsigned int segno, offset;
long int new_vblocks;
bool exist;
#ifdef CONFIG_F2FS_CHECK_FS
bool mir_exist;
#endif
segno = GET_SEGNO(sbi, blkaddr);
if (segno == NULL_SEGNO)
return;
se = get_seg_entry(sbi, segno);
new_vblocks = se->valid_blocks + del;
offset = GET_BLKOFF_FROM_SEG0(sbi, blkaddr);
f2fs_bug_on(sbi, (new_vblocks < 0 ||
(new_vblocks > f2fs_usable_blks_in_seg(sbi, segno))));
se->valid_blocks = new_vblocks;
/* Update valid block bitmap */
if (del > 0) {
exist = f2fs_test_and_set_bit(offset, se->cur_valid_map);
#ifdef CONFIG_F2FS_CHECK_FS
mir_exist = f2fs_test_and_set_bit(offset,
se->cur_valid_map_mir);
if (unlikely(exist != mir_exist)) {
f2fs_err(sbi, "Inconsistent error when setting bitmap, blk:%u, old bit:%d",
blkaddr, exist);
f2fs_bug_on(sbi, 1);
}
#endif
if (unlikely(exist)) {
f2fs_err(sbi, "Bitmap was wrongly set, blk:%u",
blkaddr);
f2fs_bug_on(sbi, 1);
se->valid_blocks--;
del = 0;
}
if (f2fs_block_unit_discard(sbi) &&
!f2fs_test_and_set_bit(offset, se->discard_map))
sbi->discard_blks--;
/*
* SSR should never reuse block which is checkpointed
* or newly invalidated.
*/
if (!is_sbi_flag_set(sbi, SBI_CP_DISABLED)) {
if (!f2fs_test_and_set_bit(offset, se->ckpt_valid_map))
se->ckpt_valid_blocks++;
}
} else {
exist = f2fs_test_and_clear_bit(offset, se->cur_valid_map);
#ifdef CONFIG_F2FS_CHECK_FS
mir_exist = f2fs_test_and_clear_bit(offset,
se->cur_valid_map_mir);
if (unlikely(exist != mir_exist)) {
f2fs_err(sbi, "Inconsistent error when clearing bitmap, blk:%u, old bit:%d",
blkaddr, exist);
f2fs_bug_on(sbi, 1);
}
#endif
if (unlikely(!exist)) {
f2fs_err(sbi, "Bitmap was wrongly cleared, blk:%u",
blkaddr);
f2fs_bug_on(sbi, 1);
se->valid_blocks++;
del = 0;
} else if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED))) {
/*
* If checkpoints are off, we must not reuse data that
* was used in the previous checkpoint. If it was used
* before, we must track that to know how much space we
* really have.
*/
if (f2fs_test_bit(offset, se->ckpt_valid_map)) {
spin_lock(&sbi->stat_lock);
sbi->unusable_block_count++;
spin_unlock(&sbi->stat_lock);
}
}
if (f2fs_block_unit_discard(sbi) &&
f2fs_test_and_clear_bit(offset, se->discard_map))
sbi->discard_blks++;
}
if (!f2fs_test_bit(offset, se->ckpt_valid_map))
se->ckpt_valid_blocks += del;
__mark_sit_entry_dirty(sbi, segno);
/* update total number of valid blocks to be written in ckpt area */
SIT_I(sbi)->written_valid_blocks += del;
if (__is_large_section(sbi))
get_sec_entry(sbi, segno)->valid_blocks += del;
}
void f2fs_invalidate_blocks(struct f2fs_sb_info *sbi, block_t addr)
{
unsigned int segno = GET_SEGNO(sbi, addr);
struct sit_info *sit_i = SIT_I(sbi);
f2fs_bug_on(sbi, addr == NULL_ADDR);
if (addr == NEW_ADDR || addr == COMPRESS_ADDR)
return;
f2fs_invalidate_internal_cache(sbi, addr);
/* add it into sit main buffer */
down_write(&sit_i->sentry_lock);
update_segment_mtime(sbi, addr, 0);
update_sit_entry(sbi, addr, -1);
/* add it into dirty seglist */
locate_dirty_segment(sbi, segno);
up_write(&sit_i->sentry_lock);
}
bool f2fs_is_checkpointed_data(struct f2fs_sb_info *sbi, block_t blkaddr)
{
struct sit_info *sit_i = SIT_I(sbi);
unsigned int segno, offset;
struct seg_entry *se;
bool is_cp = false;
if (!__is_valid_data_blkaddr(blkaddr))
return true;
down_read(&sit_i->sentry_lock);
segno = GET_SEGNO(sbi, blkaddr);
se = get_seg_entry(sbi, segno);
offset = GET_BLKOFF_FROM_SEG0(sbi, blkaddr);
if (f2fs_test_bit(offset, se->ckpt_valid_map))
is_cp = true;
up_read(&sit_i->sentry_lock);
return is_cp;
}
static unsigned short f2fs_curseg_valid_blocks(struct f2fs_sb_info *sbi, int type)
{
struct curseg_info *curseg = CURSEG_I(sbi, type);
if (sbi->ckpt->alloc_type[type] == SSR)
return BLKS_PER_SEG(sbi);
return curseg->next_blkoff;
}
/*
* Calculate the number of current summary pages for writing
*/
int f2fs_npages_for_summary_flush(struct f2fs_sb_info *sbi, bool for_ra)
{
int valid_sum_count = 0;
int i, sum_in_page;
for (i = CURSEG_HOT_DATA; i <= CURSEG_COLD_DATA; i++) {
if (sbi->ckpt->alloc_type[i] != SSR && for_ra)
valid_sum_count +=
le16_to_cpu(F2FS_CKPT(sbi)->cur_data_blkoff[i]);
else
valid_sum_count += f2fs_curseg_valid_blocks(sbi, i);
}
sum_in_page = (PAGE_SIZE - 2 * SUM_JOURNAL_SIZE -
SUM_FOOTER_SIZE) / SUMMARY_SIZE;
if (valid_sum_count <= sum_in_page)
return 1;
else if ((valid_sum_count - sum_in_page) <=
(PAGE_SIZE - SUM_FOOTER_SIZE) / SUMMARY_SIZE)
return 2;
return 3;
}
/*
* Caller should put this summary page
*/
struct page *f2fs_get_sum_page(struct f2fs_sb_info *sbi, unsigned int segno)
{
if (unlikely(f2fs_cp_error(sbi)))
return ERR_PTR(-EIO);
return f2fs_get_meta_page_retry(sbi, GET_SUM_BLOCK(sbi, segno));
}
void f2fs_update_meta_page(struct f2fs_sb_info *sbi,
void *src, block_t blk_addr)
{
struct page *page = f2fs_grab_meta_page(sbi, blk_addr);
memcpy(page_address(page), src, PAGE_SIZE);
set_page_dirty(page);
f2fs_put_page(page, 1);
}
static void write_sum_page(struct f2fs_sb_info *sbi,
struct f2fs_summary_block *sum_blk, block_t blk_addr)
{
f2fs_update_meta_page(sbi, (void *)sum_blk, blk_addr);
}
static void write_current_sum_page(struct f2fs_sb_info *sbi,
int type, block_t blk_addr)
{
struct curseg_info *curseg = CURSEG_I(sbi, type);
struct page *page = f2fs_grab_meta_page(sbi, blk_addr);
struct f2fs_summary_block *src = curseg->sum_blk;
struct f2fs_summary_block *dst;
dst = (struct f2fs_summary_block *)page_address(page);
memset(dst, 0, PAGE_SIZE);
mutex_lock(&curseg->curseg_mutex);
down_read(&curseg->journal_rwsem);
memcpy(&dst->journal, curseg->journal, SUM_JOURNAL_SIZE);
up_read(&curseg->journal_rwsem);
memcpy(dst->entries, src->entries, SUM_ENTRY_SIZE);
memcpy(&dst->footer, &src->footer, SUM_FOOTER_SIZE);
mutex_unlock(&curseg->curseg_mutex);
set_page_dirty(page);
f2fs_put_page(page, 1);
}
static int is_next_segment_free(struct f2fs_sb_info *sbi,
struct curseg_info *curseg)
{
unsigned int segno = curseg->segno + 1;
struct free_segmap_info *free_i = FREE_I(sbi);
if (segno < MAIN_SEGS(sbi) && segno % SEGS_PER_SEC(sbi))
return !test_bit(segno, free_i->free_segmap);
return 0;
}
/*
* Find a new segment from the free segments bitmap to right order
* This function should be returned with success, otherwise BUG
*/
static int get_new_segment(struct f2fs_sb_info *sbi,
unsigned int *newseg, bool new_sec, bool pinning)
{
struct free_segmap_info *free_i = FREE_I(sbi);
unsigned int segno, secno, zoneno;
unsigned int total_zones = MAIN_SECS(sbi) / sbi->secs_per_zone;
unsigned int hint = GET_SEC_FROM_SEG(sbi, *newseg);
unsigned int old_zoneno = GET_ZONE_FROM_SEG(sbi, *newseg);
bool init = true;
int i;
int ret = 0;
spin_lock(&free_i->segmap_lock);
if (time_to_inject(sbi, FAULT_NO_SEGMENT)) {
ret = -ENOSPC;
goto out_unlock;
}
if (!new_sec && ((*newseg + 1) % SEGS_PER_SEC(sbi))) {
segno = find_next_zero_bit(free_i->free_segmap,
GET_SEG_FROM_SEC(sbi, hint + 1), *newseg + 1);
if (segno < GET_SEG_FROM_SEC(sbi, hint + 1))
goto got_it;
}
/*
* If we format f2fs on zoned storage, let's try to get pinned sections
* from beginning of the storage, which should be a conventional one.
*/
if (f2fs_sb_has_blkzoned(sbi)) {
segno = pinning ? 0 : max(first_zoned_segno(sbi), *newseg);
hint = GET_SEC_FROM_SEG(sbi, segno);
}
find_other_zone:
secno = find_next_zero_bit(free_i->free_secmap, MAIN_SECS(sbi), hint);
if (secno >= MAIN_SECS(sbi)) {
secno = find_first_zero_bit(free_i->free_secmap,
MAIN_SECS(sbi));
if (secno >= MAIN_SECS(sbi)) {
ret = -ENOSPC;
goto out_unlock;
}
}
segno = GET_SEG_FROM_SEC(sbi, secno);
zoneno = GET_ZONE_FROM_SEC(sbi, secno);
/* give up on finding another zone */
if (!init)
goto got_it;
if (sbi->secs_per_zone == 1)
goto got_it;
if (zoneno == old_zoneno)
goto got_it;
for (i = 0; i < NR_CURSEG_TYPE; i++)
if (CURSEG_I(sbi, i)->zone == zoneno)
break;
if (i < NR_CURSEG_TYPE) {
/* zone is in user, try another */
if (zoneno + 1 >= total_zones)
hint = 0;
else
hint = (zoneno + 1) * sbi->secs_per_zone;
init = false;
goto find_other_zone;
}
got_it:
/* set it as dirty segment in free segmap */
f2fs_bug_on(sbi, test_bit(segno, free_i->free_segmap));
/* no free section in conventional zone */
if (new_sec && pinning &&
!f2fs_valid_pinned_area(sbi, START_BLOCK(sbi, segno))) {
ret = -EAGAIN;
goto out_unlock;
}
__set_inuse(sbi, segno);
*newseg = segno;
out_unlock:
spin_unlock(&free_i->segmap_lock);
if (ret == -ENOSPC) {
f2fs_stop_checkpoint(sbi, false, STOP_CP_REASON_NO_SEGMENT);
f2fs_bug_on(sbi, 1);
}
return ret;
}
static void reset_curseg(struct f2fs_sb_info *sbi, int type, int modified)
{
struct curseg_info *curseg = CURSEG_I(sbi, type);
struct summary_footer *sum_footer;
unsigned short seg_type = curseg->seg_type;
/* only happen when get_new_segment() fails */
if (curseg->next_segno == NULL_SEGNO)
return;
curseg->inited = true;
curseg->segno = curseg->next_segno;
curseg->zone = GET_ZONE_FROM_SEG(sbi, curseg->segno);
curseg->next_blkoff = 0;
curseg->next_segno = NULL_SEGNO;
sum_footer = &(curseg->sum_blk->footer);
memset(sum_footer, 0, sizeof(struct summary_footer));
sanity_check_seg_type(sbi, seg_type);
if (IS_DATASEG(seg_type))
SET_SUM_TYPE(sum_footer, SUM_TYPE_DATA);
if (IS_NODESEG(seg_type))
SET_SUM_TYPE(sum_footer, SUM_TYPE_NODE);
__set_sit_entry_type(sbi, seg_type, curseg->segno, modified);
}
static unsigned int __get_next_segno(struct f2fs_sb_info *sbi, int type)
{
struct curseg_info *curseg = CURSEG_I(sbi, type);
unsigned short seg_type = curseg->seg_type;
sanity_check_seg_type(sbi, seg_type);
if (f2fs_need_rand_seg(sbi))
return get_random_u32_below(MAIN_SECS(sbi) * SEGS_PER_SEC(sbi));
if (__is_large_section(sbi))
return curseg->segno;
/* inmem log may not locate on any segment after mount */
if (!curseg->inited)
return 0;
if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED)))
return 0;
if (seg_type == CURSEG_HOT_DATA || IS_NODESEG(seg_type))
return 0;
if (SIT_I(sbi)->last_victim[ALLOC_NEXT])
return SIT_I(sbi)->last_victim[ALLOC_NEXT];
/* find segments from 0 to reuse freed segments */
if (F2FS_OPTION(sbi).alloc_mode == ALLOC_MODE_REUSE)
return 0;
return curseg->segno;
}
/*
* Allocate a current working segment.
* This function always allocates a free segment in LFS manner.
*/
static int new_curseg(struct f2fs_sb_info *sbi, int type, bool new_sec)
{
struct curseg_info *curseg = CURSEG_I(sbi, type);
unsigned int segno = curseg->segno;
bool pinning = type == CURSEG_COLD_DATA_PINNED;
int ret;
if (curseg->inited)
write_sum_page(sbi, curseg->sum_blk, GET_SUM_BLOCK(sbi, segno));
segno = __get_next_segno(sbi, type);
ret = get_new_segment(sbi, &segno, new_sec, pinning);
if (ret) {
if (ret == -ENOSPC)
curseg->segno = NULL_SEGNO;
return ret;
}
curseg->next_segno = segno;
reset_curseg(sbi, type, 1);
curseg->alloc_type = LFS;
if (F2FS_OPTION(sbi).fs_mode == FS_MODE_FRAGMENT_BLK)
curseg->fragment_remained_chunk =
get_random_u32_inclusive(1, sbi->max_fragment_chunk);
return 0;
}
static int __next_free_blkoff(struct f2fs_sb_info *sbi,
int segno, block_t start)
{
struct seg_entry *se = get_seg_entry(sbi, segno);
int entries = SIT_VBLOCK_MAP_SIZE / sizeof(unsigned long);
unsigned long *target_map = SIT_I(sbi)->tmp_map;
unsigned long *ckpt_map = (unsigned long *)se->ckpt_valid_map;
unsigned long *cur_map = (unsigned long *)se->cur_valid_map;
int i;
for (i = 0; i < entries; i++)
target_map[i] = ckpt_map[i] | cur_map[i];
return __find_rev_next_zero_bit(target_map, BLKS_PER_SEG(sbi), start);
}
static int f2fs_find_next_ssr_block(struct f2fs_sb_info *sbi,
struct curseg_info *seg)
{
return __next_free_blkoff(sbi, seg->segno, seg->next_blkoff + 1);
}
bool f2fs_segment_has_free_slot(struct f2fs_sb_info *sbi, int segno)
{
return __next_free_blkoff(sbi, segno, 0) < BLKS_PER_SEG(sbi);
}
/*
* This function always allocates a used segment(from dirty seglist) by SSR
* manner, so it should recover the existing segment information of valid blocks
*/
static int change_curseg(struct f2fs_sb_info *sbi, int type)
{
struct dirty_seglist_info *dirty_i = DIRTY_I(sbi);
struct curseg_info *curseg = CURSEG_I(sbi, type);
unsigned int new_segno = curseg->next_segno;
struct f2fs_summary_block *sum_node;
struct page *sum_page;
write_sum_page(sbi, curseg->sum_blk, GET_SUM_BLOCK(sbi, curseg->segno));
__set_test_and_inuse(sbi, new_segno);
mutex_lock(&dirty_i->seglist_lock);
__remove_dirty_segment(sbi, new_segno, PRE);
__remove_dirty_segment(sbi, new_segno, DIRTY);
mutex_unlock(&dirty_i->seglist_lock);
reset_curseg(sbi, type, 1);
curseg->alloc_type = SSR;
curseg->next_blkoff = __next_free_blkoff(sbi, curseg->segno, 0);
sum_page = f2fs_get_sum_page(sbi, new_segno);
if (IS_ERR(sum_page)) {
/* GC won't be able to use stale summary pages by cp_error */
memset(curseg->sum_blk, 0, SUM_ENTRY_SIZE);
return PTR_ERR(sum_page);
}
sum_node = (struct f2fs_summary_block *)page_address(sum_page);
memcpy(curseg->sum_blk, sum_node, SUM_ENTRY_SIZE);
f2fs_put_page(sum_page, 1);
return 0;
}
static int get_ssr_segment(struct f2fs_sb_info *sbi, int type,
int alloc_mode, unsigned long long age);
static int get_atssr_segment(struct f2fs_sb_info *sbi, int type,
int target_type, int alloc_mode,
unsigned long long age)
{
struct curseg_info *curseg = CURSEG_I(sbi, type);
int ret = 0;
curseg->seg_type = target_type;
if (get_ssr_segment(sbi, type, alloc_mode, age)) {
struct seg_entry *se = get_seg_entry(sbi, curseg->next_segno);
curseg->seg_type = se->type;