fs/f2fs/segment.c

// 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/prefetch.h>
#include <linux/kthread.h>
#include <linux/swap.h>
#include <linux/timer.h>
#include <linux/freezer.h>
#include <linux/sched/signal.h>

#include "f2fs.h"
#include "segment.h"
#include "node.h"
#include "gc.h"
#include "trace.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 *inmem_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 (test_opt(sbi, LFS))
		return false;
	if (sbi->gc_mode == GC_URGENT)
		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_register_inmem_page(struct inode *inode, struct page *page)
{
	struct inmem_pages *new;

	f2fs_trace_pid(page);

	f2fs_set_page_private(page, (unsigned long)ATOMIC_WRITTEN_PAGE);

	new = f2fs_kmem_cache_alloc(inmem_entry_slab, GFP_NOFS);

	/* add atomic page indices to the list */
	new->page = page;
	INIT_LIST_HEAD(&new->list);

	/* increase reference count with clean state */
	get_page(page);
	mutex_lock(&F2FS_I(inode)->inmem_lock);
	list_add_tail(&new->list, &F2FS_I(inode)->inmem_pages);
	inc_page_count(F2FS_I_SB(inode), F2FS_INMEM_PAGES);
	mutex_unlock(&F2FS_I(inode)->inmem_lock);

	trace_f2fs_register_inmem_page(page, INMEM);
}

static int __revoke_inmem_pages(struct inode *inode,
				struct list_head *head, bool drop, bool recover,
				bool trylock)
{
	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
	struct inmem_pages *cur, *tmp;
	int err = 0;

	list_for_each_entry_safe(cur, tmp, head, list) {
		struct page *page = cur->page;

		if (drop)
			trace_f2fs_commit_inmem_page(page, INMEM_DROP);

		if (trylock) {
			/*
			 * to avoid deadlock in between page lock and
			 * inmem_lock.
			 */
			if (!trylock_page(page))
				continue;
		} else {
			lock_page(page);
		}

		f2fs_wait_on_page_writeback(page, DATA, true, true);

		if (recover) {
			struct dnode_of_data dn;
			struct node_info ni;

			trace_f2fs_commit_inmem_page(page, INMEM_REVOKE);
retry:
			set_new_dnode(&dn, inode, NULL, NULL, 0);
			err = f2fs_get_dnode_of_data(&dn, page->index,
								LOOKUP_NODE);
			if (err) {
				if (err == -ENOMEM) {
					congestion_wait(BLK_RW_ASYNC, HZ/50);
					cond_resched();
					goto retry;
				}
				err = -EAGAIN;
				goto next;
			}

			err = f2fs_get_node_info(sbi, dn.nid, &ni);
			if (err) {
				f2fs_put_dnode(&dn);
				return err;
			}

			if (cur->old_addr == NEW_ADDR) {
				f2fs_invalidate_blocks(sbi, dn.data_blkaddr);
				f2fs_update_data_blkaddr(&dn, NEW_ADDR);
			} else
				f2fs_replace_block(sbi, &dn, dn.data_blkaddr,
					cur->old_addr, ni.version, true, true);
			f2fs_put_dnode(&dn);
		}
next:
		/* we don't need to invalidate this in the sccessful status */
		if (drop || recover) {
			ClearPageUptodate(page);
			clear_cold_data(page);
		}
		f2fs_clear_page_private(page);
		f2fs_put_page(page, 1);

		list_del(&cur->list);
		kmem_cache_free(inmem_entry_slab, cur);
		dec_page_count(F2FS_I_SB(inode), F2FS_INMEM_PAGES);
	}
	return err;
}

void f2fs_drop_inmem_pages_all(struct f2fs_sb_info *sbi, bool gc_failure)
{
	struct list_head *head = &sbi->inode_list[ATOMIC_FILE];
	struct inode *inode;
	struct f2fs_inode_info *fi;
	unsigned int count = sbi->atomic_files;
	unsigned int looped = 0;
next:
	spin_lock(&sbi->inode_lock[ATOMIC_FILE]);
	if (list_empty(head)) {
		spin_unlock(&sbi->inode_lock[ATOMIC_FILE]);
		return;
	}
	fi = list_first_entry(head, struct f2fs_inode_info, inmem_ilist);
	inode = igrab(&fi->vfs_inode);
	if (inode)
		list_move_tail(&fi->inmem_ilist, head);
	spin_unlock(&sbi->inode_lock[ATOMIC_FILE]);

	if (inode) {
		if (gc_failure) {
			if (!fi->i_gc_failures[GC_FAILURE_ATOMIC])
				goto skip;
		}
		set_inode_flag(inode, FI_ATOMIC_REVOKE_REQUEST);
		f2fs_drop_inmem_pages(inode);
skip:
		iput(inode);
	}
	congestion_wait(BLK_RW_ASYNC, HZ/50);
	cond_resched();
	if (gc_failure) {
		if (++looped >= count)
			return;
	}
	goto next;
}

void f2fs_drop_inmem_pages(struct inode *inode)
{
	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
	struct f2fs_inode_info *fi = F2FS_I(inode);

	while (!list_empty(&fi->inmem_pages)) {
		mutex_lock(&fi->inmem_lock);
		__revoke_inmem_pages(inode, &fi->inmem_pages,
						true, false, true);
		mutex_unlock(&fi->inmem_lock);
	}

	fi->i_gc_failures[GC_FAILURE_ATOMIC] = 0;
	stat_dec_atomic_write(inode);

	spin_lock(&sbi->inode_lock[ATOMIC_FILE]);
	if (!list_empty(&fi->inmem_ilist))
		list_del_init(&fi->inmem_ilist);
	if (f2fs_is_atomic_file(inode)) {
		clear_inode_flag(inode, FI_ATOMIC_FILE);
		sbi->atomic_files--;
	}
	spin_unlock(&sbi->inode_lock[ATOMIC_FILE]);
}

void f2fs_drop_inmem_page(struct inode *inode, struct page *page)
{
	struct f2fs_inode_info *fi = F2FS_I(inode);
	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
	struct list_head *head = &fi->inmem_pages;
	struct inmem_pages *cur = NULL;

	f2fs_bug_on(sbi, !IS_ATOMIC_WRITTEN_PAGE(page));

	mutex_lock(&fi->inmem_lock);
	list_for_each_entry(cur, head, list) {
		if (cur->page == page)
			break;
	}

	f2fs_bug_on(sbi, list_empty(head) || cur->page != page);
	list_del(&cur->list);
	mutex_unlock(&fi->inmem_lock);

	dec_page_count(sbi, F2FS_INMEM_PAGES);
	kmem_cache_free(inmem_entry_slab, cur);

	ClearPageUptodate(page);
	f2fs_clear_page_private(page);
	f2fs_put_page(page, 0);

	trace_f2fs_commit_inmem_page(page, INMEM_INVALIDATE);
}

static int __f2fs_commit_inmem_pages(struct inode *inode)
{
	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
	struct f2fs_inode_info *fi = F2FS_I(inode);
	struct inmem_pages *cur, *tmp;
	struct f2fs_io_info fio = {
		.sbi = sbi,
		.ino = inode->i_ino,
		.type = DATA,
		.op = REQ_OP_WRITE,
		.op_flags = REQ_SYNC | REQ_PRIO,
		.io_type = FS_DATA_IO,
	};
	struct list_head revoke_list;
	bool submit_bio = false;
	int err = 0;

	INIT_LIST_HEAD(&revoke_list);

	list_for_each_entry_safe(cur, tmp, &fi->inmem_pages, list) {
		struct page *page = cur->page;

		lock_page(page);
		if (page->mapping == inode->i_mapping) {
			trace_f2fs_commit_inmem_page(page, INMEM);

			f2fs_wait_on_page_writeback(page, DATA, true, true);

			set_page_dirty(page);
			if (clear_page_dirty_for_io(page)) {
				inode_dec_dirty_pages(inode);
				f2fs_remove_dirty_inode(inode);
			}
retry:
			fio.page = page;
			fio.old_blkaddr = NULL_ADDR;
			fio.encrypted_page = NULL;
			fio.need_lock = LOCK_DONE;
			err = f2fs_do_write_data_page(&fio);
			if (err) {
				if (err == -ENOMEM) {
					congestion_wait(BLK_RW_ASYNC, HZ/50);
					cond_resched();
					goto retry;
				}
				unlock_page(page);
				break;
			}
			/* record old blkaddr for revoking */
			cur->old_addr = fio.old_blkaddr;
			submit_bio = true;
		}
		unlock_page(page);
		list_move_tail(&cur->list, &revoke_list);
	}

	if (submit_bio)
		f2fs_submit_merged_write_cond(sbi, inode, NULL, 0, DATA);

	if (err) {
		/*
		 * try to revoke all committed pages, but still we could fail
		 * due to no memory or other reason, if that happened, EAGAIN
		 * will be returned, which means in such case, transaction is
		 * already not integrity, caller should use journal to do the
		 * recovery or rewrite & commit last transaction. For other
		 * error number, revoking was done by filesystem itself.
		 */
		err = __revoke_inmem_pages(inode, &revoke_list,
						false, true, false);

		/* drop all uncommitted pages */
		__revoke_inmem_pages(inode, &fi->inmem_pages,
						true, false, false);
	} else {
		__revoke_inmem_pages(inode, &revoke_list,
						false, false, false);
	}

	return err;
}

int f2fs_commit_inmem_pages(struct inode *inode)
{
	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
	struct f2fs_inode_info *fi = F2FS_I(inode);
	int err;

	f2fs_balance_fs(sbi, true);

	down_write(&fi->i_gc_rwsem[WRITE]);

	f2fs_lock_op(sbi);
	set_inode_flag(inode, FI_ATOMIC_COMMIT);

	mutex_lock(&fi->inmem_lock);
	err = __f2fs_commit_inmem_pages(inode);
	mutex_unlock(&fi->inmem_lock);

	clear_inode_flag(inode, FI_ATOMIC_COMMIT);

	f2fs_unlock_op(sbi);
	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 (time_to_inject(sbi, FAULT_CHECKPOINT)) {
		f2fs_show_injection_info(FAULT_CHECKPOINT);
		f2fs_stop_checkpoint(sbi, false);
	}

	/* balance_fs_bg is able to be pending */
	if (need && excess_cached_nats(sbi))
		f2fs_balance_fs_bg(sbi);

	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_not_enough_free_secs(sbi, 0, 0)) {
		mutex_lock(&sbi->gc_mutex);
		f2fs_gc(sbi, false, false, NULL_SEGNO);
	}
}

void f2fs_balance_fs_bg(struct f2fs_sb_info *sbi)
{
	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, EXTENT_CACHE))
		f2fs_shrink_extent_tree(sbi, 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 (!is_idle(sbi, REQ_TIME) &&
		(!excess_dirty_nats(sbi) && !excess_dirty_nodes(sbi)))
		return;

	/* 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) ||
			excess_prefree_segs(sbi) ||
			excess_dirty_nats(sbi) ||
			excess_dirty_nodes(sbi) ||
			f2fs_time_over(sbi, CP_TIME)) {
		if (test_opt(sbi, DATA_FLUSH)) {
			struct blk_plug plug;

			mutex_lock(&sbi->flush_lock);

			blk_start_plug(&plug);
			f2fs_sync_dirty_inodes(sbi, FILE_INODE);
			blk_finish_plug(&plug);

			mutex_unlock(&sbi->flush_lock);
		}
		f2fs_sync_fs(sbi->sb, true);
		stat_inc_bg_cp_count(sbi->stat_info);
	}
}

static int __submit_flush_wait(struct f2fs_sb_info *sbi,
				struct block_device *bdev)
{
	struct bio *bio;
	int ret;

	bio = f2fs_bio_alloc(sbi, 0, false);
	if (!bio)
		return -ENOMEM;

	bio->bi_opf = REQ_OP_WRITE | REQ_SYNC | REQ_PREFLUSH;
	bio_set_dev(bio, bdev);
	ret = submit_bio_wait(bio);
	bio_put(bio);

	trace_f2fs_issue_flush(bdev, test_opt(sbi, NOBARRIER),
				test_opt(sbi, FLUSH_MERGE), ret);
	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;

	sb_start_intwrite(sbi->sb);

	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;
	}

	sb_end_intwrite(sbi->sb);

	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 */
	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;
	int err = 0;

	if (SM_I(sbi)->fcc_info) {
		fcc = SM_I(sbi)->fcc_info;
		if (fcc->f2fs_issue_flush)
			return err;
		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 err;

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)) {
		err = PTR_ERR(fcc->f2fs_issue_flush);
		kvfree(fcc);
		SM_I(sbi)->fcc_info = NULL;
		return err;
	}

	return err;
}

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) {
		kvfree(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;

	for (i = 1; i < sbi->s_ndevs; i++) {
		if (!f2fs_test_bit(i, (char *)&sbi->dirty_device))
			continue;
		ret = __submit_flush_wait(sbi, FDEV(i).bdev);
		if (ret)
			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]++;
	}
}

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);

	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]--;

		if (get_valid_blocks(sbi, segno, true) == 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
		}
	}
}

/*
 * 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;

	if (segno == NULL_SEGNO || IS_CURSEG(sbi, segno))
		return;

	mutex_lock(&dirty_i->seglist_lock);

	valid_blocks = get_valid_blocks(sbi, segno, false);
	ckpt_valid_blocks = get_ckpt_valid_blocks(sbi, segno);

	if (valid_blocks == 0 && (!is_sbi_flag_set(sbi, SBI_CP_DISABLED) ||
				ckpt_valid_blocks == sbi->blocks_per_seg)) {
		__locate_dirty_segment(sbi, segno, PRE);
		__remove_dirty_segment(sbi, segno, DIRTY);
	} else if (valid_blocks < sbi->blocks_per_seg) {
		__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 = ovp_hole_segs << sbi->log_blocks_per_seg;
	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] += sbi->blocks_per_seg - se->valid_blocks;
		else
			holes[DATA] += sbi->blocks_per_seg - se->valid_blocks;
	}
	mutex_unlock(&dirty_i->seglist_lock);

	unusable = holes[DATA] > holes[NODE] ? 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 (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;
	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))
			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);
	INIT_LIST_HEAD(&dc->list);
	dc->bdev = bdev;
	dc->lstart = lstart;
	dc->start = start;
	dc->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 struct discard_cmd *__attach_discard_cmd(struct f2fs_sb_info *sbi,
				struct block_device *bdev, block_t lstart,
				block_t start, block_t len,
				struct rb_node *parent, struct rb_node **p,
				bool leftmost)
{
	struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
	struct discard_cmd *dc;

	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);

	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->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->start, dc->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)
		printk_ratelimited(
			"%sF2FS-fs: Issue discard(%u, %u, %u) failed, ret: %d",
			KERN_INFO, dc->lstart, dc->start, dc->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;

	dc->error = blk_status_to_errno(bio->bi_status);

	spin_lock_irqsave(&dc->lock, flags);
	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, max_blocks = sbi->blocks_per_seg;
	unsigned long *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 = max_blocks;
		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)
{
	/* common policy */
	dpolicy->type = discard_type;
	dpolicy->sync = true;
	dpolicy->ordered = false;
	dpolicy->granularity = granularity;

	dpolicy->max_requests = DEF_MAX_DISCARD_REQUEST;
	dpolicy->io_aware_gran = MAX_PLIST_NUM;
	dpolicy->timeout = 0;

	if (discard_type == DPOLICY_BG) {
		dpolicy->min_interval = DEF_MIN_DISCARD_ISSUE_TIME;
		dpolicy->mid_interval = DEF_MID_DISCARD_ISSUE_TIME;
		dpolicy->max_interval = DEF_MAX_DISCARD_ISSUE_TIME;
		dpolicy->io_aware = true;
		dpolicy->sync = false;
		dpolicy->ordered = true;
		if (utilization(sbi) > DEF_DISCARD_URGENT_UTIL) {
			dpolicy->granularity = 1;
			dpolicy->max_interval = DEF_MIN_DISCARD_ISSUE_TIME;
		}
	} else if (discard_type == DPOLICY_FORCE) {
		dpolicy->min_interval = DEF_MIN_DISCARD_ISSUE_TIME;
		dpolicy->mid_interval = DEF_MID_DISCARD_ISSUE_TIME;
		dpolicy->max_interval = DEF_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->max_requests = UINT_MAX;
		dpolicy->io_aware = false;
		/* we need to issue all to keep CP_TRIMMED_FLAG */
		dpolicy->granularity = 1;
	}
}

static void __update_discard_tree_range(struct f2fs_sb_info *sbi,
				struct block_device *bdev, block_t lstart,
				block_t start, block_t len);
/* 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,
						unsigned int *issued)
{
	struct block_device *bdev = dc->bdev;
	struct request_queue *q = bdev_get_queue(bdev);
	unsigned int max_discard_blocks =
			SECTOR_TO_BLOCK(q->limits.max_discard_sectors);
	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);
	int 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;

	trace_f2fs_issue_discard(bdev, dc->start, dc->len);

	lstart = dc->lstart;
	start = dc->start;
	len = dc->len;
	total_len = len;

	dc->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->len += len;

		if (time_to_inject(sbi, FAULT_DISCARD)) {
			f2fs_show_injection_info(FAULT_DISCARD);
			err = -EIO;
			goto submit;
		}
		err = __blkdev_issue_discard(bdev,
					SECTOR_FROM_BLOCK(start),
					SECTOR_FROM_BLOCK(len),
					GFP_NOFS, 0, &bio);
submit:
		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, FS_DISCARD, 1);

		lstart += len;
		start += len;
		total_len -= len;
		len = total_len;
	}

	if (!err && len)
		__update_discard_tree_range(sbi, bdev, lstart, start, len);
	return err;
}

static struct discard_cmd *__insert_discard_tree(struct f2fs_sb_info *sbi,
				struct block_device *bdev, block_t lstart,
				block_t start, block_t len,
				struct rb_node **insert_p,
				struct rb_node *insert_parent)
{
	struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
	struct rb_node **p;
	struct rb_node *parent = NULL;
	struct discard_cmd *dc = NULL;
	bool leftmost = true;

	if (insert_p && insert_parent) {
		parent = insert_parent;
		p = insert_p;
		goto do_insert;
	}

	p = f2fs_lookup_rb_tree_for_insert(sbi, &dcc->root, &parent,
							lstart, &leftmost);
do_insert:
	dc = __attach_discard_cmd(sbi, bdev, lstart, start, len, parent,
								p, leftmost);
	if (!dc)
		return NULL;

	return dc;
}

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->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->len == 1) {
		__remove_discard_cmd(sbi, dc);
		return;
	}

	dcc->undiscard_blks -= di.len;

	if (blkaddr > di.lstart) {
		dc->len = blkaddr - dc->lstart;
		dcc->undiscard_blks += dc->len;
		__relocate_discard_cmd(dcc, dc);
		modified = true;
	}

	if (blkaddr < di.lstart + di.len - 1) {
		if (modified) {
			__insert_discard_tree(sbi, dc->bdev, blkaddr + 1,
					di.start + blkaddr + 1 - di.lstart,
					di.lstart + di.len - 1 - blkaddr,
					NULL, NULL);
		} else {
			dc->lstart++;
			dc->len--;
			dc->start++;
			dcc->undiscard_blks += dc->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;
	struct request_queue *q = bdev_get_queue(bdev);
	unsigned int max_discard_blocks =
			SECTOR_TO_BLOCK(q->limits.max_discard_sectors);
	block_t end = lstart + len;

	dc = (struct discard_cmd *)f2fs_lookup_rb_tree_ret(&dcc->root,
					NULL, lstart,
					(struct rb_entry **)&prev_dc,
					(struct rb_entry **)&next_dc,
					&insert_p, &insert_parent, true, NULL);
	if (dc)
		prev_dc = dc;

	if (!prev_dc) {
		di.lstart = lstart;
		di.len = next_dc ? next_dc->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->lstart + prev_dc->len;
			if (di.lstart < lstart)
				di.lstart = lstart;
			if (di.lstart >= end)
				break;

			if (!next_dc || next_dc->lstart > end)
				di.len = end - di.lstart;
			else
				di.len = next_dc->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_tree(sbi, bdev, di.lstart, di.start,
							di.len, NULL, NULL);
		}
 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);
	}
}

static int __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 0;

	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);
	return 0;
}

static unsigned int __issue_discard_cmd_orderly(struct f2fs_sb_info *sbi,
					struct discard_policy *dpolicy)
{
	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;
	unsigned int pos = dcc->next_pos;
	unsigned int issued = 0;
	bool io_interrupted = false;

	mutex_lock(&dcc->cmd_lock);
	dc = (struct discard_cmd *)f2fs_lookup_rb_tree_ret(&dcc->root,
					NULL, pos,
					(struct rb_entry **)&prev_dc,
					(struct rb_entry **)&next_dc,
					&insert_p, &insert_parent, true, NULL);
	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->lstart + dc->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;

	return issued;
}

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 = 0;
	bool io_interrupted = false;

	if (dpolicy->timeout != 0)
		f2fs_update_time(sbi, dpolicy->timeout);

	for (i = MAX_PLIST_NUM - 1; i >= 0; i--) {
		if (dpolicy->timeout != 0 &&
				f2fs_time_over(sbi, dpolicy->timeout))
			break;

		if (i + 1 < dpolicy->granularity)
			break;

		if (i < DEFAULT_DISCARD_GRANULARITY && dpolicy->ordered)
			return __issue_discard_cmd_orderly(sbi, dpolicy);

		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_rb_tree_consistence(sbi,
								&dcc->root));
		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 != 0 &&
				f2fs_time_over(sbi, dpolicy->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 (!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->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, *tmp;
	bool need_wait;
	unsigned int trimmed = 0;

next:
	need_wait = false;

	mutex_lock(&dcc->cmd_lock);
	list_for_each_entry_safe(dc, tmp, wait_list, list) {
		if (dc->lstart + dc->len <= start || end <= dc->lstart)
			continue;
		if (dc->len < dpolicy->granularity)
			continue;
		if (dc->state == D_DONE && !dc->ref) {
			wait_for_completion_io(&dc->wait);
			if (!dc->error)
				trimmed += dc->len;
			__remove_discard_cmd(sbi, dc);
		} else {
			dc->ref++;
			need_wait = true;
			break;
		}
	}
	mutex_unlock(&dcc->cmd_lock);

	if (need_wait) {
		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, 1);
	discard_blks = __wait_discard_cmd_range(sbi, &dp, 0, UINT_MAX);
	__init_discard_policy(sbi, &dp, DPOLICY_UMOUNT, 1);
	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 = (struct discard_cmd *)f2fs_lookup_rb_tree(&dcc->root,
							NULL, blkaddr);
	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);
	}
}

/* This comes from f2fs_put_super */
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;

	__init_discard_policy(sbi, &dpolicy, DPOLICY_UMOUNT,
					dcc->discard_granularity);
	dpolicy.timeout = UMOUNT_DISCARD_TIMEOUT;
	__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 = DEF_MIN_DISCARD_ISSUE_TIME;
	int issued;

	set_freezable();

	do {
		__init_discard_policy(sbi, &dpolicy, DPOLICY_BG,
					dcc->discard_granularity);

		wait_event_interruptible_timeout(*q,
				kthread_should_stop() || freezing(current) ||
				dcc->discard_wake,
				msecs_to_jiffies(wait_ms));

		if (dcc->discard_wake)
			dcc->discard_wake = 0;

		/* clean up pending candidates before going to sleep */
		if (atomic_read(&dcc->queued_discard))
			__wait_all_discard_cmd(sbi, NULL);

		if (try_to_freeze())
			continue;
		if (f2fs_readonly(sbi->sb))
			continue;
		if (kthread_should_stop())
			return 0;
		if (is_sbi_flag_set(sbi, SBI_NEED_FSCK)) {
			wait_ms = dpolicy.max_interval;
			continue;
		}

		if (sbi->gc_mode == GC_URGENT)
			__init_discard_policy(sbi, &dpolicy, DPOLICY_FORCE, 1);

		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;
		}

		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;

	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);

		if (sector & (bdev_zone_sectors(bdev) - 1) ||
				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;
		}
		trace_f2fs_issue_reset_zone(bdev, blkstart);
		return blkdev_reset_zones(bdev, sector, nr_sects, GFP_NOFS);
	}

	/* For conventional zones, use regular discard if supported */
	return __queue_discard_cmd(sbi, bdev, lblkstart, blklen);
}
#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
	return __queue_discard_cmd(sbi, bdev, blkstart, blklen);
}

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_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);
	int max_blocks = sbi->blocks_per_seg;
	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 == max_blocks || !f2fs_hw_support_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, max_blocks, end + 1);
		if (start >= max_blocks)
			break;

		end = __find_rev_next_zero_bit(dmap, max_blocks, start + 1);
		if (force && start && end != max_blocks
					&& (end - start) < cpc->trim_minlen)
			continue;

		if (check_only)
			return true;

		if (!de) {
			de = f2fs_kmem_cache_alloc(discard_entry_slab,
								GFP_F2FS_ZERO);
			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);
	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 need_align = test_opt(sbi, LFS) && __is_large_section(sbi);

	mutex_lock(&dirty_i->seglist_lock);

	while (1) {
		int i;

		if (need_align && 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 (need_align) {
			start = rounddown(start, sbi->segs_per_sec);
			end = roundup(end, sbi->segs_per_sec);
		}

		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;

		if (!test_opt(sbi, LFS) || !__is_large_section(sbi)) {
			f2fs_issue_discard(sbi, START_BLOCK(sbi, start),
				(end - start) << sbi->log_blocks_per_seg);
			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),
				sbi->segs_per_sec << sbi->log_blocks_per_seg);

		start = start_segno + sbi->segs_per_sec;
		if (start < end)
			goto next;
		else
			end = start - 1;
	}
	mutex_unlock(&dirty_i->seglist_lock);

	/* 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,
					sbi->blocks_per_seg, 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,
					sbi->blocks_per_seg, cur_pos);
		}
skip:
		cur_pos = next_pos;
		is_valid = !is_valid;

		if (cur_pos < sbi->blocks_per_seg)
			goto find_next;

		release_discard_addr(entry);
		dcc->nr_discards -= total_len;
	}

	wake_up_discard_thread(sbi, false);
}

static int create_discard_cmd_control(struct f2fs_sb_info *sbi)
{
	dev_t dev = sbi->sb->s_bdev->bd_dev;
	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_granularity = DEFAULT_DISCARD_GRANULARITY;
	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 = MAIN_SEGS(sbi) << sbi->log_blocks_per_seg;
	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:
	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);
		kvfree(dcc);
		SM_I(sbi)->dcc_info = NULL;
		return err;
	}

	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.
	 */
	if (unlikely(atomic_read(&dcc->discard_cmd_cnt)))
		f2fs_issue_discard_timeout(sbi);

	kvfree(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 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);

	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 >> (sizeof(unsigned short) << 3) ||
				(new_vblocks > sbi->blocks_per_seg)));

	se->valid_blocks = new_vblocks;
	se->mtime = get_mtime(sbi, false);
	if (se->mtime > SIT_I(sbi)->max_mtime)
		SIT_I(sbi)->max_mtime = se->mtime;

	/* 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_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_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)
		return;

	invalidate_mapping_pages(META_MAPPING(sbi), addr, addr);

	/* add it into sit main buffer */
	down_write(&sit_i->sentry_lock);

	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;
}

/*
 * This function should be resided under the curseg_mutex lock
 */
static void __add_sum_entry(struct f2fs_sb_info *sbi, int type,
					struct f2fs_summary *sum)
{
	struct curseg_info *curseg = CURSEG_I(sbi, type);
	void *addr = curseg->sum_blk;
	addr += curseg->next_blkoff * sizeof(struct f2fs_summary);
	memcpy(addr, sum, sizeof(struct f2fs_summary));
}

/*
 * 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)
			valid_sum_count += sbi->blocks_per_seg;
		else {
			if (for_ra)
				valid_sum_count += le16_to_cpu(
					F2FS_CKPT(sbi)->cur_data_blkoff[i]);
			else
				valid_sum_count += curseg_blkoff(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, int type)
{
	struct curseg_info *curseg = CURSEG_I(sbi, type);
	unsigned int segno = curseg->segno + 1;
	struct free_segmap_info *free_i = FREE_I(sbi);

	if (segno < MAIN_SEGS(sbi) && segno % sbi->segs_per_sec)
		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 void get_new_segment(struct f2fs_sb_info *sbi,
			unsigned int *newseg, bool new_sec, int dir)
{
	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);
	unsigned int left_start = hint;
	bool init = true;
	int go_left = 0;
	int i;

	spin_lock(&free_i->segmap_lock);

	if (!new_sec && ((*newseg + 1) % sbi->segs_per_sec)) {
		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;
	}
find_other_zone:
	secno = find_next_zero_bit(free_i->free_secmap, MAIN_SECS(sbi), hint);
	if (secno >= MAIN_SECS(sbi)) {
		if (dir == ALLOC_RIGHT) {
			secno = find_next_zero_bit(free_i->free_secmap,
							MAIN_SECS(sbi), 0);
			f2fs_bug_on(sbi, secno >= MAIN_SECS(sbi));
		} else {
			go_left = 1;
			left_start = hint - 1;
		}
	}
	if (go_left == 0)
		goto skip_left;

	while (test_bit(left_start, free_i->free_secmap)) {
		if (left_start > 0) {
			left_start--;
			continue;
		}
		left_start = find_next_zero_bit(free_i->free_secmap,
							MAIN_SECS(sbi), 0);
		f2fs_bug_on(sbi, left_start >= MAIN_SECS(sbi));
		break;
	}
	secno = left_start;
skip_left:
	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;
	if (dir == ALLOC_LEFT) {
		if (!go_left && zoneno + 1 >= total_zones)
			goto got_it;
		if (go_left && zoneno == 0)
			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 (go_left)
			hint = zoneno * sbi->secs_per_zone - 1;
		else 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));
	__set_inuse(sbi, segno);
	*newseg = segno;
	spin_unlock(&free_i->segmap_lock);
}

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;

	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));
	if (IS_DATASEG(type))
		SET_SUM_TYPE(sum_footer, SUM_TYPE_DATA);
	if (IS_NODESEG(type))
		SET_SUM_TYPE(sum_footer, SUM_TYPE_NODE);
	__set_sit_entry_type(sbi, type, curseg->segno, modified);
}

static unsigned int __get_next_segno(struct f2fs_sb_info *sbi, int type)
{
	/* if segs_per_sec is large than 1, we need to keep original policy. */
	if (__is_large_section(sbi))
		return CURSEG_I(sbi, type)->segno;

	if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED)))
		return 0;

	if (test_opt(sbi, NOHEAP) &&
		(type == CURSEG_HOT_DATA || IS_NODESEG(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_I(sbi, type)->segno;
}

/*
 * Allocate a current working segment.
 * This function always allocates a free segment in LFS manner.
 */
static void 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;
	int dir = ALLOC_LEFT;

	write_sum_page(sbi, curseg->sum_blk,
				GET_SUM_BLOCK(sbi, segno));
	if (type == CURSEG_WARM_DATA || type == CURSEG_COLD_DATA)
		dir = ALLOC_RIGHT;

	if (test_opt(sbi, NOHEAP))
		dir = ALLOC_RIGHT;

	segno = __get_next_segno(sbi, type);
	get_new_segment(sbi, &segno, new_sec, dir);
	curseg->next_segno = segno;
	reset_curseg(sbi, type, 1);
	curseg->alloc_type = LFS;
}

static void __next_free_blkoff(struct f2fs_sb_info *sbi,
			struct curseg_info *seg, block_t start)
{
	struct seg_entry *se = get_seg_entry(sbi, seg->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, pos;

	for (i = 0; i < entries; i++)
		target_map[i] = ckpt_map[i] | cur_map[i];

	pos = __find_rev_next_zero_bit(target_map, sbi->blocks_per_seg, start);

	seg->next_blkoff = pos;
}

/*
 * If a segment is written by LFS manner, next block offset is just obtained
 * by increasing the current block offset. However, if a segment is written by
 * SSR manner, next block offset obtained by calling __next_free_blkoff
 */
static void __refresh_next_blkoff(struct f2fs_sb_info *sbi,
				struct curseg_info *seg)
{
	if (seg->alloc_type == SSR)
		__next_free_blkoff(sbi, seg, seg->next_blkoff + 1);
	else
		seg->next_blkoff++;
}

/*
 * 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 void 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;
	__next_free_blkoff(sbi, curseg, 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;
	}
	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);
}

static int get_ssr_segment(struct f2fs_sb_info *sbi, int type)
{
	struct curseg_info *curseg = CURSEG_I(sbi, type);
	const struct victim_selection *v_ops = DIRTY_I(sbi)->v_ops;
	unsigned segno = NULL_SEGNO;
	int i, cnt;
	bool reversed = false;

	/* f2fs_need_SSR() already forces to do this */
	if (v_ops->get_victim(sbi, &segno, BG_GC, type, SSR)) {
		curseg->next_segno = segno;
		return 1;
	}

	/* For node segments, let's do SSR more intensively */
	if (IS_NODESEG(type)) {
		if (type >= CURSEG_WARM_NODE) {
			reversed = true;
			i = CURSEG_COLD_NODE;
		} else {
			i = CURSEG_HOT_NODE;
		}
		cnt = NR_CURSEG_NODE_TYPE;
	} else {
		if (type >= CURSEG_WARM_DATA) {
			reversed = true;
			i = CURSEG_COLD_DATA;
		} else {
			i = CURSEG_HOT_DATA;
		}
		cnt = NR_CURSEG_DATA_TYPE;
	}

	for (; cnt-- > 0; reversed ? i-- : i++) {
		if (i == type)
			continue;
		if (v_ops->get_victim(sbi, &segno, BG_GC, i, SSR)) {
			curseg->next_segno = segno;
			return 1;
		}
	}

	/* find valid_blocks=0 in dirty list */
	if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED))) {
		segno = get_free_segment(sbi);
		if (segno != NULL_SEGNO) {
			curseg->next_segno = segno;
			return 1;
		}
	}
	return 0;
}

/*
 * flush out current segment and replace it with new segment
 * This function should be returned with success, otherwise BUG
 */
static void allocate_segment_by_default(struct f2fs_sb_info *sbi,
						int type, bool force)
{
	struct curseg_info *curseg = CURSEG_I(sbi, type);

	if (force)
		new_curseg(sbi, type, true);
	else if (!is_set_ckpt_flags(sbi, CP_CRC_RECOVERY_FLAG) &&
					type == CURSEG_WARM_NODE)
		new_curseg(sbi, type, false);
	else if (curseg->alloc_type == LFS && is_next_segment_free(sbi, type) &&
			likely(!is_sbi_flag_set(sbi, SBI_CP_DISABLED)))
		new_curseg(sbi, type, false);
	else if (f2fs_need_SSR(sbi) && get_ssr_segment(sbi, type))
		change_curseg(sbi, type);
	else
		new_curseg(sbi, type, false);

	stat_inc_seg_type(sbi, curseg);
}

void allocate_segment_for_resize(struct f2fs_sb_info *sbi, int type,
					unsigned int start, unsigned int end)
{
	struct curseg_info *curseg = CURSEG_I(sbi, type);
	unsigned int segno;

	down_read(&SM_I(sbi)->curseg_lock);
	mutex_lock(&curseg->curseg_mutex);
	down_write(&SIT_I(sbi)->sentry_lock);

	segno = CURSEG_I(sbi, type)->segno;
	if (segno < start || segno > end)
		goto unlock;

	if (f2fs_need_SSR(sbi) && get_ssr_segment(sbi, type))
		change_curseg(sbi, type);
	else
		new_curseg(sbi, type, true);

	stat_inc_seg_type(sbi, curseg);

	locate_dirty_segment(sbi, segno);
unlock:
	up_write(&SIT_I(sbi)->sentry_lock);

	if (segno != curseg->segno)
		f2fs_notice(sbi, "For resize: curseg of type %d: %u ==> %u",
			    type, segno, curseg->segno);

	mutex_unlock(&curseg->curseg_mutex);
	up_read(&SM_I(sbi)->curseg_lock);
}

void f2fs_allocate_new_segments(struct f2fs_sb_info *sbi)
{
	struct curseg_info *curseg;
	unsigned int old_segno;
	int i;

	down_write(&SIT_I(sbi)->sentry_lock);

	for (i = CURSEG_HOT_DATA; i <= CURSEG_COLD_DATA; i++) {
		curseg = CURSEG_I(sbi, i);
		old_segno = curseg->segno;
		SIT_I(sbi)->s_ops->allocate_segment(sbi, i, true);
		locate_dirty_segment(sbi, old_segno);
	}

	up_write(&SIT_I(sbi)->sentry_lock);
}

static const struct segment_allocation default_salloc_ops = {
	.allocate_segment = allocate_segment_by_default,
};

bool f2fs_exist_trim_candidates(struct f2fs_sb_info *sbi,
						struct cp_control *cpc)
{
	__u64 trim_start = cpc->trim_start;
	bool has_candidate = false;

	down_write(&SIT_I(sbi)->sentry_lock);
	for (; cpc->trim_start <= cpc->trim_end; cpc->trim_start++) {
		if (add_discard_addrs(sbi, cpc, true)) {
			has_candidate = true;
			break;
		}
	}
	up_write(&SIT_I(sbi)->sentry_lock);

	cpc->trim_start = trim_start;
	return has_candidate;
}

static unsigned int __issue_discard_cmd_range(struct f2fs_sb_info *sbi,
					struct discard_policy *dpolicy,
					unsigned int start, unsigned int end)
{
	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;
	int issued;
	unsigned int trimmed = 0;

next:
	issued = 0;

	mutex_lock(&dcc->cmd_lock);
	if (unlikely(dcc->rbtree_check))
		f2fs_bug_on(sbi, !f2fs_check_rb_tree_consistence(sbi,
								&dcc->root));

	dc = (struct discard_cmd *)f2fs_lookup_rb_tree_ret(&dcc->root,
					NULL, start,
					(struct rb_entry **)&prev_dc,
					(struct rb_entry **)&next_dc,
					&insert_p, &insert_parent, true, NULL);
	if (!dc)
		dc = next_dc;

	blk_start_plug(&plug);

	while (dc && dc->lstart <= end) {
		struct rb_node *node;
		int err = 0;

		if (dc->len < dpolicy->granularity)
			goto skip;

		if (dc->state != D_PREP) {
			list_move_tail(&dc->list, &dcc->fstrim_list);
			goto skip;
		}

		err = __submit_discard_cmd(sbi, dpolicy, dc, &issued);

		if (issued >= dpolicy->max_requests) {
			start = dc->lstart + dc->len;

			if (err)
				__remove_discard_cmd(sbi, dc);

			blk_finish_plug(&plug);
			mutex_unlock(&dcc->cmd_lock);
			trimmed += __wait_all_discard_cmd(sbi, NULL);
			congestion_wait(BLK_RW_ASYNC, HZ/50);
			goto next;
		}
skip:
		node = rb_next(&dc->rb_node);
		if (err)
			__remove_discard_cmd(sbi, dc);
		dc = rb_entry_safe(node, struct discard_cmd, rb_node);

		if (fatal_signal_pending(current))
			break;
	}

	blk_finish_plug(&plug);
	mutex_unlock(&dcc->cmd_lock);

	return trimmed;
}

int f2fs_trim_fs(struct f2fs_sb_info *sbi, struct fstrim_range *range)
{
	__u64 start = F2FS_BYTES_TO_BLK(range->start);
	__u64 end = start + F2FS_BYTES_TO_BLK(range->len) - 1;
	unsigned int start_segno, end_segno;
	block_t start_block, end_block;
	struct cp_control cpc;
	struct discard_policy dpolicy;
	unsigned long long trimmed = 0;
	int err = 0;
	bool need_align = test_opt(sbi, LFS) && __is_large_section(sbi);

	if (start >= MAX_BLKADDR(sbi) || range->len < sbi->blocksize)
		return -EINVAL;

	if (end < MAIN_BLKADDR(sbi))
		goto out;

	if (is_sbi_flag_set(sbi, SBI_NEED_FSCK)) {
		f2fs_warn(sbi, "Found FS corruption, run fsck to fix.");
		return -EFSCORRUPTED;
	}

	/* start/end segment number in main_area */
	start_segno = (start <= MAIN_BLKADDR(sbi)) ? 0 : GET_SEGNO(sbi, start);
	end_segno = (end >= MAX_BLKADDR(sbi)) ? MAIN_SEGS(sbi) - 1 :
						GET_SEGNO(sbi, end);
	if (need_align) {
		start_segno = rounddown(start_segno, sbi->segs_per_sec);
		end_segno = roundup(end_segno + 1, sbi->segs_per_sec) - 1;
	}

	cpc.reason = CP_DISCARD;
	cpc.trim_minlen = max_t(__u64, 1, F2FS_BYTES_TO_BLK(range->minlen));
	cpc.trim_start = start_segno;
	cpc.trim_end = end_segno;

	if (sbi->discard_blks == 0)
		goto out;

	mutex_lock(&sbi->gc_mutex);
	err = f2fs_write_checkpoint(sbi, &cpc);
	mutex_unlock(&sbi->gc_mutex);
	if (err)
		goto out;

	/*
	 * We filed discard candidates, but actually we don't need to wait for
	 * all of them, since they'll be issued in idle time along with runtime
	 * discard option. User configuration looks like using runtime discard
	 * or periodic fstrim instead of it.
	 */
	if (f2fs_realtime_discard_enable(sbi))
		goto out;

	start_block = START_BLOCK(sbi, start_segno);
	end_block = START_BLOCK(sbi, end_segno + 1);

	__init_discard_policy(sbi, &dpolicy, DPOLICY_FSTRIM, cpc.trim_minlen);
	trimmed = __issue_discard_cmd_range(sbi, &dpolicy,
					start_block, end_block);

	trimmed += __wait_discard_cmd_range(sbi, &dpolicy,
					start_block, end_block);
out:
	if (!err)
		range->len = F2FS_BLK_TO_BYTES(trimmed);
	return err;
}

static bool __has_curseg_space(struct f2fs_sb_info *sbi, int type)
{
	struct curseg_info *curseg = CURSEG_I(sbi, type);
	if (curseg->next_blkoff < sbi->blocks_per_seg)
		return true;
	return false;
}

int f2fs_rw_hint_to_seg_type(enum rw_hint hint)
{
	switch (hint) {
	case WRITE_LIFE_SHORT:
		return CURSEG_HOT_DATA;
	case WRITE_LIFE_EXTREME:
		return CURSEG_COLD_DATA;
	default:
		return CURSEG_WARM_DATA;
	}
}

/* This returns write hints for each segment type. This hints will be
 * passed down to block layer. There are mapping tables which depend on
 * the mount option 'whint_mode'.
 *
 * 1) whint_mode=off. F2FS only passes down WRITE_LIFE_NOT_SET.
 *
 * 2) whint_mode=user-based. F2FS tries to pass down hints given by users.
 *
 * User                  F2FS                     Block
 * ----                  ----                     -----
 *                       META                     WRITE_LIFE_NOT_SET
 *                       HOT_NODE                 "
 *                       WARM_NODE                "
 *                       COLD_NODE                "
 * ioctl(COLD)           COLD_DATA                WRITE_LIFE_EXTREME
 * extension list        "                        "
 *
 * -- buffered io
 * WRITE_LIFE_EXTREME    COLD_DATA                WRITE_LIFE_EXTREME
 * WRITE_LIFE_SHORT      HOT_DATA                 WRITE_LIFE_SHORT
 * WRITE_LIFE_NOT_SET    WARM_DATA                WRITE_LIFE_NOT_SET
 * WRITE_LIFE_NONE       "                        "
 * WRITE_LIFE_MEDIUM     "                        "
 * WRITE_LIFE_LONG       "                        "
 *
 * -- direct io
 * WRITE_LIFE_EXTREME    COLD_DATA                WRITE_LIFE_EXTREME
 * WRITE_LIFE_SHORT      HOT_DATA                 WRITE_LIFE_SHORT
 * WRITE_LIFE_NOT_SET    WARM_DATA                WRITE_LIFE_NOT_SET
 * WRITE_LIFE_NONE       "                        WRITE_LIFE_NONE
 * WRITE_LIFE_MEDIUM     "                        WRITE_LIFE_MEDIUM
 * WRITE_LIFE_LONG       "                        WRITE_LIFE_LONG
 *
 * 3) whint_mode=fs-based. F2FS passes down hints with its policy.
 *
 * User                  F2FS                     Block
 * ----                  ----                     -----
 *                       META                     WRITE_LIFE_MEDIUM;
 *                       HOT_NODE                 WRITE_LIFE_NOT_SET
 *                       WARM_NODE                "
 *                       COLD_NODE                WRITE_LIFE_NONE
 * ioctl(COLD)           COLD_DATA                WRITE_LIFE_EXTREME
 * extension list        "                        "
 *