+// SPDX-License-Identifier: GPL-2.0
/*
* fs/f2fs/segment.c
*
* Copyright (c) 2012 Samsung Electronics Co., Ltd.
* http://www.samsung.com/
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
*/
#include <linux/fs.h>
#include <linux/f2fs_fs.h>
return result - size + __reverse_ffz(tmp);
}
-bool need_SSR(struct f2fs_sb_info *sbi)
+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);
if (test_opt(sbi, LFS))
return false;
- if (sbi->gc_thread && sbi->gc_thread->gc_urgent)
+ 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 register_inmem_page(struct inode *inode, struct page *page)
+void f2fs_register_inmem_page(struct inode *inode, struct page *page)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct f2fs_inode_info *fi = F2FS_I(inode);
f2fs_trace_pid(page);
- set_page_private(page, (unsigned long)ATOMIC_WRITTEN_PAGE);
- SetPagePrivate(page);
+ f2fs_set_page_private(page, (unsigned long)ATOMIC_WRITTEN_PAGE);
new = f2fs_kmem_cache_alloc(inmem_entry_slab, GFP_NOFS);
}
static int __revoke_inmem_pages(struct inode *inode,
- struct list_head *head, bool drop, bool recover)
+ struct list_head *head, bool drop, bool recover,
+ bool trylock)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct inmem_pages *cur, *tmp;
if (drop)
trace_f2fs_commit_inmem_page(page, INMEM_DROP);
- lock_page(page);
+ 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;
trace_f2fs_commit_inmem_page(page, INMEM_REVOKE);
retry:
set_new_dnode(&dn, inode, NULL, NULL, 0);
- err = get_dnode_of_data(&dn, page->index, LOOKUP_NODE);
+ err = f2fs_get_dnode_of_data(&dn, page->index,
+ LOOKUP_NODE);
if (err) {
if (err == -ENOMEM) {
congestion_wait(BLK_RW_ASYNC, HZ/50);
err = -EAGAIN;
goto next;
}
- get_node_info(sbi, dn.nid, &ni);
+
+ err = f2fs_get_node_info(sbi, dn.nid, &ni);
+ if (err) {
+ f2fs_put_dnode(&dn);
+ return err;
+ }
+
if (cur->old_addr == NEW_ADDR) {
- invalidate_blocks(sbi, dn.data_blkaddr);
+ f2fs_invalidate_blocks(sbi, dn.data_blkaddr);
f2fs_update_data_blkaddr(&dn, NEW_ADDR);
} else
f2fs_replace_block(sbi, &dn, dn.data_blkaddr,
}
next:
/* we don't need to invalidate this in the sccessful status */
- if (drop || recover)
+ if (drop || recover) {
ClearPageUptodate(page);
- set_page_private(page, 0);
- ClearPagePrivate(page);
+ clear_cold_data(page);
+ }
+ f2fs_clear_page_private(page);
f2fs_put_page(page, 1);
list_del(&cur->list);
return err;
}
-void drop_inmem_pages_all(struct f2fs_sb_info *sbi)
+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;
spin_unlock(&sbi->inode_lock[ATOMIC_FILE]);
if (inode) {
- drop_inmem_pages(inode);
+ if (gc_failure) {
+ if (fi->i_gc_failures[GC_FAILURE_ATOMIC])
+ goto drop;
+ goto skip;
+ }
+drop:
+ set_inode_flag(inode, FI_ATOMIC_REVOKE_REQUEST);
+ f2fs_drop_inmem_pages(inode);
iput(inode);
}
+skip:
congestion_wait(BLK_RW_ASYNC, HZ/50);
cond_resched();
goto next;
}
-void drop_inmem_pages(struct inode *inode)
+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);
- mutex_lock(&fi->inmem_lock);
- __revoke_inmem_pages(inode, &fi->inmem_pages, true, false);
- spin_lock(&sbi->inode_lock[ATOMIC_FILE]);
- if (!list_empty(&fi->inmem_ilist))
- list_del_init(&fi->inmem_ilist);
- spin_unlock(&sbi->inode_lock[ATOMIC_FILE]);
- mutex_unlock(&fi->inmem_lock);
+ while (!list_empty(&fi->inmem_pages)) {
+ mutex_lock(&fi->inmem_lock);
+ __revoke_inmem_pages(inode, &fi->inmem_pages,
+ true, false, true);
+
+ if (list_empty(&fi->inmem_pages)) {
+ spin_lock(&sbi->inode_lock[ATOMIC_FILE]);
+ if (!list_empty(&fi->inmem_ilist))
+ list_del_init(&fi->inmem_ilist);
+ spin_unlock(&sbi->inode_lock[ATOMIC_FILE]);
+ }
+ mutex_unlock(&fi->inmem_lock);
+ }
clear_inode_flag(inode, FI_ATOMIC_FILE);
- clear_inode_flag(inode, FI_HOT_DATA);
+ fi->i_gc_failures[GC_FAILURE_ATOMIC] = 0;
stat_dec_atomic_write(inode);
}
-void drop_inmem_page(struct inode *inode, struct page *page)
+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);
break;
}
- f2fs_bug_on(sbi, !cur || cur->page != page);
+ f2fs_bug_on(sbi, list_empty(head) || cur->page != page);
list_del(&cur->list);
mutex_unlock(&fi->inmem_lock);
kmem_cache_free(inmem_entry_slab, cur);
ClearPageUptodate(page);
- set_page_private(page, 0);
- ClearPagePrivate(page);
+ f2fs_clear_page_private(page);
f2fs_put_page(page, 0);
trace_f2fs_commit_inmem_page(page, INMEM_INVALIDATE);
}
-static int __commit_inmem_pages(struct inode *inode,
- struct list_head *revoke_list)
+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);
.op_flags = REQ_SYNC | REQ_PRIO,
.io_type = FS_DATA_IO,
};
- pgoff_t last_idx = ULONG_MAX;
+ 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;
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);
- f2fs_wait_on_page_writeback(page, DATA, true);
if (clear_page_dirty_for_io(page)) {
inode_dec_dirty_pages(inode);
- remove_dirty_inode(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 = do_write_data_page(&fio);
+ err = f2fs_do_write_data_page(&fio);
if (err) {
if (err == -ENOMEM) {
congestion_wait(BLK_RW_ASYNC, HZ/50);
}
/* record old blkaddr for revoking */
cur->old_addr = fio.old_blkaddr;
- last_idx = page->index;
+ submit_bio = true;
}
unlock_page(page);
- list_move_tail(&cur->list, revoke_list);
+ list_move_tail(&cur->list, &revoke_list);
}
- if (last_idx != ULONG_MAX)
- f2fs_submit_merged_write_cond(sbi, inode, 0, last_idx, DATA);
+ if (submit_bio)
+ f2fs_submit_merged_write_cond(sbi, inode, NULL, 0, DATA);
- if (!err)
- __revoke_inmem_pages(inode, revoke_list, false, false);
+ 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 commit_inmem_pages(struct inode *inode)
+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 list_head revoke_list;
int err;
- INIT_LIST_HEAD(&revoke_list);
f2fs_balance_fs(sbi, true);
- f2fs_lock_op(sbi);
+ down_write(&fi->i_gc_rwsem[WRITE]);
+
+ f2fs_lock_op(sbi);
set_inode_flag(inode, FI_ATOMIC_COMMIT);
mutex_lock(&fi->inmem_lock);
- err = __commit_inmem_pages(inode, &revoke_list);
- if (err) {
- int ret;
- /*
- * 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.
- */
- ret = __revoke_inmem_pages(inode, &revoke_list, false, true);
- if (ret)
- err = ret;
+ err = __f2fs_commit_inmem_pages(inode);
- /* drop all uncommitted pages */
- __revoke_inmem_pages(inode, &fi->inmem_pages, true, false);
- }
spin_lock(&sbi->inode_lock[ATOMIC_FILE]);
if (!list_empty(&fi->inmem_ilist))
list_del_init(&fi->inmem_ilist);
clear_inode_flag(inode, FI_ATOMIC_COMMIT);
f2fs_unlock_op(sbi);
+ up_write(&fi->i_gc_rwsem[WRITE]);
+
return err;
}
*/
void f2fs_balance_fs(struct f2fs_sb_info *sbi, bool need)
{
-#ifdef CONFIG_F2FS_FAULT_INJECTION
if (time_to_inject(sbi, FAULT_CHECKPOINT)) {
f2fs_show_injection_info(FAULT_CHECKPOINT);
f2fs_stop_checkpoint(sbi, false);
}
-#endif
/* 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.
return;
/* try to shrink extent cache when there is no enough memory */
- if (!available_free_memory(sbi, EXTENT_CACHE))
+ if (!f2fs_available_free_memory(sbi, EXTENT_CACHE))
f2fs_shrink_extent_tree(sbi, EXTENT_CACHE_SHRINK_NUMBER);
/* check the # of cached NAT entries */
- if (!available_free_memory(sbi, NAT_ENTRIES))
- try_to_free_nats(sbi, NAT_ENTRY_PER_BLOCK);
+ if (!f2fs_available_free_memory(sbi, NAT_ENTRIES))
+ f2fs_try_to_free_nats(sbi, NAT_ENTRY_PER_BLOCK);
- if (!available_free_memory(sbi, FREE_NIDS))
- try_to_free_nids(sbi, MAX_FREE_NIDS);
+ if (!f2fs_available_free_memory(sbi, FREE_NIDS))
+ f2fs_try_to_free_nids(sbi, MAX_FREE_NIDS);
else
- build_free_nids(sbi, false, false);
+ f2fs_build_free_nids(sbi, false, false);
- if (!is_idle(sbi) && !excess_dirty_nats(sbi))
+ 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 (!available_free_memory(sbi, NAT_ENTRIES) ||
- !available_free_memory(sbi, INO_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);
- sync_dirty_inodes(sbi, FILE_INODE);
+ 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 = f2fs_bio_alloc(sbi, 0, true);
+ struct bio *bio;
int ret;
+ bio = f2fs_bio_alloc(sbi, 0, false);
+ if (!bio)
+ return -ENOMEM;
+
bio->bi_rw = REQ_OP_WRITE;
bio->bi_bdev = bdev;
ret = submit_bio_wait(WRITE_FLUSH, bio);
int ret = 0;
int i;
- if (!sbi->s_ndevs)
+ if (!f2fs_is_multi_device(sbi))
return __submit_flush_wait(sbi, sbi->sb->s_bdev);
for (i = 0; i < sbi->s_ndevs; i++) {
- if (!is_dirty_device(sbi, ino, i, FLUSH_INO))
+ if (!f2fs_is_dirty_device(sbi, ino, i, FLUSH_INO))
continue;
ret = __submit_flush_wait(sbi, FDEV(i).bdev);
if (ret)
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->issing_flush) == 1 || sbi->s_ndevs > 1) {
+ if (atomic_inc_return(&fcc->queued_flush) == 1 ||
+ f2fs_is_multi_device(sbi)) {
ret = submit_flush_wait(sbi, ino);
- atomic_dec(&fcc->issing_flush);
+ atomic_dec(&fcc->queued_flush);
atomic_inc(&fcc->issued_flush);
return ret;
if (fcc->f2fs_issue_flush) {
wait_for_completion(&cmd.wait);
- atomic_dec(&fcc->issing_flush);
+ 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->issing_flush);
+ atomic_dec(&fcc->queued_flush);
} else {
struct flush_cmd *tmp, *next;
llist_for_each_entry_safe(tmp, next, list, llnode) {
if (tmp == &cmd) {
cmd.ret = ret;
- atomic_dec(&fcc->issing_flush);
+ atomic_dec(&fcc->queued_flush);
continue;
}
tmp->ret = ret;
return cmd.ret;
}
-int create_flush_cmd_control(struct f2fs_sb_info *sbi)
+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 (!fcc)
return -ENOMEM;
atomic_set(&fcc->issued_flush, 0);
- atomic_set(&fcc->issing_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;
"f2fs_flush-%u:%u", MAJOR(dev), MINOR(dev));
if (IS_ERR(fcc->f2fs_issue_flush)) {
err = PTR_ERR(fcc->f2fs_issue_flush);
- kfree(fcc);
+ kvfree(fcc);
SM_I(sbi)->fcc_info = NULL;
return err;
}
return err;
}
-void destroy_flush_cmd_control(struct f2fs_sb_info *sbi, bool free)
+void f2fs_destroy_flush_cmd_control(struct f2fs_sb_info *sbi, bool free)
{
struct flush_cmd_control *fcc = SM_I(sbi)->fcc_info;
kthread_stop(flush_thread);
}
if (free) {
- kfree(fcc);
+ kvfree(fcc);
SM_I(sbi)->fcc_info = NULL;
}
}
{
int ret = 0, i;
- if (!sbi->s_ndevs)
+ if (!f2fs_is_multi_device(sbi))
return 0;
for (i = 1; i < sbi->s_ndevs; i++) {
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;
+ 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) {
+ 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) {
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)
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;
struct discard_cmd *dc)
{
if (dc->state == D_DONE)
- atomic_dec(&dcc->issing_discard);
+ atomic_sub(dc->queued, &dcc->queued_discard);
list_del(&dc->list);
rb_erase(&dc->rb_node, &dcc->root);
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)
- f2fs_msg(sbi->sb, KERN_INFO,
- "Issue discard(%u, %u, %u) failed, ret: %d",
- dc->lstart, dc->start, dc->len, 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 = bio->bi_error;
- dc->state = D_DONE;
- complete_all(&dc->wait);
+
+ 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);
}
/* 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 void __submit_discard_cmd(struct f2fs_sb_info *sbi,
+static int __submit_discard_cmd(struct f2fs_sb_info *sbi,
struct discard_policy *dpolicy,
- struct discard_cmd *dc)
+ 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);
- struct bio *bio = NULL;
int flag = dpolicy->sync ? REQ_SYNC : 0;
+ block_t lstart, start, len, total_len;
+ int err = 0;
if (dc->state != D_PREP)
- return;
+ return 0;
- trace_f2fs_issue_discard(dc->bdev, dc->start, dc->len);
+ if (is_sbi_flag_set(sbi, SBI_NEED_FSCK))
+ return 0;
- dc->error = __blkdev_issue_discard(dc->bdev,
- SECTOR_FROM_BLOCK(dc->start),
- SECTOR_FROM_BLOCK(dc->len),
- GFP_NOFS, 0, &bio);
- if (!dc->error) {
- /* should keep before submission to avoid D_DONE right away */
- dc->state = D_SUBMIT;
- atomic_inc(&dcc->issued_discard);
- atomic_inc(&dcc->issing_discard);
- if (bio) {
- bio->bi_private = dc;
- bio->bi_end_io = f2fs_submit_discard_endio;
- submit_bio(flag, bio);
- list_move_tail(&dc->list, wait_list);
- __check_sit_bitmap(sbi, dc->start, dc->start + dc->len);
+ trace_f2fs_issue_discard(bdev, dc->start, dc->len);
+
+ lstart = dc->lstart;
+ start = dc->start;
+ len = dc->len;
+ total_len = len;
+
+ dc->len = 0;
- f2fs_update_iostat(sbi, FS_DISCARD, 1);
+ 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;
}
- } else {
- __remove_discard_cmd(sbi, dc);
+
+ (*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;
+ submit_bio(flag, 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,
goto do_insert;
}
- p = __lookup_rb_tree_for_insert(sbi, &dcc->root, &parent, lstart);
+ p = f2fs_lookup_rb_tree_for_insert(sbi, &dcc->root, &parent, lstart);
do_insert:
dc = __attach_discard_cmd(sbi, bdev, lstart, start, len, parent, p);
if (!dc)
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;
- mutex_lock(&dcc->cmd_lock);
-
- dc = (struct discard_cmd *)__lookup_rb_tree_ret(&dcc->root,
+ dc = (struct discard_cmd *)f2fs_lookup_rb_tree_ret(&dcc->root,
NULL, lstart,
(struct rb_entry **)&prev_dc,
(struct rb_entry **)&next_dc,
if (prev_dc && prev_dc->state == D_PREP &&
prev_dc->bdev == bdev &&
- __is_discard_back_mergeable(&di, &prev_dc->di)) {
+ __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);
if (next_dc && next_dc->state == D_PREP &&
next_dc->bdev == bdev &&
- __is_discard_front_mergeable(&di, &next_dc->di)) {
+ __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;
node = rb_next(&prev_dc->rb_node);
next_dc = rb_entry_safe(node, struct discard_cmd, rb_node);
}
-
- mutex_unlock(&dcc->cmd_lock);
}
static int __queue_discard_cmd(struct f2fs_sb_info *sbi,
{
block_t lblkstart = blkstart;
+ if (!f2fs_bdev_support_discard(bdev))
+ return 0;
+
trace_f2fs_queue_discard(bdev, blkstart, blklen);
- if (sbi->s_ndevs) {
+ 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);
+ 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 list_head *pend_list;
struct discard_cmd *dc, *tmp;
struct blk_plug plug;
- int i, iter = 0, issued = 0;
+ 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;
- f2fs_bug_on(sbi, !__check_rb_tree_consistence(sbi, &dcc->root));
+ 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)) {
+ !is_idle(sbi, DISCARD_TIME)) {
io_interrupted = true;
- goto skip;
+ break;
}
- __submit_discard_cmd(sbi, dpolicy, dc);
- issued++;
-skip:
- if (++iter >= dpolicy->max_requests)
+ __submit_discard_cmd(sbi, dpolicy, dc, &issued);
+
+ if (issued >= dpolicy->max_requests)
break;
}
blk_finish_plug(&plug);
next:
mutex_unlock(&dcc->cmd_lock);
- if (iter >= dpolicy->max_requests)
+ if (issued >= dpolicy->max_requests || io_interrupted)
break;
}
return dropped;
}
-void drop_discard_cmd(struct f2fs_sb_info *sbi)
+void f2fs_drop_discard_cmd(struct f2fs_sb_info *sbi)
{
__drop_discard_cmd(sbi);
}
return trimmed;
}
-static void __wait_all_discard_cmd(struct f2fs_sb_info *sbi,
+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) {
- __wait_discard_cmd_range(sbi, dpolicy, 0, UINT_MAX);
- return;
- }
+ if (dpolicy)
+ return __wait_discard_cmd_range(sbi, dpolicy, 0, UINT_MAX);
/* wait all */
__init_discard_policy(sbi, &dp, DPOLICY_FSTRIM, 1);
- __wait_discard_cmd_range(sbi, &dp, 0, UINT_MAX);
+ discard_blks = __wait_discard_cmd_range(sbi, &dp, 0, UINT_MAX);
__init_discard_policy(sbi, &dp, DPOLICY_UMOUNT, 1);
- __wait_discard_cmd_range(sbi, &dp, 0, UINT_MAX);
+ 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 */
bool need_wait = false;
mutex_lock(&dcc->cmd_lock);
- dc = (struct discard_cmd *)__lookup_rb_tree(&dcc->root, NULL, blkaddr);
+ 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);
__wait_one_discard_bio(sbi, dc);
}
-void stop_discard_thread(struct f2fs_sb_info *sbi)
+void f2fs_stop_discard_thread(struct f2fs_sb_info *sbi)
{
struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
}
/* This comes from f2fs_put_super */
-bool f2fs_wait_discard_bios(struct f2fs_sb_info *sbi)
+bool f2fs_issue_discard_timeout(struct f2fs_sb_info *sbi)
{
struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
struct discard_policy dpolicy;
__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;
}
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 (dcc->discard_wake)
- dcc->discard_wake = 0;
-
- if (sbi->gc_thread && sbi->gc_thread->gc_urgent)
+ 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) {
+ 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;
}
block_t lblkstart = blkstart;
int devi = 0;
- if (sbi->s_ndevs) {
+ 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;
}
- /*
- * We need to know the type of the zone: for conventional zones,
- * use regular discard if the drive supports it. For sequential
- * zones, reset the zone write pointer.
- */
- switch (get_blkz_type(sbi, bdev, blkstart)) {
-
- case BLK_ZONE_TYPE_CONVENTIONAL:
- if (!blk_queue_discard(bdev_get_queue(bdev)))
- return 0;
- return __queue_discard_cmd(sbi, bdev, lblkstart, blklen);
- case BLK_ZONE_TYPE_SEQWRITE_REQ:
- case BLK_ZONE_TYPE_SEQWRITE_PREF:
+ /* 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_msg(sbi->sb, KERN_INFO,
- "(%d) %s: Unaligned discard attempted (block %x + %x)",
- devi, sbi->s_ndevs ? FDEV(devi).path: "",
- blkstart, blklen);
+ 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);
- default:
- /* Unknown zone type: broken device ? */
- return -EIO;
+ 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
struct block_device *bdev, block_t blkstart, block_t blklen)
{
#ifdef CONFIG_BLK_DEV_ZONED
- if (f2fs_sb_has_blkzoned(sbi->sb) &&
- bdev_zoned_model(bdev) != BLK_ZONED_NONE)
+ 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);
struct list_head *head = &SM_I(sbi)->dcc_info->entry_list;
int i;
- if (se->valid_blocks == max_blocks || !f2fs_discard_en(sbi))
+ if (se->valid_blocks == max_blocks || !f2fs_hw_support_discard(sbi))
return false;
if (!force) {
- if (!test_opt(sbi, DISCARD) || !se->valid_blocks ||
+ 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;
return false;
}
-void release_discard_addrs(struct f2fs_sb_info *sbi)
+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) {
- list_del(&entry->list);
- kmem_cache_free(discard_entry_slab, entry);
- }
+ list_for_each_entry_safe(entry, this, head, list)
+ release_discard_addr(entry);
}
/*
- * Should call clear_prefree_segments after checkpoint is done.
+ * Should call f2fs_clear_prefree_segments after checkpoint is done.
*/
static void set_prefree_as_free_segments(struct f2fs_sb_info *sbi)
{
mutex_unlock(&dirty_i->seglist_lock);
}
-void clear_prefree_segments(struct f2fs_sb_info *sbi, struct cp_control *cpc)
+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;
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);
- for (i = start; i < end; i++)
- clear_bit(i, prefree_map);
+ if (need_align) {
+ start = rounddown(start, sbi->segs_per_sec);
+ end = roundup(end, sbi->segs_per_sec);
+ }
- dirty_i->nr_dirty[PRE] -= end - start;
+ for (i = start; i < end; i++) {
+ if (test_and_clear_bit(i, prefree_map))
+ dirty_i->nr_dirty[PRE]--;
+ }
- if (!test_opt(sbi, DISCARD))
+ if (!f2fs_realtime_discard_enable(sbi))
continue;
if (force && start >= cpc->trim_start &&
(end - 1) <= cpc->trim_end)
continue;
- if (!test_opt(sbi, LFS) || sbi->segs_per_sec == 1) {
+ 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;
sbi->blocks_per_seg, cur_pos);
len = next_pos - cur_pos;
- if (f2fs_sb_has_blkzoned(sbi->sb) ||
+ if (f2fs_sb_has_blkzoned(sbi) ||
(force && len < cpc->trim_minlen))
goto skip;
if (cur_pos < sbi->blocks_per_seg)
goto find_next;
- list_del(&entry->list);
+ release_discard_addr(entry);
dcc->nr_discards -= total_len;
- kmem_cache_free(discard_entry_slab, entry);
}
wake_up_discard_thread(sbi, false);
INIT_LIST_HEAD(&dcc->fstrim_list);
mutex_init(&dcc->cmd_lock);
atomic_set(&dcc->issued_discard, 0);
- atomic_set(&dcc->issing_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;
+ dcc->rbtree_check = false;
init_waitqueue_head(&dcc->discard_wait_queue);
SM_I(sbi)->dcc_info = dcc;
"f2fs_discard-%u:%u", MAJOR(dev), MINOR(dev));
if (IS_ERR(dcc->f2fs_issue_discard)) {
err = PTR_ERR(dcc->f2fs_issue_discard);
- kfree(dcc);
+ kvfree(dcc);
SM_I(sbi)->dcc_info = NULL;
return err;
}
if (!dcc)
return;
- stop_discard_thread(sbi);
+ f2fs_stop_discard_thread(sbi);
- kfree(dcc);
+ kvfree(dcc);
SM_I(sbi)->dcc_info = NULL;
}
(new_vblocks > sbi->blocks_per_seg)));
se->valid_blocks = new_vblocks;
- se->mtime = get_mtime(sbi);
- SIT_I(sbi)->max_mtime = se->mtime;
+ 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) {
mir_exist = f2fs_test_and_set_bit(offset,
se->cur_valid_map_mir);
if (unlikely(exist != mir_exist)) {
- f2fs_msg(sbi->sb, KERN_ERR, "Inconsistent error "
- "when setting bitmap, blk:%u, old bit:%d",
- blkaddr, 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_msg(sbi->sb, KERN_ERR,
- "Bitmap was wrongly set, blk:%u", blkaddr);
+ f2fs_err(sbi, "Bitmap was wrongly set, blk:%u",
+ blkaddr);
f2fs_bug_on(sbi, 1);
se->valid_blocks--;
del = 0;
}
- if (f2fs_discard_en(sbi) &&
- !f2fs_test_and_set_bit(offset, se->discard_map))
+ if (!f2fs_test_and_set_bit(offset, se->discard_map))
sbi->discard_blks--;
/* don't overwrite by SSR to keep node chain */
- if (IS_NODESEG(se->type)) {
+ if (IS_NODESEG(se->type) &&
+ !is_sbi_flag_set(sbi, SBI_CP_DISABLED)) {
if (!f2fs_test_and_set_bit(offset, se->ckpt_valid_map))
se->ckpt_valid_blocks++;
}
mir_exist = f2fs_test_and_clear_bit(offset,
se->cur_valid_map_mir);
if (unlikely(exist != mir_exist)) {
- f2fs_msg(sbi->sb, KERN_ERR, "Inconsistent error "
- "when clearing bitmap, blk:%u, old bit:%d",
- blkaddr, 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_msg(sbi->sb, KERN_ERR,
- "Bitmap was wrongly cleared, blk:%u", blkaddr);
+ 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_discard_en(sbi) &&
- f2fs_test_and_clear_bit(offset, se->discard_map))
+ if (f2fs_test_and_clear_bit(offset, se->discard_map))
sbi->discard_blks++;
}
if (!f2fs_test_bit(offset, se->ckpt_valid_map))
/* update total number of valid blocks to be written in ckpt area */
SIT_I(sbi)->written_valid_blocks += del;
- if (sbi->segs_per_sec > 1)
+ if (__is_large_section(sbi))
get_sec_entry(sbi, segno)->valid_blocks += del;
}
-void invalidate_blocks(struct f2fs_sb_info *sbi, block_t addr)
+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);
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);
up_write(&sit_i->sentry_lock);
}
-bool is_checkpointed_data(struct f2fs_sb_info *sbi, block_t blkaddr)
+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 (blkaddr == NEW_ADDR || blkaddr == NULL_ADDR)
+ if (!__is_valid_data_blkaddr(blkaddr))
return true;
down_read(&sit_i->sentry_lock);
/*
* Calculate the number of current summary pages for writing
*/
-int npages_for_summary_flush(struct f2fs_sb_info *sbi, bool for_ra)
+int f2fs_npages_for_summary_flush(struct f2fs_sb_info *sbi, bool for_ra)
{
int valid_sum_count = 0;
int i, sum_in_page;
/*
* Caller should put this summary page
*/
-struct page *get_sum_page(struct f2fs_sb_info *sbi, unsigned int segno)
+struct page *f2fs_get_sum_page(struct f2fs_sb_info *sbi, unsigned int segno)
{
- return get_meta_page(sbi, GET_SUM_BLOCK(sbi, segno));
+ return f2fs_get_meta_page_nofail(sbi, GET_SUM_BLOCK(sbi, segno));
}
-void update_meta_page(struct f2fs_sb_info *sbi, void *src, block_t blk_addr)
+void f2fs_update_meta_page(struct f2fs_sb_info *sbi,
+ void *src, block_t blk_addr)
{
- struct page *page = grab_meta_page(sbi, blk_addr);
+ struct page *page = f2fs_grab_meta_page(sbi, blk_addr);
memcpy(page_address(page), src, PAGE_SIZE);
set_page_dirty(page);
static void write_sum_page(struct f2fs_sb_info *sbi,
struct f2fs_summary_block *sum_blk, block_t blk_addr)
{
- update_meta_page(sbi, (void *)sum_blk, 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 = grab_meta_page(sbi, blk_addr);
+ 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);
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 (sbi->segs_per_sec != 1)
+ 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;
curseg->alloc_type = SSR;
__next_free_blkoff(sbi, curseg, 0);
- sum_page = get_sum_page(sbi, new_segno);
+ sum_page = f2fs_get_sum_page(sbi, new_segno);
+ f2fs_bug_on(sbi, IS_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);
int i, cnt;
bool reversed = false;
- /* need_SSR() already forces to do this */
+ /* 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;
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;
}
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))
+ 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 (need_SSR(sbi) && get_ssr_segment(sbi, type))
+ 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_new_segments(struct f2fs_sb_info *sbi)
+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;
.allocate_segment = allocate_segment_by_default,
};
-bool exist_trim_candidates(struct f2fs_sb_info *sbi, struct cp_control *cpc)
+bool f2fs_exist_trim_candidates(struct f2fs_sb_info *sbi,
+ struct cp_control *cpc)
{
__u64 trim_start = cpc->trim_start;
bool has_candidate = false;
return has_candidate;
}
-static void __issue_discard_cmd_range(struct f2fs_sb_info *sbi,
+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 *dc;
struct blk_plug plug;
int issued;
+ unsigned int trimmed = 0;
next:
issued = 0;
mutex_lock(&dcc->cmd_lock);
- f2fs_bug_on(sbi, !__check_rb_tree_consistence(sbi, &dcc->root));
+ if (unlikely(dcc->rbtree_check))
+ f2fs_bug_on(sbi, !f2fs_check_rb_tree_consistence(sbi,
+ &dcc->root));
- dc = (struct discard_cmd *)__lookup_rb_tree_ret(&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,
while (dc && dc->lstart <= end) {
struct rb_node *node;
+ int err = 0;
if (dc->len < dpolicy->granularity)
goto skip;
goto skip;
}
- __submit_discard_cmd(sbi, dpolicy, dc);
+ err = __submit_discard_cmd(sbi, dpolicy, dc, &issued);
- if (++issued >= dpolicy->max_requests) {
+ 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);
- __wait_all_discard_cmd(sbi, NULL);
+ 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))
blk_finish_plug(&plug);
mutex_unlock(&dcc->cmd_lock);
+
+ return trimmed;
}
int f2fs_trim_fs(struct f2fs_sb_info *sbi, struct fstrim_range *range)
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))
+ if (end < MAIN_BLKADDR(sbi))
goto out;
if (is_sbi_flag_set(sbi, SBI_NEED_FSCK)) {
- f2fs_msg(sbi->sb, KERN_WARNING,
- "Found FS corruption, run fsck to fix.");
- goto out;
+ 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));
goto out;
mutex_lock(&sbi->gc_mutex);
- err = write_checkpoint(sbi, &cpc);
+ err = f2fs_write_checkpoint(sbi, &cpc);
mutex_unlock(&sbi->gc_mutex);
if (err)
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);
- __issue_discard_cmd_range(sbi, &dpolicy, start_block, end_block);
-
/*
* 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 (!test_opt(sbi, DISCARD)) {
- trimmed = __wait_discard_cmd_range(sbi, &dpolicy,
+ 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);
- range->len = F2FS_BLK_TO_BYTES(trimmed);
- }
out:
+ if (!err)
+ range->len = F2FS_BLK_TO_BYTES(trimmed);
return err;
}
return false;
}
-int rw_hint_to_seg_type(enum rw_hint hint)
+int f2fs_rw_hint_to_seg_type(enum rw_hint hint)
{
switch (hint) {
case WRITE_LIFE_SHORT:
* WRITE_LIFE_LONG " WRITE_LIFE_LONG
*/
-enum rw_hint io_type_to_rw_hint(struct f2fs_sb_info *sbi,
+enum rw_hint f2fs_io_type_to_rw_hint(struct f2fs_sb_info *sbi,
enum page_type type, enum temp_type temp)
{
if (F2FS_OPTION(sbi).whint_mode == WHINT_MODE_USER) {
if (is_cold_data(fio->page) || file_is_cold(inode))
return CURSEG_COLD_DATA;
if (file_is_hot(inode) ||
- is_inode_flag_set(inode, FI_HOT_DATA))
+ is_inode_flag_set(inode, FI_HOT_DATA) ||
+ f2fs_is_atomic_file(inode) ||
+ f2fs_is_volatile_file(inode))
return CURSEG_HOT_DATA;
- /* rw_hint_to_seg_type(inode->i_write_hint); */
+ /* f2fs_rw_hint_to_seg_type(inode->i_write_hint); */
return CURSEG_WARM_DATA;
} else {
if (IS_DNODE(fio->page))
return type;
}
-void allocate_data_block(struct f2fs_sb_info *sbi, struct page *page,
+void f2fs_allocate_data_block(struct f2fs_sb_info *sbi, struct page *page,
block_t old_blkaddr, block_t *new_blkaddr,
struct f2fs_summary *sum, int type,
struct f2fs_io_info *fio, bool add_list)
INIT_LIST_HEAD(&fio->list);
fio->in_list = true;
+ fio->retry = false;
io = sbi->write_io[fio->type] + fio->temp;
spin_lock(&io->io_lock);
list_add_tail(&fio->list, &io->io_list);
struct f2fs_sb_info *sbi = fio->sbi;
unsigned int devidx;
- if (!sbi->s_ndevs)
+ if (!f2fs_is_multi_device(sbi))
return;
devidx = f2fs_target_device_index(sbi, fio->new_blkaddr);
/* update device state for fsync */
- set_dirty_device(sbi, fio->ino, devidx, FLUSH_INO);
+ f2fs_set_dirty_device(sbi, fio->ino, devidx, FLUSH_INO);
/* update device state for checkpoint */
if (!f2fs_test_bit(devidx, (char *)&sbi->dirty_device)) {
static void do_write_page(struct f2fs_summary *sum, struct f2fs_io_info *fio)
{
int type = __get_segment_type(fio);
- int err;
+ bool keep_order = (test_opt(fio->sbi, LFS) && type == CURSEG_COLD_DATA);
+ if (keep_order)
+ down_read(&fio->sbi->io_order_lock);
reallocate:
- allocate_data_block(fio->sbi, fio->page, fio->old_blkaddr,
+ f2fs_allocate_data_block(fio->sbi, fio->page, fio->old_blkaddr,
&fio->new_blkaddr, sum, type, fio, true);
+ if (GET_SEGNO(fio->sbi, fio->old_blkaddr) != NULL_SEGNO)
+ invalidate_mapping_pages(META_MAPPING(fio->sbi),
+ fio->old_blkaddr, fio->old_blkaddr);
/* writeout dirty page into bdev */
- err = f2fs_submit_page_write(fio);
- if (err == -EAGAIN) {
+ f2fs_submit_page_write(fio);
+ if (fio->retry) {
fio->old_blkaddr = fio->new_blkaddr;
goto reallocate;
- } else if (!err) {
- update_device_state(fio);
}
+
+ update_device_state(fio);
+
+ if (keep_order)
+ up_read(&fio->sbi->io_order_lock);
}
-void write_meta_page(struct f2fs_sb_info *sbi, struct page *page,
+void f2fs_do_write_meta_page(struct f2fs_sb_info *sbi, struct page *page,
enum iostat_type io_type)
{
struct f2fs_io_info fio = {
ClearPageError(page);
f2fs_submit_page_write(&fio);
+ stat_inc_meta_count(sbi, page->index);
f2fs_update_iostat(sbi, io_type, F2FS_BLKSIZE);
}
-void write_node_page(unsigned int nid, struct f2fs_io_info *fio)
+void f2fs_do_write_node_page(unsigned int nid, struct f2fs_io_info *fio)
{
struct f2fs_summary sum;
f2fs_update_iostat(fio->sbi, fio->io_type, F2FS_BLKSIZE);
}
-void write_data_page(struct dnode_of_data *dn, struct f2fs_io_info *fio)
+void f2fs_outplace_write_data(struct dnode_of_data *dn,
+ struct f2fs_io_info *fio)
{
struct f2fs_sb_info *sbi = fio->sbi;
struct f2fs_summary sum;
- struct node_info ni;
f2fs_bug_on(sbi, dn->data_blkaddr == NULL_ADDR);
- get_node_info(sbi, dn->nid, &ni);
- set_summary(&sum, dn->nid, dn->ofs_in_node, ni.version);
+ set_summary(&sum, dn->nid, dn->ofs_in_node, fio->version);
do_write_page(&sum, fio);
f2fs_update_data_blkaddr(dn, fio->new_blkaddr);
f2fs_update_iostat(sbi, fio->io_type, F2FS_BLKSIZE);
}
-int rewrite_data_page(struct f2fs_io_info *fio)
+int f2fs_inplace_write_data(struct f2fs_io_info *fio)
{
int err;
struct f2fs_sb_info *sbi = fio->sbi;
+ unsigned int segno;
fio->new_blkaddr = fio->old_blkaddr;
/* i/o temperature is needed for passing down write hints */
__get_segment_type(fio);
- f2fs_bug_on(sbi, !IS_DATASEG(get_seg_entry(sbi,
- GET_SEGNO(sbi, fio->new_blkaddr))->type));
+ segno = GET_SEGNO(sbi, fio->new_blkaddr);
+
+ if (!IS_DATASEG(get_seg_entry(sbi, segno)->type)) {
+ set_sbi_flag(sbi, SBI_NEED_FSCK);
+ f2fs_warn(sbi, "%s: incorrect segment(%u) type, run fsck to fix.",
+ __func__, segno);
+ return -EFSCORRUPTED;
+ }
stat_inc_inplace_blocks(fio->sbi);
- err = f2fs_submit_page_bio(fio);
- if (!err)
+ if (fio->bio)
+ err = f2fs_merge_page_bio(fio);
+ else
+ err = f2fs_submit_page_bio(fio);
+ if (!err) {
update_device_state(fio);
-
- f2fs_update_iostat(fio->sbi, fio->io_type, F2FS_BLKSIZE);
+ f2fs_update_iostat(fio->sbi, fio->io_type, F2FS_BLKSIZE);
+ }
return err;
}
return i;
}
-void __f2fs_replace_block(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
+void f2fs_do_replace_block(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
block_t old_blkaddr, block_t new_blkaddr,
bool recover_curseg, bool recover_newaddr)
{
if (!recover_curseg || recover_newaddr)
update_sit_entry(sbi, new_blkaddr, 1);
- if (GET_SEGNO(sbi, old_blkaddr) != NULL_SEGNO)
+ if (GET_SEGNO(sbi, old_blkaddr) != NULL_SEGNO) {
+ invalidate_mapping_pages(META_MAPPING(sbi),
+ old_blkaddr, old_blkaddr);
update_sit_entry(sbi, old_blkaddr, -1);
+ }
locate_dirty_segment(sbi, GET_SEGNO(sbi, old_blkaddr));
locate_dirty_segment(sbi, GET_SEGNO(sbi, new_blkaddr));
set_summary(&sum, dn->nid, dn->ofs_in_node, version);
- __f2fs_replace_block(sbi, &sum, old_addr, new_addr,
+ f2fs_do_replace_block(sbi, &sum, old_addr, new_addr,
recover_curseg, recover_newaddr);
f2fs_update_data_blkaddr(dn, new_addr);
}
void f2fs_wait_on_page_writeback(struct page *page,
- enum page_type type, bool ordered)
+ enum page_type type, bool ordered, bool locked)
{
if (PageWriteback(page)) {
struct f2fs_sb_info *sbi = F2FS_P_SB(page);
- f2fs_submit_merged_write_cond(sbi, page->mapping->host,
- 0, page->index, type);
- if (ordered)
+ f2fs_submit_merged_write_cond(sbi, NULL, page, 0, type);
+ if (ordered) {
wait_on_page_writeback(page);
- else
+ f2fs_bug_on(sbi, locked && PageWriteback(page));
+ } else {
wait_for_stable_page(page);
+ }
}
}
-void f2fs_wait_on_block_writeback(struct f2fs_sb_info *sbi, block_t blkaddr)
+void f2fs_wait_on_block_writeback(struct inode *inode, block_t blkaddr)
{
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct page *cpage;
- if (blkaddr == NEW_ADDR || blkaddr == NULL_ADDR)
+ if (!f2fs_post_read_required(inode))
+ return;
+
+ if (!__is_valid_data_blkaddr(blkaddr))
return;
cpage = find_lock_page(META_MAPPING(sbi), blkaddr);
if (cpage) {
- f2fs_wait_on_page_writeback(cpage, DATA, true);
+ f2fs_wait_on_page_writeback(cpage, DATA, true, true);
f2fs_put_page(cpage, 1);
}
}
-static void read_compacted_summaries(struct f2fs_sb_info *sbi)
+void f2fs_wait_on_block_writeback_range(struct inode *inode, block_t blkaddr,
+ block_t len)
+{
+ block_t i;
+
+ for (i = 0; i < len; i++)
+ f2fs_wait_on_block_writeback(inode, blkaddr + i);
+}
+
+static int read_compacted_summaries(struct f2fs_sb_info *sbi)
{
struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);
struct curseg_info *seg_i;
start = start_sum_block(sbi);
- page = get_meta_page(sbi, start++);
+ page = f2fs_get_meta_page(sbi, start++);
+ if (IS_ERR(page))
+ return PTR_ERR(page);
kaddr = (unsigned char *)page_address(page);
/* Step 1: restore nat cache */
f2fs_put_page(page, 1);
page = NULL;
- page = get_meta_page(sbi, start++);
+ page = f2fs_get_meta_page(sbi, start++);
+ if (IS_ERR(page))
+ return PTR_ERR(page);
kaddr = (unsigned char *)page_address(page);
offset = 0;
}
}
f2fs_put_page(page, 1);
+ return 0;
}
static int read_normal_summaries(struct f2fs_sb_info *sbi, int type)
unsigned short blk_off;
unsigned int segno = 0;
block_t blk_addr = 0;
+ int err = 0;
/* get segment number and block addr */
if (IS_DATASEG(type)) {
blk_addr = GET_SUM_BLOCK(sbi, segno);
}
- new = get_meta_page(sbi, blk_addr);
+ new = f2fs_get_meta_page(sbi, blk_addr);
+ if (IS_ERR(new))
+ return PTR_ERR(new);
sum = (struct f2fs_summary_block *)page_address(new);
if (IS_NODESEG(type)) {
ns->ofs_in_node = 0;
}
} else {
- restore_node_summary(sbi, segno, sum);
+ err = f2fs_restore_node_summary(sbi, segno, sum);
+ if (err)
+ goto out;
}
}
curseg->alloc_type = ckpt->alloc_type[type];
curseg->next_blkoff = blk_off;
mutex_unlock(&curseg->curseg_mutex);
+out:
f2fs_put_page(new, 1);
- return 0;
+ return err;
}
static int restore_curseg_summaries(struct f2fs_sb_info *sbi)
int err;
if (is_set_ckpt_flags(sbi, CP_COMPACT_SUM_FLAG)) {
- int npages = npages_for_summary_flush(sbi, true);
+ int npages = f2fs_npages_for_summary_flush(sbi, true);
if (npages >= 2)
- ra_meta_pages(sbi, start_sum_block(sbi), npages,
+ f2fs_ra_meta_pages(sbi, start_sum_block(sbi), npages,
META_CP, true);
/* restore for compacted data summary */
- read_compacted_summaries(sbi);
+ err = read_compacted_summaries(sbi);
+ if (err)
+ return err;
type = CURSEG_HOT_NODE;
}
if (__exist_node_summaries(sbi))
- ra_meta_pages(sbi, sum_blk_addr(sbi, NR_CURSEG_TYPE, type),
+ f2fs_ra_meta_pages(sbi, sum_blk_addr(sbi, NR_CURSEG_TYPE, type),
NR_CURSEG_TYPE - type, META_CP, true);
for (; type <= CURSEG_COLD_NODE; type++) {
/* sanity check for summary blocks */
if (nats_in_cursum(nat_j) > NAT_JOURNAL_ENTRIES ||
- sits_in_cursum(sit_j) > SIT_JOURNAL_ENTRIES)
+ sits_in_cursum(sit_j) > SIT_JOURNAL_ENTRIES) {
+ f2fs_err(sbi, "invalid journal entries nats %u sits %u\n",
+ nats_in_cursum(nat_j), sits_in_cursum(sit_j));
return -EINVAL;
+ }
return 0;
}
int written_size = 0;
int i, j;
- page = grab_meta_page(sbi, blkaddr++);
+ page = f2fs_grab_meta_page(sbi, blkaddr++);
kaddr = (unsigned char *)page_address(page);
+ memset(kaddr, 0, PAGE_SIZE);
/* Step 1: write nat cache */
seg_i = CURSEG_I(sbi, CURSEG_HOT_DATA);
for (j = 0; j < blkoff; j++) {
if (!page) {
- page = grab_meta_page(sbi, blkaddr++);
+ page = f2fs_grab_meta_page(sbi, blkaddr++);
kaddr = (unsigned char *)page_address(page);
+ memset(kaddr, 0, PAGE_SIZE);
written_size = 0;
}
summary = (struct f2fs_summary *)(kaddr + written_size);
write_current_sum_page(sbi, i, blkaddr + (i - type));
}
-void write_data_summaries(struct f2fs_sb_info *sbi, block_t start_blk)
+void f2fs_write_data_summaries(struct f2fs_sb_info *sbi, block_t start_blk)
{
if (is_set_ckpt_flags(sbi, CP_COMPACT_SUM_FLAG))
write_compacted_summaries(sbi, start_blk);
write_normal_summaries(sbi, start_blk, CURSEG_HOT_DATA);
}
-void write_node_summaries(struct f2fs_sb_info *sbi, block_t start_blk)
+void f2fs_write_node_summaries(struct f2fs_sb_info *sbi, block_t start_blk)
{
write_normal_summaries(sbi, start_blk, CURSEG_HOT_NODE);
}
-int lookup_journal_in_cursum(struct f2fs_journal *journal, int type,
+int f2fs_lookup_journal_in_cursum(struct f2fs_journal *journal, int type,
unsigned int val, int alloc)
{
int i;
static struct page *get_current_sit_page(struct f2fs_sb_info *sbi,
unsigned int segno)
{
- return get_meta_page(sbi, current_sit_addr(sbi, segno));
+ return f2fs_get_meta_page_nofail(sbi, current_sit_addr(sbi, segno));
}
static struct page *get_next_sit_page(struct f2fs_sb_info *sbi,
src_off = current_sit_addr(sbi, start);
dst_off = next_sit_addr(sbi, src_off);
- page = grab_meta_page(sbi, dst_off);
+ page = f2fs_grab_meta_page(sbi, dst_off);
seg_info_to_sit_page(sbi, page, start);
set_page_dirty(page);
* CP calls this function, which flushes SIT entries including sit_journal,
* and moves prefree segs to free segs.
*/
-void flush_sit_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc)
+void f2fs_flush_sit_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc)
{
struct sit_info *sit_i = SIT_I(sbi);
unsigned long *bitmap = sit_i->dirty_sentries_bitmap;
struct f2fs_journal *journal = curseg->journal;
struct sit_entry_set *ses, *tmp;
struct list_head *head = &SM_I(sbi)->sit_entry_set;
- bool to_journal = true;
+ bool to_journal = !is_sbi_flag_set(sbi, SBI_IS_RESIZEFS);
struct seg_entry *se;
down_write(&sit_i->sentry_lock);
* entries, remove all entries from journal and add and account
* them in sit entry set.
*/
- if (!__has_cursum_space(journal, sit_i->dirty_sentries, SIT_JOURNAL))
+ if (!__has_cursum_space(journal, sit_i->dirty_sentries, SIT_JOURNAL) ||
+ !to_journal)
remove_sits_in_journal(sbi);
/*
int offset, sit_offset;
se = get_seg_entry(sbi, segno);
+#ifdef CONFIG_F2FS_CHECK_FS
+ if (memcmp(se->cur_valid_map, se->cur_valid_map_mir,
+ SIT_VBLOCK_MAP_SIZE))
+ f2fs_bug_on(sbi, 1);
+#endif
/* add discard candidates */
if (!(cpc->reason & CP_DISCARD)) {
}
if (to_journal) {
- offset = lookup_journal_in_cursum(journal,
+ offset = f2fs_lookup_journal_in_cursum(journal,
SIT_JOURNAL, segno, 1);
f2fs_bug_on(sbi, offset < 0);
segno_in_journal(journal, offset) =
cpu_to_le32(segno);
seg_info_to_raw_sit(se,
&sit_in_journal(journal, offset));
+ check_block_count(sbi, segno,
+ &sit_in_journal(journal, offset));
} else {
sit_offset = SIT_ENTRY_OFFSET(sit_i, segno);
seg_info_to_raw_sit(se,
&raw_sit->entries[sit_offset]);
+ check_block_count(sbi, segno,
+ &raw_sit->entries[sit_offset]);
}
__clear_bit(segno, bitmap);
SM_I(sbi)->sit_info = sit_i;
- sit_i->sentries = f2fs_kvzalloc(sbi, MAIN_SEGS(sbi) *
- sizeof(struct seg_entry), GFP_KERNEL);
+ sit_i->sentries =
+ f2fs_kvzalloc(sbi, array_size(sizeof(struct seg_entry),
+ MAIN_SEGS(sbi)),
+ GFP_KERNEL);
if (!sit_i->sentries)
return -ENOMEM;
return -ENOMEM;
#endif
- if (f2fs_discard_en(sbi)) {
- sit_i->sentries[start].discard_map
- = f2fs_kzalloc(sbi, SIT_VBLOCK_MAP_SIZE,
- GFP_KERNEL);
- if (!sit_i->sentries[start].discard_map)
- return -ENOMEM;
- }
+ sit_i->sentries[start].discard_map
+ = f2fs_kzalloc(sbi, SIT_VBLOCK_MAP_SIZE,
+ GFP_KERNEL);
+ if (!sit_i->sentries[start].discard_map)
+ return -ENOMEM;
}
sit_i->tmp_map = f2fs_kzalloc(sbi, SIT_VBLOCK_MAP_SIZE, GFP_KERNEL);
if (!sit_i->tmp_map)
return -ENOMEM;
- if (sbi->segs_per_sec > 1) {
- sit_i->sec_entries = f2fs_kvzalloc(sbi, MAIN_SECS(sbi) *
- sizeof(struct sec_entry), GFP_KERNEL);
+ if (__is_large_section(sbi)) {
+ sit_i->sec_entries =
+ f2fs_kvzalloc(sbi, array_size(sizeof(struct sec_entry),
+ MAIN_SECS(sbi)),
+ GFP_KERNEL);
if (!sit_i->sec_entries)
return -ENOMEM;
}
struct curseg_info *array;
int i;
- array = f2fs_kzalloc(sbi, sizeof(*array) * NR_CURSEG_TYPE, GFP_KERNEL);
+ array = f2fs_kzalloc(sbi, array_size(NR_CURSEG_TYPE, sizeof(*array)),
+ GFP_KERNEL);
if (!array)
return -ENOMEM;
unsigned int i, start, end;
unsigned int readed, start_blk = 0;
int err = 0;
+ block_t total_node_blocks = 0;
do {
- readed = ra_meta_pages(sbi, start_blk, BIO_MAX_PAGES,
+ readed = f2fs_ra_meta_pages(sbi, start_blk, BIO_MAX_PAGES,
META_SIT, true);
start = start_blk * sit_i->sents_per_block;
se = &sit_i->sentries[start];
page = get_current_sit_page(sbi, start);
+ if (IS_ERR(page))
+ return PTR_ERR(page);
sit_blk = (struct f2fs_sit_block *)page_address(page);
sit = sit_blk->entries[SIT_ENTRY_OFFSET(sit_i, start)];
f2fs_put_page(page, 1);
if (err)
return err;
seg_info_from_raw_sit(se, &sit);
+ if (IS_NODESEG(se->type))
+ total_node_blocks += se->valid_blocks;
/* build discard map only one time */
- if (f2fs_discard_en(sbi)) {
- if (is_set_ckpt_flags(sbi, CP_TRIMMED_FLAG)) {
- memset(se->discard_map, 0xff,
- SIT_VBLOCK_MAP_SIZE);
- } else {
- memcpy(se->discard_map,
- se->cur_valid_map,
- SIT_VBLOCK_MAP_SIZE);
- sbi->discard_blks +=
- sbi->blocks_per_seg -
- se->valid_blocks;
- }
+ if (is_set_ckpt_flags(sbi, CP_TRIMMED_FLAG)) {
+ memset(se->discard_map, 0xff,
+ SIT_VBLOCK_MAP_SIZE);
+ } else {
+ memcpy(se->discard_map,
+ se->cur_valid_map,
+ SIT_VBLOCK_MAP_SIZE);
+ sbi->discard_blks +=
+ sbi->blocks_per_seg -
+ se->valid_blocks;
}
- if (sbi->segs_per_sec > 1)
+ if (__is_large_section(sbi))
get_sec_entry(sbi, start)->valid_blocks +=
se->valid_blocks;
}
unsigned int old_valid_blocks;
start = le32_to_cpu(segno_in_journal(journal, i));
+ if (start >= MAIN_SEGS(sbi)) {
+ f2fs_err(sbi, "Wrong journal entry on segno %u",
+ start);
+ set_sbi_flag(sbi, SBI_NEED_FSCK);
+ err = -EFSCORRUPTED;
+ break;
+ }
+
se = &sit_i->sentries[start];
sit = sit_in_journal(journal, i);
old_valid_blocks = se->valid_blocks;
+ if (IS_NODESEG(se->type))
+ total_node_blocks -= old_valid_blocks;
err = check_block_count(sbi, start, &sit);
if (err)
break;
seg_info_from_raw_sit(se, &sit);
+ if (IS_NODESEG(se->type))
+ total_node_blocks += se->valid_blocks;
- if (f2fs_discard_en(sbi)) {
- if (is_set_ckpt_flags(sbi, CP_TRIMMED_FLAG)) {
- memset(se->discard_map, 0xff,
- SIT_VBLOCK_MAP_SIZE);
- } else {
- memcpy(se->discard_map, se->cur_valid_map,
- SIT_VBLOCK_MAP_SIZE);
- sbi->discard_blks += old_valid_blocks -
- se->valid_blocks;
- }
+ if (is_set_ckpt_flags(sbi, CP_TRIMMED_FLAG)) {
+ memset(se->discard_map, 0xff, SIT_VBLOCK_MAP_SIZE);
+ } else {
+ memcpy(se->discard_map, se->cur_valid_map,
+ SIT_VBLOCK_MAP_SIZE);
+ sbi->discard_blks += old_valid_blocks;
+ sbi->discard_blks -= se->valid_blocks;
}
- if (sbi->segs_per_sec > 1)
+ if (__is_large_section(sbi)) {
get_sec_entry(sbi, start)->valid_blocks +=
- se->valid_blocks - old_valid_blocks;
+ se->valid_blocks;
+ get_sec_entry(sbi, start)->valid_blocks -=
+ old_valid_blocks;
+ }
}
up_read(&curseg->journal_rwsem);
+
+ if (!err && total_node_blocks != valid_node_count(sbi)) {
+ f2fs_err(sbi, "SIT is corrupted node# %u vs %u",
+ total_node_blocks, valid_node_count(sbi));
+ set_sbi_flag(sbi, SBI_NEED_FSCK);
+ err = -EFSCORRUPTED;
+ }
+
return err;
}
return init_victim_secmap(sbi);
}
+static int sanity_check_curseg(struct f2fs_sb_info *sbi)
+{
+ int i;
+
+ /*
+ * In LFS/SSR curseg, .next_blkoff should point to an unused blkaddr;
+ * In LFS curseg, all blkaddr after .next_blkoff should be unused.
+ */
+ for (i = 0; i < NO_CHECK_TYPE; i++) {
+ struct curseg_info *curseg = CURSEG_I(sbi, i);
+ struct seg_entry *se = get_seg_entry(sbi, curseg->segno);
+ unsigned int blkofs = curseg->next_blkoff;
+
+ if (f2fs_test_bit(blkofs, se->cur_valid_map))
+ goto out;
+
+ if (curseg->alloc_type == SSR)
+ continue;
+
+ for (blkofs += 1; blkofs < sbi->blocks_per_seg; blkofs++) {
+ if (!f2fs_test_bit(blkofs, se->cur_valid_map))
+ continue;
+out:
+ f2fs_err(sbi,
+ "Current segment's next free block offset is "
+ "inconsistent with bitmap, logtype:%u, "
+ "segno:%u, type:%u, next_blkoff:%u, blkofs:%u",
+ i, curseg->segno, curseg->alloc_type,
+ curseg->next_blkoff, blkofs);
+ return -EFSCORRUPTED;
+ }
+ }
+ return 0;
+}
+
/*
* Update min, max modified time for cost-benefit GC algorithm
*/
down_write(&sit_i->sentry_lock);
- sit_i->min_mtime = LLONG_MAX;
+ sit_i->min_mtime = ULLONG_MAX;
for (segno = 0; segno < MAIN_SEGS(sbi); segno += sbi->segs_per_sec) {
unsigned int i;
if (sit_i->min_mtime > mtime)
sit_i->min_mtime = mtime;
}
- sit_i->max_mtime = get_mtime(sbi);
+ sit_i->max_mtime = get_mtime(sbi, false);
up_write(&sit_i->sentry_lock);
}
-int build_segment_manager(struct f2fs_sb_info *sbi)
+int f2fs_build_segment_manager(struct f2fs_sb_info *sbi)
{
struct f2fs_super_block *raw_super = F2FS_RAW_SUPER(sbi);
struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);
sm_info->ipu_policy = 1 << F2FS_IPU_FSYNC;
sm_info->min_ipu_util = DEF_MIN_IPU_UTIL;
sm_info->min_fsync_blocks = DEF_MIN_FSYNC_BLOCKS;
+ sm_info->min_seq_blocks = sbi->blocks_per_seg * sbi->segs_per_sec;
sm_info->min_hot_blocks = DEF_MIN_HOT_BLOCKS;
sm_info->min_ssr_sections = reserved_sections(sbi);
init_rwsem(&sm_info->curseg_lock);
if (!f2fs_readonly(sbi->sb)) {
- err = create_flush_cmd_control(sbi);
+ err = f2fs_create_flush_cmd_control(sbi);
if (err)
return err;
}
if (err)
return err;
+ err = sanity_check_curseg(sbi);
+ if (err)
+ return err;
+
init_min_max_mtime(sbi);
return 0;
}
destroy_victim_secmap(sbi);
SM_I(sbi)->dirty_info = NULL;
- kfree(dirty_i);
+ kvfree(dirty_i);
}
static void destroy_curseg(struct f2fs_sb_info *sbi)
return;
SM_I(sbi)->curseg_array = NULL;
for (i = 0; i < NR_CURSEG_TYPE; i++) {
- kfree(array[i].sum_blk);
- kfree(array[i].journal);
+ kvfree(array[i].sum_blk);
+ kvfree(array[i].journal);
}
- kfree(array);
+ kvfree(array);
}
static void destroy_free_segmap(struct f2fs_sb_info *sbi)
SM_I(sbi)->free_info = NULL;
kvfree(free_i->free_segmap);
kvfree(free_i->free_secmap);
- kfree(free_i);
+ kvfree(free_i);
}
static void destroy_sit_info(struct f2fs_sb_info *sbi)
if (sit_i->sentries) {
for (start = 0; start < MAIN_SEGS(sbi); start++) {
- kfree(sit_i->sentries[start].cur_valid_map);
+ kvfree(sit_i->sentries[start].cur_valid_map);
#ifdef CONFIG_F2FS_CHECK_FS
- kfree(sit_i->sentries[start].cur_valid_map_mir);
+ kvfree(sit_i->sentries[start].cur_valid_map_mir);
#endif
- kfree(sit_i->sentries[start].ckpt_valid_map);
- kfree(sit_i->sentries[start].discard_map);
+ kvfree(sit_i->sentries[start].ckpt_valid_map);
+ kvfree(sit_i->sentries[start].discard_map);
}
}
- kfree(sit_i->tmp_map);
+ kvfree(sit_i->tmp_map);
kvfree(sit_i->sentries);
kvfree(sit_i->sec_entries);
kvfree(sit_i->dirty_sentries_bitmap);
SM_I(sbi)->sit_info = NULL;
- kfree(sit_i->sit_bitmap);
+ kvfree(sit_i->sit_bitmap);
#ifdef CONFIG_F2FS_CHECK_FS
- kfree(sit_i->sit_bitmap_mir);
+ kvfree(sit_i->sit_bitmap_mir);
#endif
- kfree(sit_i);
+ kvfree(sit_i);
}
-void destroy_segment_manager(struct f2fs_sb_info *sbi)
+void f2fs_destroy_segment_manager(struct f2fs_sb_info *sbi)
{
struct f2fs_sm_info *sm_info = SM_I(sbi);
if (!sm_info)
return;
- destroy_flush_cmd_control(sbi, true);
+ f2fs_destroy_flush_cmd_control(sbi, true);
destroy_discard_cmd_control(sbi);
destroy_dirty_segmap(sbi);
destroy_curseg(sbi);
destroy_free_segmap(sbi);
destroy_sit_info(sbi);
sbi->sm_info = NULL;
- kfree(sm_info);
+ kvfree(sm_info);
}
-int __init create_segment_manager_caches(void)
+int __init f2fs_create_segment_manager_caches(void)
{
discard_entry_slab = f2fs_kmem_cache_create("discard_entry",
sizeof(struct discard_entry));
return -ENOMEM;
}
-void destroy_segment_manager_caches(void)
+void f2fs_destroy_segment_manager_caches(void)
{
kmem_cache_destroy(sit_entry_set_slab);
kmem_cache_destroy(discard_cmd_slab);
OSDN Git Service
