static int recover_data(struct f2fs_sb_info *sbi, struct list_head *inode_list,
struct list_head *tmp_inode_list, struct list_head *dir_list)
{
struct curseg_info *curseg;
struct page *page = NULL;
int err = 0;
block_t blkaddr;
/* get node pages in the current segment */
curseg = CURSEG_I(sbi, CURSEG_WARM_NODE);
blkaddr = NEXT_FREE_BLKADDR(sbi, curseg);
while (1) {
struct fsync_inode_entry *entry;
if (!f2fs_is_valid_blkaddr(sbi, blkaddr, META_POR))
break;
f2fs_ra_meta_pages_cond(sbi, blkaddr);
page = f2fs_get_tmp_page(sbi, blkaddr);
if (IS_ERR(page)) {
err = PTR_ERR(page);
break;
}
if (!is_recoverable_dnode(page)) {
f2fs_put_page(page, 1);
break;
}
entry = get_fsync_inode(inode_list, ino_of_node(page));
if (!entry)
goto next;
/*
* inode(x) | CP | inode(x) | dnode(F)
* In this case, we can lose the latest inode(x).
* So, call recover_inode for the inode update.
*/
if (IS_INODE(page)) {
err = recover_inode(entry->inode, page);
if (err) {
f2fs_put_page(page, 1);
break;
}
}
if (entry->last_dentry == blkaddr) {
err = recover_dentry(entry->inode, page, dir_list);
if (err) {
f2fs_put_page(page, 1);
break;
}
}
err = do_recover_data(sbi, entry->inode, page);
if (err) {
f2fs_put_page(page, 1);
break;
}
if (entry->blkaddr == blkaddr)
list_move_tail(&entry->list, tmp_inode_list);
next:
/* check next segment */
blkaddr = next_blkaddr_of_node(page);
f2fs_put_page(page, 1);
}
if (!err)
f2fs_allocate_new_segments(sbi);
return err;
}
static int check_index_in_prev_nodes(struct f2fs_sb_info *sbi,
block_t blkaddr, struct dnode_of_data *dn)
{
struct seg_entry *sentry;
unsigned int segno = GET_SEGNO(sbi, blkaddr);
unsigned short blkoff = GET_BLKOFF_FROM_SEG0(sbi, blkaddr);
struct f2fs_summary_block *sum_node;
struct f2fs_summary sum;
struct page *sum_page, *node_page;
struct dnode_of_data tdn = *dn;
nid_t ino, nid;
struct inode *inode;
unsigned int offset;
block_t bidx;
int i;
sentry = get_seg_entry(sbi, segno);
if (!f2fs_test_bit(blkoff, sentry->cur_valid_map))
return 0;
/* Get the previous summary */
for (i = CURSEG_HOT_DATA; i <= CURSEG_COLD_DATA; i++) {
struct curseg_info *curseg = CURSEG_I(sbi, i);
if (curseg->segno == segno) {
sum = curseg->sum_blk->entries[blkoff];
goto got_it;
}
}
sum_page = f2fs_get_sum_page(sbi, segno);
if (IS_ERR(sum_page))
return PTR_ERR(sum_page);
sum_node = (struct f2fs_summary_block *)page_address(sum_page);
sum = sum_node->entries[blkoff];
f2fs_put_page(sum_page, 1);
got_it:
/* Use the locked dnode page and inode */
nid = le32_to_cpu(sum.nid);
if (dn->inode->i_ino == nid) {
tdn.nid = nid;
if (!dn->inode_page_locked)
lock_page(dn->inode_page);
tdn.node_page = dn->inode_page;
tdn.ofs_in_node = le16_to_cpu(sum.ofs_in_node);
goto truncate_out;
} else if (dn->nid == nid) {
tdn.ofs_in_node = le16_to_cpu(sum.ofs_in_node);
goto truncate_out;
}
/* Get the node page */
node_page = f2fs_get_node_page(sbi, nid);
if (IS_ERR(node_page))
return PTR_ERR(node_page);
offset = ofs_of_node(node_page);
ino = ino_of_node(node_page);
f2fs_put_page(node_page, 1);
if (ino != dn->inode->i_ino) {
int ret;
/* Deallocate previous index in the node page */
inode = f2fs_iget_retry(sbi->sb, ino);
if (IS_ERR(inode))
return PTR_ERR(inode);
ret = dquot_initialize(inode);
if (ret) {
iput(inode);
return ret;
}
} else {
inode = dn->inode;
}
bidx = f2fs_start_bidx_of_node(offset, inode) +
le16_to_cpu(sum.ofs_in_node);
/*
* if inode page is locked, unlock temporarily, but its reference
* count keeps alive.
*/
if (ino == dn->inode->i_ino && dn->inode_page_locked)
unlock_page(dn->inode_page);
set_new_dnode(&tdn, inode, NULL, NULL, 0);
if (f2fs_get_dnode_of_data(&tdn, bidx, LOOKUP_NODE))
goto out;
if (tdn.data_blkaddr == blkaddr)
f2fs_truncate_data_blocks_range(&tdn, 1);
f2fs_put_dnode(&tdn);
out:
if (ino != dn->inode->i_ino)
iput(inode);
else if (dn->inode_page_locked)
lock_page(dn->inode_page);
return 0;
truncate_out:
if (datablock_addr(tdn.inode, tdn.node_page,
tdn.ofs_in_node) == blkaddr)
f2fs_truncate_data_blocks_range(&tdn, 1);
if (dn->inode->i_ino == nid && !dn->inode_page_locked)
unlock_page(dn->inode_page);
return 0;
}
static int find_fsync_dnodes(struct f2fs_sb_info *sbi, struct list_head *head,
bool check_only)
{
struct curseg_info *curseg;
struct page *page = NULL;
block_t blkaddr;
unsigned int loop_cnt = 0;
unsigned int free_blocks = MAIN_SEGS(sbi) * sbi->blocks_per_seg -
valid_user_blocks(sbi);
int err = 0;
/* get node pages in the current segment */
curseg = CURSEG_I(sbi, CURSEG_WARM_NODE);
blkaddr = NEXT_FREE_BLKADDR(sbi, curseg);
while (1) {
struct fsync_inode_entry *entry;
if (!f2fs_is_valid_blkaddr(sbi, blkaddr, META_POR))
return 0;
page = f2fs_get_tmp_page(sbi, blkaddr);
if (IS_ERR(page)) {
err = PTR_ERR(page);
break;
}
if (!is_recoverable_dnode(page)) {
f2fs_put_page(page, 1);
break;
}
if (!is_fsync_dnode(page))
goto next;
entry = get_fsync_inode(head, ino_of_node(page));
if (!entry) {
bool quota_inode = false;
if (!check_only &&
IS_INODE(page) && is_dent_dnode(page)) {
err = f2fs_recover_inode_page(sbi, page);
if (err) {
f2fs_put_page(page, 1);
break;
}
quota_inode = true;
}
/*
* CP | dnode(F) | inode(DF)
* For this case, we should not give up now.
*/
entry = add_fsync_inode(sbi, head, ino_of_node(page),
quota_inode);
if (IS_ERR(entry)) {
err = PTR_ERR(entry);
if (err == -ENOENT) {
err = 0;
goto next;
}
f2fs_put_page(page, 1);
break;
}
}
entry->blkaddr = blkaddr;
if (IS_INODE(page) && is_dent_dnode(page))
entry->last_dentry = blkaddr;
next:
/* sanity check in order to detect looped node chain */
if (++loop_cnt >= free_blocks ||
blkaddr == next_blkaddr_of_node(page)) {
f2fs_msg(sbi->sb, KERN_NOTICE,
"%s: detect looped node chain, "
"blkaddr:%u, next:%u",
__func__, blkaddr, next_blkaddr_of_node(page));
f2fs_put_page(page, 1);
err = -EINVAL;
break;
}
/* check next segment */
blkaddr = next_blkaddr_of_node(page);
f2fs_put_page(page, 1);
f2fs_ra_meta_pages_cond(sbi, blkaddr);
}
return err;
}
static int find_fsync_dnodes(struct f2fs_sb_info *sbi, struct list_head *head)
{
unsigned long long cp_ver = cur_cp_version(F2FS_CKPT(sbi));
struct curseg_info *curseg;
struct page *page = NULL;
block_t blkaddr;
int err = 0;
/* get node pages in the current segment */
curseg = CURSEG_I(sbi, CURSEG_WARM_NODE);
blkaddr = NEXT_FREE_BLKADDR(sbi, curseg);
ra_meta_pages(sbi, blkaddr, 1, META_POR, true);
while (1) {
struct fsync_inode_entry *entry;
if (!is_valid_blkaddr(sbi, blkaddr, META_POR))
return 0;
page = get_tmp_page(sbi, blkaddr);
if (cp_ver != cpver_of_node(page))
break;
if (!is_fsync_dnode(page))
goto next;
entry = get_fsync_inode(head, ino_of_node(page));
if (entry) {
if (!is_same_inode(entry->inode, page))
goto next;
} else {
if (IS_INODE(page) && is_dent_dnode(page)) {
err = recover_inode_page(sbi, page);
if (err)
break;
}
/* add this fsync inode to the list */
entry = kmem_cache_alloc(fsync_entry_slab, GFP_F2FS_ZERO);
if (!entry) {
err = -ENOMEM;
break;
}
/*
* CP | dnode(F) | inode(DF)
* For this case, we should not give up now.
*/
entry->inode = f2fs_iget(sbi->sb, ino_of_node(page));
if (IS_ERR(entry->inode)) {
err = PTR_ERR(entry->inode);
kmem_cache_free(fsync_entry_slab, entry);
if (err == -ENOENT) {
err = 0;
goto next;
}
break;
}
list_add_tail(&entry->list, head);
}
entry->blkaddr = blkaddr;
if (IS_INODE(page)) {
entry->last_inode = blkaddr;
if (is_dent_dnode(page))
entry->last_dentry = blkaddr;
}
next:
/* check next segment */
blkaddr = next_blkaddr_of_node(page);
f2fs_put_page(page, 1);
ra_meta_pages_cond(sbi, blkaddr);
}
f2fs_put_page(page, 1);
return err;
}
static int find_fsync_dnodes(struct f2fs_sb_info *sbi, struct list_head *head)
{
unsigned long long cp_ver = cur_cp_version(F2FS_CKPT(sbi));
struct curseg_info *curseg;
struct page *page;
block_t blkaddr;
int err = 0;
/* get node pages in the current segment */
curseg = CURSEG_I(sbi, CURSEG_WARM_NODE);
blkaddr = NEXT_FREE_BLKADDR(sbi, curseg);
/* read node page */
page = alloc_page(GFP_F2FS_ZERO);
if (!page)
return -ENOMEM;
lock_page(page);
while (1) {
struct fsync_inode_entry *entry;
err = f2fs_submit_page_bio(sbi, page, blkaddr, READ_SYNC);
if (err)
return err;
lock_page(page);
if (cp_ver != cpver_of_node(page))
break;
if (!is_fsync_dnode(page))
goto next;
entry = get_fsync_inode(head, ino_of_node(page));
if (entry) {
if (IS_INODE(page) && is_dent_dnode(page))
set_inode_flag(F2FS_I(entry->inode),
FI_INC_LINK);
} else {
if (IS_INODE(page) && is_dent_dnode(page)) {
err = recover_inode_page(sbi, page);
if (err) {
f2fs_msg(sbi->sb, KERN_INFO,
"%s: recover_inode_page failed: %d",
__func__, err);
break;
}
}
/* add this fsync inode to the list */
entry = kmem_cache_alloc(fsync_entry_slab, GFP_NOFS);
if (!entry) {
err = -ENOMEM;
break;
}
entry->inode = f2fs_iget(sbi->sb, ino_of_node(page));
if (IS_ERR(entry->inode)) {
err = PTR_ERR(entry->inode);
f2fs_msg(sbi->sb, KERN_INFO,
"%s: f2fs_iget failed: %d",
__func__, err);
kmem_cache_free(fsync_entry_slab, entry);
break;
}
list_add_tail(&entry->list, head);
}
entry->blkaddr = blkaddr;
err = recover_inode(entry->inode, page);
if (err && err != -ENOENT) {
f2fs_msg(sbi->sb, KERN_INFO,
"%s: recover_inode failed: %d",
__func__, err);
break;
}
next:
/* check next segment */
blkaddr = next_blkaddr_of_node(page);
}
unlock_page(page);
__free_pages(page, 0);
return err;
}
static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
{
struct f2fs_sb_info *sbi;
struct f2fs_super_block *raw_super;
struct inode *root;
long err;
bool retry = true, need_fsck = false;
char *options = NULL;
int recovery, i, valid_super_block;
struct curseg_info *seg_i;
try_onemore:
err = -EINVAL;
raw_super = NULL;
valid_super_block = -1;
recovery = 0;
/* allocate memory for f2fs-specific super block info */
sbi = kzalloc(sizeof(struct f2fs_sb_info), GFP_KERNEL);
if (!sbi)
return -ENOMEM;
/* Load the checksum driver */
sbi->s_chksum_driver = crypto_alloc_shash("crc32", 0, 0);
if (IS_ERR(sbi->s_chksum_driver)) {
f2fs_msg(sb, KERN_ERR, "Cannot load crc32 driver.");
err = PTR_ERR(sbi->s_chksum_driver);
sbi->s_chksum_driver = NULL;
goto free_sbi;
}
/* set a block size */
if (unlikely(!sb_set_blocksize(sb, F2FS_BLKSIZE))) {
f2fs_msg(sb, KERN_ERR, "unable to set blocksize");
goto free_sbi;
}
err = read_raw_super_block(sb, &raw_super, &valid_super_block,
&recovery);
if (err)
goto free_sbi;
sb->s_fs_info = sbi;
default_options(sbi);
/* parse mount options */
options = kstrdup((const char *)data, GFP_KERNEL);
if (data && !options) {
err = -ENOMEM;
goto free_sb_buf;
}
err = parse_options(sb, options);
if (err)
goto free_options;
sbi->max_file_blocks = max_file_blocks();
sb->s_maxbytes = sbi->max_file_blocks <<
le32_to_cpu(raw_super->log_blocksize);
sb->s_max_links = F2FS_LINK_MAX;
get_random_bytes(&sbi->s_next_generation, sizeof(u32));
sb->s_op = &f2fs_sops;
sb->s_cop = &f2fs_cryptops;
sb->s_xattr = f2fs_xattr_handlers;
sb->s_export_op = &f2fs_export_ops;
sb->s_magic = F2FS_SUPER_MAGIC;
sb->s_time_gran = 1;
sb->s_flags = (sb->s_flags & ~MS_POSIXACL) |
(test_opt(sbi, POSIX_ACL) ? MS_POSIXACL : 0);
memcpy(sb->s_uuid, raw_super->uuid, sizeof(raw_super->uuid));
/* init f2fs-specific super block info */
sbi->sb = sb;
sbi->raw_super = raw_super;
sbi->valid_super_block = valid_super_block;
mutex_init(&sbi->gc_mutex);
mutex_init(&sbi->writepages);
mutex_init(&sbi->cp_mutex);
init_rwsem(&sbi->node_write);
/* disallow all the data/node/meta page writes */
set_sbi_flag(sbi, SBI_POR_DOING);
spin_lock_init(&sbi->stat_lock);
init_rwsem(&sbi->read_io.io_rwsem);
sbi->read_io.sbi = sbi;
sbi->read_io.bio = NULL;
for (i = 0; i < NR_PAGE_TYPE; i++) {
init_rwsem(&sbi->write_io[i].io_rwsem);
sbi->write_io[i].sbi = sbi;
sbi->write_io[i].bio = NULL;
}
init_rwsem(&sbi->cp_rwsem);
init_waitqueue_head(&sbi->cp_wait);
init_sb_info(sbi);
/* get an inode for meta space */
sbi->meta_inode = f2fs_iget(sb, F2FS_META_INO(sbi));
if (IS_ERR(sbi->meta_inode)) {
f2fs_msg(sb, KERN_ERR, "Failed to read F2FS meta data inode");
err = PTR_ERR(sbi->meta_inode);
goto free_options;
}
err = get_valid_checkpoint(sbi);
if (err) {
f2fs_msg(sb, KERN_ERR, "Failed to get valid F2FS checkpoint");
goto free_meta_inode;
}
sbi->total_valid_node_count =
le32_to_cpu(sbi->ckpt->valid_node_count);
sbi->total_valid_inode_count =
le32_to_cpu(sbi->ckpt->valid_inode_count);
sbi->user_block_count = le64_to_cpu(sbi->ckpt->user_block_count);
sbi->total_valid_block_count =
le64_to_cpu(sbi->ckpt->valid_block_count);
sbi->last_valid_block_count = sbi->total_valid_block_count;
sbi->alloc_valid_block_count = 0;
for (i = 0; i < NR_INODE_TYPE; i++) {
INIT_LIST_HEAD(&sbi->inode_list[i]);
spin_lock_init(&sbi->inode_lock[i]);
}
init_extent_cache_info(sbi);
init_ino_entry_info(sbi);
/* setup f2fs internal modules */
err = build_segment_manager(sbi);
if (err) {
f2fs_msg(sb, KERN_ERR,
"Failed to initialize F2FS segment manager");
goto free_sm;
}
err = build_node_manager(sbi);
if (err) {
f2fs_msg(sb, KERN_ERR,
"Failed to initialize F2FS node manager");
goto free_nm;
}
/* For write statistics */
if (sb->s_bdev->bd_part)
sbi->sectors_written_start =
(u64)part_stat_read(sb->s_bdev->bd_part, sectors[1]);
/* Read accumulated write IO statistics if exists */
seg_i = CURSEG_I(sbi, CURSEG_HOT_NODE);
if (__exist_node_summaries(sbi))
sbi->kbytes_written =
le64_to_cpu(seg_i->sum_blk->journal.info.kbytes_written);
build_gc_manager(sbi);
/* get an inode for node space */
sbi->node_inode = f2fs_iget(sb, F2FS_NODE_INO(sbi));
if (IS_ERR(sbi->node_inode)) {
f2fs_msg(sb, KERN_ERR, "Failed to read node inode");
err = PTR_ERR(sbi->node_inode);
goto free_nm;
}
f2fs_join_shrinker(sbi);
/* if there are nt orphan nodes free them */
err = recover_orphan_inodes(sbi);
if (err)
goto free_node_inode;
/* read root inode and dentry */
root = f2fs_iget(sb, F2FS_ROOT_INO(sbi));
if (IS_ERR(root)) {
f2fs_msg(sb, KERN_ERR, "Failed to read root inode");
err = PTR_ERR(root);
goto free_node_inode;
}
if (!S_ISDIR(root->i_mode) || !root->i_blocks || !root->i_size) {
iput(root);
err = -EINVAL;
goto free_node_inode;
}
sb->s_root = d_make_root(root); /* allocate root dentry */
if (!sb->s_root) {
err = -ENOMEM;
goto free_root_inode;
}
err = f2fs_build_stats(sbi);
if (err)
goto free_root_inode;
if (f2fs_proc_root)
sbi->s_proc = proc_mkdir(sb->s_id, f2fs_proc_root);
if (sbi->s_proc)
proc_create_data("segment_info", S_IRUGO, sbi->s_proc,
&f2fs_seq_segment_info_fops, sb);
sbi->s_kobj.kset = f2fs_kset;
init_completion(&sbi->s_kobj_unregister);
err = kobject_init_and_add(&sbi->s_kobj, &f2fs_ktype, NULL,
"%s", sb->s_id);
if (err)
goto free_proc;
/* recover fsynced data */
if (!test_opt(sbi, DISABLE_ROLL_FORWARD)) {
/*
* mount should be failed, when device has readonly mode, and
* previous checkpoint was not done by clean system shutdown.
*/
if (bdev_read_only(sb->s_bdev) &&
!is_set_ckpt_flags(sbi->ckpt, CP_UMOUNT_FLAG)) {
err = -EROFS;
goto free_kobj;
}
if (need_fsck)
set_sbi_flag(sbi, SBI_NEED_FSCK);
err = recover_fsync_data(sbi);
if (err) {
need_fsck = true;
f2fs_msg(sb, KERN_ERR,
"Cannot recover all fsync data errno=%ld", err);
goto free_kobj;
}
}
/* recover_fsync_data() cleared this already */
clear_sbi_flag(sbi, SBI_POR_DOING);
/*
* If filesystem is not mounted as read-only then
* do start the gc_thread.
*/
if (test_opt(sbi, BG_GC) && !f2fs_readonly(sb)) {
/* After POR, we can run background GC thread.*/
err = start_gc_thread(sbi);
if (err)
goto free_kobj;
}
kfree(options);
/* recover broken superblock */
if (recovery && !f2fs_readonly(sb) && !bdev_read_only(sb->s_bdev)) {
err = f2fs_commit_super(sbi, true);
f2fs_msg(sb, KERN_INFO,
"Try to recover %dth superblock, ret: %ld",
sbi->valid_super_block ? 1 : 2, err);
}
f2fs_update_time(sbi, CP_TIME);
f2fs_update_time(sbi, REQ_TIME);
return 0;
free_kobj:
kobject_del(&sbi->s_kobj);
kobject_put(&sbi->s_kobj);
wait_for_completion(&sbi->s_kobj_unregister);
free_proc:
if (sbi->s_proc) {
remove_proc_entry("segment_info", sbi->s_proc);
remove_proc_entry(sb->s_id, f2fs_proc_root);
}
f2fs_destroy_stats(sbi);
free_root_inode:
dput(sb->s_root);
sb->s_root = NULL;
free_node_inode:
mutex_lock(&sbi->umount_mutex);
f2fs_leave_shrinker(sbi);
iput(sbi->node_inode);
mutex_unlock(&sbi->umount_mutex);
free_nm:
destroy_node_manager(sbi);
free_sm:
destroy_segment_manager(sbi);
kfree(sbi->ckpt);
free_meta_inode:
make_bad_inode(sbi->meta_inode);
iput(sbi->meta_inode);
free_options:
kfree(options);
free_sb_buf:
kfree(raw_super);
free_sbi:
if (sbi->s_chksum_driver)
crypto_free_shash(sbi->s_chksum_driver);
kfree(sbi);
/* give only one another chance */
if (retry) {
retry = false;
shrink_dcache_sb(sb);
goto try_onemore;
}
return err;
}
