/*
* This must be called after early kernel init, since then the rootdev
* is available.
*/
static void check_pinning_enforcement(struct super_block *mnt_sb)
{
bool ro = false;
/*
* If load pinning is not enforced via a read-only block
* device, allow sysctl to change modes for testing.
*/
if (mnt_sb->s_bdev) {
char bdev[BDEVNAME_SIZE];
ro = bdev_read_only(mnt_sb->s_bdev);
bdevname(mnt_sb->s_bdev, bdev);
pr_info("%s (%u:%u): %s\n", bdev,
MAJOR(mnt_sb->s_bdev->bd_dev),
MINOR(mnt_sb->s_bdev->bd_dev),
ro ? "read-only" : "writable");
} else
pr_info("mnt_sb lacks block device, treating as: writable\n");
if (!ro) {
if (!register_sysctl_paths(loadpin_sysctl_path,
loadpin_sysctl_table))
pr_notice("sysctl registration failed!\n");
else
pr_info("enforcement can be disabled.\n");
} else
pr_info("load pinning engaged.\n");
}
co_rc_t co_os_file_block_open(struct co_monitor *linuxvm, co_monitor_file_block_dev_t *fdev)
{
struct file *filp;
struct inode *inode = NULL;
co_rc_t rc = CO_RC(OK);
co_debug("opening %s\n", fdev->pathname);
filp = filp_open(fdev->pathname, O_RDWR | O_LARGEFILE, 0);
if (IS_ERR(filp))
return CO_RC(ERROR);
if (filp->f_dentry)
inode = filp->f_dentry->d_inode;
if (inode && S_ISBLK(inode->i_mode)) {
if (bdev_read_only(inode->i_bdev)) {
/* TODO... */
}
} else if (!inode || !S_ISREG(inode->i_mode)) {
co_debug("colinux: invalid file type: %s\n", fdev->pathname);
rc = CO_RC(ERROR);
goto out;
}
fdev->sysdep = (struct co_os_file_block_sysdep *)(filp);
return rc;
out:
filp_close(filp, current->files);
return rc;
}
/**
* blkdev_reset_zones - Reset zones write pointer
* @bdev: Target block device
* @sector: Start sector of the first zone to reset
* @nr_sectors: Number of sectors, at least the length of one zone
* @gfp_mask: Memory allocation flags (for bio_alloc)
*
* Description:
* Reset the write pointer of the zones contained in the range
* @sector..@sector+@nr_sectors. Specifying the entire disk sector range
* is valid, but the specified range should not contain conventional zones.
*/
int blkdev_reset_zones(struct block_device *bdev,
sector_t sector, sector_t nr_sectors,
gfp_t gfp_mask)
{
struct request_queue *q = bdev_get_queue(bdev);
sector_t zone_sectors;
sector_t end_sector = sector + nr_sectors;
struct bio *bio = NULL;
struct blk_plug plug;
int ret;
if (!blk_queue_is_zoned(q))
return -EOPNOTSUPP;
if (bdev_read_only(bdev))
return -EPERM;
if (!nr_sectors || end_sector > bdev->bd_part->nr_sects)
/* Out of range */
return -EINVAL;
/* Check alignment (handle eventual smaller last zone) */
zone_sectors = blk_queue_zone_sectors(q);
if (sector & (zone_sectors - 1))
return -EINVAL;
if ((nr_sectors & (zone_sectors - 1)) &&
end_sector != bdev->bd_part->nr_sects)
return -EINVAL;
blk_start_plug(&plug);
while (sector < end_sector) {
bio = blk_next_bio(bio, 0, gfp_mask);
bio->bi_iter.bi_sector = sector;
bio_set_dev(bio, bdev);
bio_set_op_attrs(bio, REQ_OP_ZONE_RESET, 0);
sector += zone_sectors;
/* This may take a while, so be nice to others */
cond_resched();
}
ret = submit_bio_wait(bio);
bio_put(bio);
blk_finish_plug(&plug);
return ret;
}
/* Check if the root device is read-only (e.g. dm-verity is enabled).
* This must be called after early kernel init, since then the rootdev
* is available.
*/
static bool rootdev_readonly(void)
{
bool rc;
struct block_device *bdev;
const fmode_t mode = FMODE_WRITE;
bdev = blkdev_get_by_dev(ROOT_DEV, mode, NULL);
if (IS_ERR(bdev)) {
/* In this weird case, assume it is read-only. */
pr_info("dev(%u,%u): FMODE_WRITE disallowed?!\n",
MAJOR(ROOT_DEV), MINOR(ROOT_DEV));
return true;
}
rc = bdev_read_only(bdev);
blkdev_put(bdev, mode);
pr_info("dev(%u,%u): %s\n", MAJOR(ROOT_DEV), MINOR(ROOT_DEV),
rc ? "read-only" : "writable");
return rc;
}
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 buffer_head *raw_super_buf;
struct inode *root;
long err;
bool retry = true, need_fsck = false;
char *options = NULL;
int recovery, i;
try_onemore:
err = -EINVAL;
raw_super = NULL;
raw_super_buf = NULL;
recovery = 0;
/* allocate memory for f2fs-specific super block info */
sbi = kzalloc(sizeof(struct f2fs_sb_info), GFP_KERNEL);
if (!sbi)
return -ENOMEM;
/* 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, &raw_super_buf, &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;
sb->s_maxbytes = max_file_size(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_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->raw_super_buf = raw_super_buf;
mutex_init(&sbi->gc_mutex);
mutex_init(&sbi->writepages);
mutex_init(&sbi->cp_mutex);
init_rwsem(&sbi->node_write);
clear_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;
}
/* sanity checking of checkpoint */
err = -EINVAL;
if (sanity_check_ckpt(sbi)) {
f2fs_msg(sb, KERN_ERR, "Invalid F2FS checkpoint");
goto free_cp;
}
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;
INIT_LIST_HEAD(&sbi->dir_inode_list);
spin_lock_init(&sbi->dir_inode_lock);
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;
}
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;
}
/* if there are nt orphan nodes free them */
recover_orphan_inodes(sbi);
/* 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);
if (test_opt(sbi, DISCARD)) {
struct request_queue *q = bdev_get_queue(sb->s_bdev);
if (!blk_queue_discard(q))
f2fs_msg(sb, KERN_WARNING,
"mounting with \"discard\" option, but "
"the device does not support discard");
clear_opt(sbi, DISCARD);
}
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;
}
}
/*
* 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)) {
f2fs_msg(sb, KERN_INFO, "Recover invalid superblock");
f2fs_commit_super(sbi);
}
return 0;
free_kobj:
kobject_del(&sbi->s_kobj);
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:
iput(sbi->node_inode);
free_nm:
destroy_node_manager(sbi);
free_sm:
destroy_segment_manager(sbi);
free_cp:
kfree(sbi->ckpt);
free_meta_inode:
make_bad_inode(sbi->meta_inode);
iput(sbi->meta_inode);
free_options:
kfree(options);
free_sb_buf:
brelse(raw_super_buf);
free_sbi:
kfree(sbi);
/* give only one another chance */
if (retry) {
retry = false;
shrink_dcache_sb(sb);
goto try_onemore;
}
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;
}
int
xfs_readonly_buftarg(
xfs_buftarg_t *btp)
{
return bdev_read_only(btp->pbr_bdev);
}
