/**
* create_default_filesystem - format empty UBI volume.
* @c: UBIFS file-system description object
*
* This function creates default empty file-system. Returns zero in case of
* success and a negative error code in case of failure.
*/
static int create_default_filesystem(struct ubifs_info *c)
{
struct ubifs_sb_node *sup;
struct ubifs_mst_node *mst;
struct ubifs_idx_node *idx;
struct ubifs_branch *br;
struct ubifs_ino_node *ino;
struct ubifs_cs_node *cs;
union ubifs_key key;
int err, tmp, jnl_lebs, log_lebs, max_buds, main_lebs, main_first;
int lpt_lebs, lpt_first, orph_lebs, big_lpt, ino_waste, sup_flags = 0;
int min_leb_cnt = UBIFS_MIN_LEB_CNT;
long long tmp64, main_bytes;
__le64 tmp_le64;
/* Some functions called from here depend on the @c->key_len filed */
c->key_len = UBIFS_SK_LEN;
/*
* First of all, we have to calculate default file-system geometry -
* log size, journal size, etc.
*/
if (c->leb_cnt < 0x7FFFFFFF / DEFAULT_JNL_PERCENT)
/* We can first multiply then divide and have no overflow */
jnl_lebs = c->leb_cnt * DEFAULT_JNL_PERCENT / 100;
else
jnl_lebs = (c->leb_cnt / 100) * DEFAULT_JNL_PERCENT;
if (jnl_lebs < UBIFS_MIN_JNL_LEBS)
jnl_lebs = UBIFS_MIN_JNL_LEBS;
if (jnl_lebs * c->leb_size > DEFAULT_MAX_JNL)
jnl_lebs = DEFAULT_MAX_JNL / c->leb_size;
/*
* The log should be large enough to fit reference nodes for all bud
* LEBs. Because buds do not have to start from the beginning of LEBs
* (half of the LEB may contain committed data), the log should
* generally be larger, make it twice as large.
*/
tmp = 2 * (c->ref_node_alsz * jnl_lebs) + c->leb_size - 1;
log_lebs = tmp / c->leb_size;
/* Plus one LEB reserved for commit */
log_lebs += 1;
if (c->leb_cnt - min_leb_cnt > 8) {
/* And some extra space to allow writes while committing */
log_lebs += 1;
min_leb_cnt += 1;
}
max_buds = jnl_lebs - log_lebs;
if (max_buds < UBIFS_MIN_BUD_LEBS)
max_buds = UBIFS_MIN_BUD_LEBS;
/*
* Orphan nodes are stored in a separate area. One node can store a lot
* of orphan inode numbers, but when new orphan comes we just add a new
* orphan node. At some point the nodes are consolidated into one
* orphan node.
*/
orph_lebs = UBIFS_MIN_ORPH_LEBS;
#ifdef CONFIG_UBIFS_FS_DEBUG
if (c->leb_cnt - min_leb_cnt > 1)
/*
* For debugging purposes it is better to have at least 2
* orphan LEBs, because the orphan subsystem would need to do
* consolidations and would be stressed more.
*/
orph_lebs += 1;
#endif
main_lebs = c->leb_cnt - UBIFS_SB_LEBS - UBIFS_MST_LEBS - log_lebs;
main_lebs -= orph_lebs;
lpt_first = UBIFS_LOG_LNUM + log_lebs;
c->lsave_cnt = DEFAULT_LSAVE_CNT;
c->max_leb_cnt = c->leb_cnt;
err = ubifs_create_dflt_lpt(c, &main_lebs, lpt_first, &lpt_lebs,
&big_lpt);
if (err)
return err;
dbg_gen("LEB Properties Tree created (LEBs %d-%d)", lpt_first,
lpt_first + lpt_lebs - 1);
main_first = c->leb_cnt - main_lebs;
/* Create default superblock */
tmp = ALIGN(UBIFS_SB_NODE_SZ, c->min_io_size);
sup = kzalloc(tmp, GFP_KERNEL);
if (!sup)
return -ENOMEM;
tmp64 = (long long)max_buds * c->leb_size;
if (big_lpt)
sup_flags |= UBIFS_FLG_BIGLPT;
sup->ch.node_type = UBIFS_SB_NODE;
sup->key_hash = UBIFS_KEY_HASH_R5;
sup->flags = cpu_to_le32(sup_flags);
sup->min_io_size = cpu_to_le32(c->min_io_size);
sup->leb_size = cpu_to_le32(c->leb_size);
sup->leb_cnt = cpu_to_le32(c->leb_cnt);
sup->max_leb_cnt = cpu_to_le32(c->max_leb_cnt);
sup->max_bud_bytes = cpu_to_le64(tmp64);
sup->log_lebs = cpu_to_le32(log_lebs);
sup->lpt_lebs = cpu_to_le32(lpt_lebs);
sup->orph_lebs = cpu_to_le32(orph_lebs);
sup->jhead_cnt = cpu_to_le32(DEFAULT_JHEADS_CNT);
sup->fanout = cpu_to_le32(DEFAULT_FANOUT);
sup->lsave_cnt = cpu_to_le32(c->lsave_cnt);
sup->fmt_version = cpu_to_le32(UBIFS_FORMAT_VERSION);
sup->time_gran = cpu_to_le32(DEFAULT_TIME_GRAN);
if (c->mount_opts.override_compr)
sup->default_compr = cpu_to_le16(c->mount_opts.compr_type);
else
sup->default_compr = cpu_to_le16(UBIFS_COMPR_LZO);
generate_random_uuid(sup->uuid);
main_bytes = (long long)main_lebs * c->leb_size;
tmp64 = div_u64(main_bytes * DEFAULT_RP_PERCENT, 100);
if (tmp64 > DEFAULT_MAX_RP_SIZE)
tmp64 = DEFAULT_MAX_RP_SIZE;
sup->rp_size = cpu_to_le64(tmp64);
sup->ro_compat_version = cpu_to_le32(UBIFS_RO_COMPAT_VERSION);
err = ubifs_write_node(c, sup, UBIFS_SB_NODE_SZ, 0, 0, UBI_LONGTERM);
kfree(sup);
if (err)
return err;
dbg_gen("default superblock created at LEB 0:0");
/* Create default master node */
mst = kzalloc(c->mst_node_alsz, GFP_KERNEL);
if (!mst)
return -ENOMEM;
mst->ch.node_type = UBIFS_MST_NODE;
mst->log_lnum = cpu_to_le32(UBIFS_LOG_LNUM);
mst->highest_inum = cpu_to_le64(UBIFS_FIRST_INO);
mst->cmt_no = 0;
mst->root_lnum = cpu_to_le32(main_first + DEFAULT_IDX_LEB);
mst->root_offs = 0;
tmp = ubifs_idx_node_sz(c, 1);
mst->root_len = cpu_to_le32(tmp);
mst->gc_lnum = cpu_to_le32(main_first + DEFAULT_GC_LEB);
mst->ihead_lnum = cpu_to_le32(main_first + DEFAULT_IDX_LEB);
mst->ihead_offs = cpu_to_le32(ALIGN(tmp, c->min_io_size));
mst->index_size = cpu_to_le64(ALIGN(tmp, 8));
mst->lpt_lnum = cpu_to_le32(c->lpt_lnum);
mst->lpt_offs = cpu_to_le32(c->lpt_offs);
mst->nhead_lnum = cpu_to_le32(c->nhead_lnum);
mst->nhead_offs = cpu_to_le32(c->nhead_offs);
mst->ltab_lnum = cpu_to_le32(c->ltab_lnum);
mst->ltab_offs = cpu_to_le32(c->ltab_offs);
mst->lsave_lnum = cpu_to_le32(c->lsave_lnum);
mst->lsave_offs = cpu_to_le32(c->lsave_offs);
mst->lscan_lnum = cpu_to_le32(main_first);
mst->empty_lebs = cpu_to_le32(main_lebs - 2);
mst->idx_lebs = cpu_to_le32(1);
mst->leb_cnt = cpu_to_le32(c->leb_cnt);
/* Calculate lprops statistics */
tmp64 = main_bytes;
tmp64 -= ALIGN(ubifs_idx_node_sz(c, 1), c->min_io_size);
tmp64 -= ALIGN(UBIFS_INO_NODE_SZ, c->min_io_size);
mst->total_free = cpu_to_le64(tmp64);
tmp64 = ALIGN(ubifs_idx_node_sz(c, 1), c->min_io_size);
ino_waste = ALIGN(UBIFS_INO_NODE_SZ, c->min_io_size) -
UBIFS_INO_NODE_SZ;
tmp64 += ino_waste;
tmp64 -= ALIGN(ubifs_idx_node_sz(c, 1), 8);
mst->total_dirty = cpu_to_le64(tmp64);
/* The indexing LEB does not contribute to dark space */
tmp64 = (c->main_lebs - 1) * c->dark_wm;
mst->total_dark = cpu_to_le64(tmp64);
mst->total_used = cpu_to_le64(UBIFS_INO_NODE_SZ);
err = ubifs_write_node(c, mst, UBIFS_MST_NODE_SZ, UBIFS_MST_LNUM, 0,
UBI_UNKNOWN);
if (err) {
kfree(mst);
return err;
}
err = ubifs_write_node(c, mst, UBIFS_MST_NODE_SZ, UBIFS_MST_LNUM + 1, 0,
UBI_UNKNOWN);
kfree(mst);
if (err)
return err;
dbg_gen("default master node created at LEB %d:0", UBIFS_MST_LNUM);
/* Create the root indexing node */
tmp = ubifs_idx_node_sz(c, 1);
idx = kzalloc(ALIGN(tmp, c->min_io_size), GFP_KERNEL);
if (!idx)
return -ENOMEM;
c->key_fmt = UBIFS_SIMPLE_KEY_FMT;
c->key_hash = key_r5_hash;
idx->ch.node_type = UBIFS_IDX_NODE;
idx->child_cnt = cpu_to_le16(1);
ino_key_init(c, &key, UBIFS_ROOT_INO);
br = ubifs_idx_branch(c, idx, 0);
key_write_idx(c, &key, &br->key);
br->lnum = cpu_to_le32(main_first + DEFAULT_DATA_LEB);
br->len = cpu_to_le32(UBIFS_INO_NODE_SZ);
err = ubifs_write_node(c, idx, tmp, main_first + DEFAULT_IDX_LEB, 0,
UBI_UNKNOWN);
kfree(idx);
if (err)
return err;
dbg_gen("default root indexing node created LEB %d:0",
main_first + DEFAULT_IDX_LEB);
/* Create default root inode */
tmp = ALIGN(UBIFS_INO_NODE_SZ, c->min_io_size);
ino = kzalloc(tmp, GFP_KERNEL);
if (!ino)
return -ENOMEM;
ino_key_init_flash(c, &ino->key, UBIFS_ROOT_INO);
ino->ch.node_type = UBIFS_INO_NODE;
ino->creat_sqnum = cpu_to_le64(++c->max_sqnum);
ino->nlink = cpu_to_le32(2);
tmp_le64 = cpu_to_le64(CURRENT_TIME_SEC.tv_sec);
ino->atime_sec = tmp_le64;
ino->ctime_sec = tmp_le64;
ino->mtime_sec = tmp_le64;
ino->atime_nsec = 0;
ino->ctime_nsec = 0;
ino->mtime_nsec = 0;
ino->mode = cpu_to_le32(S_IFDIR | S_IRUGO | S_IWUSR | S_IXUGO);
ino->size = cpu_to_le64(UBIFS_INO_NODE_SZ);
/* Set compression enabled by default */
ino->flags = cpu_to_le32(UBIFS_COMPR_FL);
err = ubifs_write_node(c, ino, UBIFS_INO_NODE_SZ,
main_first + DEFAULT_DATA_LEB, 0,
UBI_UNKNOWN);
kfree(ino);
if (err)
return err;
dbg_gen("root inode created at LEB %d:0",
main_first + DEFAULT_DATA_LEB);
/*
* The first node in the log has to be the commit start node. This is
* always the case during normal file-system operation. Write a fake
* commit start node to the log.
*/
tmp = ALIGN(UBIFS_CS_NODE_SZ, c->min_io_size);
cs = kzalloc(tmp, GFP_KERNEL);
if (!cs)
return -ENOMEM;
cs->ch.node_type = UBIFS_CS_NODE;
err = ubifs_write_node(c, cs, UBIFS_CS_NODE_SZ, UBIFS_LOG_LNUM,
0, UBI_UNKNOWN);
kfree(cs);
ubifs_msg("default file-system created");
return 0;
}
/**
* dbg_check_old_index - check the old copy of the index.
* @c: UBIFS file-system description object
* @zroot: root of the new index
*
* In order to be able to recover from an unclean unmount, a complete copy of
* the index must exist on flash. This is the "old" index. The commit process
* must write the "new" index to flash without overwriting or destroying any
* part of the old index. This function is run at commit end in order to check
* that the old index does indeed exist completely intact.
*
* This function returns %0 on success and a negative error code on failure.
*/
int dbg_check_old_index(struct ubifs_info *c, struct ubifs_zbranch *zroot)
{
int lnum, offs, len, err = 0, uninitialized_var(last_level), child_cnt;
int first = 1, iip;
struct ubifs_debug_info *d = c->dbg;
union ubifs_key lower_key, upper_key, l_key, u_key;
unsigned long long uninitialized_var(last_sqnum);
struct ubifs_idx_node *idx;
struct list_head list;
struct idx_node *i;
size_t sz;
if (!(ubifs_chk_flags & UBIFS_CHK_OLD_IDX))
goto out;
INIT_LIST_HEAD(&list);
sz = sizeof(struct idx_node) + ubifs_idx_node_sz(c, c->fanout) -
UBIFS_IDX_NODE_SZ;
/* Start at the old zroot */
lnum = d->old_zroot.lnum;
offs = d->old_zroot.offs;
len = d->old_zroot.len;
iip = 0;
/*
* Traverse the index tree preorder depth-first i.e. do a node and then
* its subtrees from left to right.
*/
while (1) {
struct ubifs_branch *br;
/* Get the next index node */
i = kmalloc(sz, GFP_NOFS);
if (!i) {
err = -ENOMEM;
goto out_free;
}
i->iip = iip;
/* Keep the index nodes on our path in a linked list */
list_add_tail(&i->list, &list);
/* Read the index node */
idx = &i->idx;
err = ubifs_read_node(c, idx, UBIFS_IDX_NODE, len, lnum, offs);
if (err)
goto out_free;
/* Validate index node */
child_cnt = le16_to_cpu(idx->child_cnt);
if (child_cnt < 1 || child_cnt > c->fanout) {
err = 1;
goto out_dump;
}
if (first) {
first = 0;
/* Check root level and sqnum */
if (le16_to_cpu(idx->level) != d->old_zroot_level) {
err = 2;
goto out_dump;
}
if (le64_to_cpu(idx->ch.sqnum) != d->old_zroot_sqnum) {
err = 3;
goto out_dump;
}
/* Set last values as though root had a parent */
last_level = le16_to_cpu(idx->level) + 1;
last_sqnum = le64_to_cpu(idx->ch.sqnum) + 1;
key_read(c, ubifs_idx_key(c, idx), &lower_key);
highest_ino_key(c, &upper_key, INUM_WATERMARK);
}
key_copy(c, &upper_key, &i->upper_key);
if (le16_to_cpu(idx->level) != last_level - 1) {
err = 3;
goto out_dump;
}
/*
* The index is always written bottom up hence a child's sqnum
* is always less than the parents.
*/
if (le64_to_cpu(idx->ch.sqnum) >= last_sqnum) {
err = 4;
goto out_dump;
}
/* Check key range */
key_read(c, ubifs_idx_key(c, idx), &l_key);
br = ubifs_idx_branch(c, idx, child_cnt - 1);
key_read(c, &br->key, &u_key);
if (keys_cmp(c, &lower_key, &l_key) > 0) {
err = 5;
goto out_dump;
}
if (keys_cmp(c, &upper_key, &u_key) < 0) {
err = 6;
goto out_dump;
}
if (keys_cmp(c, &upper_key, &u_key) == 0)
if (!is_hash_key(c, &u_key)) {
err = 7;
goto out_dump;
}
/* Go to next index node */
if (le16_to_cpu(idx->level) == 0) {
/* At the bottom, so go up until can go right */
while (1) {
/* Drop the bottom of the list */
list_del(&i->list);
kfree(i);
/* No more list means we are done */
if (list_empty(&list))
goto out;
/* Look at the new bottom */
i = list_entry(list.prev, struct idx_node,
list);
idx = &i->idx;
/* Can we go right */
if (iip + 1 < le16_to_cpu(idx->child_cnt)) {
iip = iip + 1;
break;
} else
/* Nope, so go up again */
iip = i->iip;
}
} else
/* Go down left */
iip = 0;
/*
* We have the parent in 'idx' and now we set up for reading the
* child pointed to by slot 'iip'.
*/
last_level = le16_to_cpu(idx->level);
last_sqnum = le64_to_cpu(idx->ch.sqnum);
br = ubifs_idx_branch(c, idx, iip);
lnum = le32_to_cpu(br->lnum);
offs = le32_to_cpu(br->offs);
len = le32_to_cpu(br->len);
key_read(c, &br->key, &lower_key);
if (iip + 1 < le16_to_cpu(idx->child_cnt)) {
br = ubifs_idx_branch(c, idx, iip + 1);
key_read(c, &br->key, &upper_key);
} else
key_copy(c, &i->upper_key, &upper_key);
}
/**
* validate_sb - validate superblock node.
* @c: UBIFS file-system description object
* @sup: superblock node
*
* This function validates superblock node @sup. Since most of data was read
* from the superblock and stored in @c, the function validates fields in @c
* instead. Returns zero in case of success and %-EINVAL in case of validation
* failure.
*/
static int validate_sb(struct ubifs_info *c, struct ubifs_sb_node *sup)
{
long long max_bytes;
int err = 1, min_leb_cnt;
if (!c->key_hash) {
err = 2;
goto failed;
}
if (sup->key_fmt != UBIFS_SIMPLE_KEY_FMT) {
err = 3;
goto failed;
}
if (le32_to_cpu(sup->min_io_size) != c->min_io_size) {
ubifs_err("min. I/O unit mismatch: %d in superblock, %d real",
le32_to_cpu(sup->min_io_size), c->min_io_size);
goto failed;
}
if (le32_to_cpu(sup->leb_size) != c->leb_size) {
ubifs_err("LEB size mismatch: %d in superblock, %d real",
le32_to_cpu(sup->leb_size), c->leb_size);
goto failed;
}
if (c->log_lebs < UBIFS_MIN_LOG_LEBS ||
c->lpt_lebs < UBIFS_MIN_LPT_LEBS ||
c->orph_lebs < UBIFS_MIN_ORPH_LEBS ||
c->main_lebs < UBIFS_MIN_MAIN_LEBS) {
err = 4;
goto failed;
}
/*
* Calculate minimum allowed amount of main area LEBs. This is very
* similar to %UBIFS_MIN_LEB_CNT, but we take into account real what we
* have just read from the superblock.
*/
min_leb_cnt = UBIFS_SB_LEBS + UBIFS_MST_LEBS + c->log_lebs;
min_leb_cnt += c->lpt_lebs + c->orph_lebs + c->jhead_cnt + 6;
if (c->leb_cnt < min_leb_cnt || c->leb_cnt > c->vi.size) {
ubifs_err("bad LEB count: %d in superblock, %d on UBI volume, "
"%d minimum required", c->leb_cnt, c->vi.size,
min_leb_cnt);
goto failed;
}
if (c->max_leb_cnt < c->leb_cnt) {
ubifs_err("max. LEB count %d less than LEB count %d",
c->max_leb_cnt, c->leb_cnt);
goto failed;
}
if (c->main_lebs < UBIFS_MIN_MAIN_LEBS) {
err = 7;
goto failed;
}
if (c->max_bud_bytes < (long long)c->leb_size * UBIFS_MIN_BUD_LEBS ||
c->max_bud_bytes > (long long)c->leb_size * c->main_lebs) {
err = 8;
goto failed;
}
if (c->jhead_cnt < NONDATA_JHEADS_CNT + 1 ||
c->jhead_cnt > NONDATA_JHEADS_CNT + UBIFS_MAX_JHEADS) {
err = 9;
goto failed;
}
if (c->fanout < UBIFS_MIN_FANOUT ||
ubifs_idx_node_sz(c, c->fanout) > c->leb_size) {
err = 10;
goto failed;
}
if (c->lsave_cnt < 0 || (c->lsave_cnt > DEFAULT_LSAVE_CNT &&
c->lsave_cnt > c->max_leb_cnt - UBIFS_SB_LEBS - UBIFS_MST_LEBS -
c->log_lebs - c->lpt_lebs - c->orph_lebs)) {
err = 11;
goto failed;
}
if (UBIFS_SB_LEBS + UBIFS_MST_LEBS + c->log_lebs + c->lpt_lebs +
c->orph_lebs + c->main_lebs != c->leb_cnt) {
err = 12;
goto failed;
}
if (c->default_compr < 0 || c->default_compr >= UBIFS_COMPR_TYPES_CNT) {
err = 13;
goto failed;
}
max_bytes = c->main_lebs * (long long)c->leb_size;
if (c->rp_size < 0 || max_bytes < c->rp_size) {
err = 14;
goto failed;
}
if (le32_to_cpu(sup->time_gran) > 1000000000 ||
le32_to_cpu(sup->time_gran) < 1) {
err = 15;
goto failed;
}
return 0;
failed:
ubifs_err("bad superblock, error %d", err);
dbg_dump_node(c, sup);
return -EINVAL;
}
/*
* init_constants_sb - initialize UBIFS constants.
* @c: UBIFS file-system description object
*
* This is a helper function which initializes various UBIFS constants after
* the superblock has been read. It also checks various UBIFS parameters and
* makes sure they are all right. Returns zero in case of success and a
* negative error code in case of failure.
*/
static int init_constants_sb(struct ubifs_info *c)
{
int tmp, err;
long long tmp64;
c->main_bytes = (long long)c->main_lebs * c->leb_size;
c->max_znode_sz = sizeof(struct ubifs_znode) +
c->fanout * sizeof(struct ubifs_zbranch);
tmp = ubifs_idx_node_sz(c, 1);
c->ranges[UBIFS_IDX_NODE].min_len = tmp;
c->min_idx_node_sz = ALIGN(tmp, 8);
tmp = ubifs_idx_node_sz(c, c->fanout);
c->ranges[UBIFS_IDX_NODE].max_len = tmp;
c->max_idx_node_sz = ALIGN(tmp, 8);
/* Make sure LEB size is large enough to fit full commit */
tmp = UBIFS_CS_NODE_SZ + UBIFS_REF_NODE_SZ * c->jhead_cnt;
tmp = ALIGN(tmp, c->min_io_size);
if (tmp > c->leb_size) {
dbg_err("too small LEB size %d, at least %d needed",
c->leb_size, tmp);
return -EINVAL;
}
/*
* Make sure that the log is large enough to fit reference nodes for
* all buds plus one reserved LEB.
*/
tmp64 = c->max_bud_bytes + c->leb_size - 1;
c->max_bud_cnt = div_u64(tmp64, c->leb_size);
tmp = (c->ref_node_alsz * c->max_bud_cnt + c->leb_size - 1);
tmp /= c->leb_size;
tmp += 1;
if (c->log_lebs < tmp) {
dbg_err("too small log %d LEBs, required min. %d LEBs",
c->log_lebs, tmp);
return -EINVAL;
}
/*
* When budgeting we assume worst-case scenarios when the pages are not
* be compressed and direntries are of the maximum size.
*
* Note, data, which may be stored in inodes is budgeted separately, so
* it is not included into 'c->inode_budget'.
*/
c->page_budget = UBIFS_MAX_DATA_NODE_SZ * UBIFS_BLOCKS_PER_PAGE;
c->inode_budget = UBIFS_INO_NODE_SZ;
c->dent_budget = UBIFS_MAX_DENT_NODE_SZ;
/*
* When the amount of flash space used by buds becomes
* 'c->max_bud_bytes', UBIFS just blocks all writers and starts commit.
* The writers are unblocked when the commit is finished. To avoid
* writers to be blocked UBIFS initiates background commit in advance,
* when number of bud bytes becomes above the limit defined below.
*/
c->bg_bud_bytes = (c->max_bud_bytes * 13) >> 4;
/*
* Ensure minimum journal size. All the bytes in the journal heads are
* considered to be used, when calculating the current journal usage.
* Consequently, if the journal is too small, UBIFS will treat it as
* always full.
*/
tmp64 = (long long)(c->jhead_cnt + 1) * c->leb_size + 1;
if (c->bg_bud_bytes < tmp64)
c->bg_bud_bytes = tmp64;
if (c->max_bud_bytes < tmp64 + c->leb_size)
c->max_bud_bytes = tmp64 + c->leb_size;
err = ubifs_calc_lpt_geom(c);
if (err)
return err;
return 0;
}
