int ext4_data_block_valid(struct ext4_sb_info *sbi, ext4_fsblk_t start_blk,
unsigned int count)
{
struct ext4_system_zone *entry;
struct rb_node *n = sbi->system_blks.rb_node;
if ((start_blk <= le32_to_cpu(sbi->s_es->s_first_data_block)) ||
(start_blk + count < start_blk) ||
(start_blk + count > ext4_blocks_count(sbi->s_es))) {
sbi->s_es->s_last_error_block = cpu_to_le64(start_blk);
return 0;
}
while (n) {
entry = rb_entry(n, struct ext4_system_zone, node);
if (start_blk + count - 1 < entry->start_blk)
n = n->rb_left;
else if (start_blk >= (entry->start_blk + entry->count))
n = n->rb_right;
else {
sbi->s_es->s_last_error_block = cpu_to_le64(start_blk);
return 0;
}
}
return 1;
}
/*
* Migrate a simple extent-based inode to use the i_blocks[] array
*/
int ext4_ind_migrate(struct inode *inode)
{
struct ext4_extent_header *eh;
struct ext4_super_block *es = EXT4_SB(inode->i_sb)->s_es;
struct ext4_inode_info *ei = EXT4_I(inode);
struct ext4_extent *ex;
unsigned int i, len;
ext4_fsblk_t blk;
handle_t *handle;
int ret;
if (!EXT4_HAS_INCOMPAT_FEATURE(inode->i_sb,
EXT4_FEATURE_INCOMPAT_EXTENTS) ||
(!ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)))
return -EINVAL;
if (EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb,
EXT4_FEATURE_RO_COMPAT_BIGALLOC))
return -EOPNOTSUPP;
handle = ext4_journal_start(inode, EXT4_HT_MIGRATE, 1);
if (IS_ERR(handle))
return PTR_ERR(handle);
down_write(&EXT4_I(inode)->i_data_sem);
ret = ext4_ext_check_inode(inode);
if (ret)
goto errout;
eh = ext_inode_hdr(inode);
ex = EXT_FIRST_EXTENT(eh);
if (ext4_blocks_count(es) > EXT4_MAX_BLOCK_FILE_PHYS ||
eh->eh_depth != 0 || le16_to_cpu(eh->eh_entries) > 1) {
ret = -EOPNOTSUPP;
goto errout;
}
if (eh->eh_entries == 0)
blk = len = 0;
else {
len = le16_to_cpu(ex->ee_len);
blk = ext4_ext_pblock(ex);
if (len > EXT4_NDIR_BLOCKS) {
ret = -EOPNOTSUPP;
goto errout;
}
}
ext4_clear_inode_flag(inode, EXT4_INODE_EXTENTS);
memset(ei->i_data, 0, sizeof(ei->i_data));
for (i=0; i < len; i++)
ei->i_data[i] = cpu_to_le32(blk++);
ext4_mark_inode_dirty(handle, inode);
errout:
ext4_journal_stop(handle);
up_write(&EXT4_I(inode)->i_data_sem);
return ret;
}
/* Initializes an uninitialized block bitmap if given, and returns the
* number of blocks free in the group. */
unsigned ext4_init_block_bitmap(struct super_block *sb, struct buffer_head *bh,
ext4_group_t block_group, struct ext4_group_desc *gdp)
{
int bit, bit_max;
ext4_group_t ngroups = ext4_get_groups_count(sb);
unsigned free_blocks, group_blocks;
struct ext4_sb_info *sbi = EXT4_SB(sb);
if (bh) {
J_ASSERT_BH(bh, buffer_locked(bh));
/* If checksum is bad mark all blocks used to prevent allocation
* essentially implementing a per-group read-only flag. */
if (!ext4_group_desc_csum_verify(sbi, block_group, gdp)) {
ext4_error(sb, __func__,
"Checksum bad for group %u", block_group);
ext4_free_blks_set(sb, gdp, 0);
ext4_free_inodes_set(sb, gdp, 0);
ext4_itable_unused_set(sb, gdp, 0);
memset(bh->b_data, 0xff, sb->s_blocksize);
return 0;
}
memset(bh->b_data, 0, sb->s_blocksize);
}
/* Check for superblock and gdt backups in this group */
bit_max = ext4_bg_has_super(sb, block_group);
if (!EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_META_BG) ||
block_group < le32_to_cpu(sbi->s_es->s_first_meta_bg) *
sbi->s_desc_per_block) {
if (bit_max) {
bit_max += ext4_bg_num_gdb(sb, block_group);
bit_max +=
le16_to_cpu(sbi->s_es->s_reserved_gdt_blocks);
}
} else { /* For META_BG_BLOCK_GROUPS */
bit_max += ext4_bg_num_gdb(sb, block_group);
}
if (block_group == ngroups - 1) {
/*
* Even though mke2fs always initialize first and last group
* if some other tool enabled the EXT4_BG_BLOCK_UNINIT we need
* to make sure we calculate the right free blocks
*/
group_blocks = ext4_blocks_count(sbi->s_es) -
le32_to_cpu(sbi->s_es->s_first_data_block) -
(EXT4_BLOCKS_PER_GROUP(sb) * (ngroups - 1));
} else {
group_blocks = EXT4_BLOCKS_PER_GROUP(sb);
}
free_blocks = group_blocks - bit_max;
if (bh) {
ext4_fsblk_t start, tmp;
int flex_bg = 0;
for (bit = 0; bit < bit_max; bit++)
ext4_set_bit(bit, bh->b_data);
start = ext4_group_first_block_no(sb, block_group);
if (EXT4_HAS_INCOMPAT_FEATURE(sb,
EXT4_FEATURE_INCOMPAT_FLEX_BG))
flex_bg = 1;
/* Set bits for block and inode bitmaps, and inode table */
tmp = ext4_block_bitmap(sb, gdp);
if (!flex_bg || ext4_block_in_group(sb, tmp, block_group))
ext4_set_bit(tmp - start, bh->b_data);
tmp = ext4_inode_bitmap(sb, gdp);
if (!flex_bg || ext4_block_in_group(sb, tmp, block_group))
ext4_set_bit(tmp - start, bh->b_data);
tmp = ext4_inode_table(sb, gdp);
for (; tmp < ext4_inode_table(sb, gdp) +
sbi->s_itb_per_group; tmp++) {
if (!flex_bg ||
ext4_block_in_group(sb, tmp, block_group))
ext4_set_bit(tmp - start, bh->b_data);
}
/*
* Also if the number of blocks within the group is
* less than the blocksize * 8 ( which is the size
* of bitmap ), set rest of the block bitmap to 1
*/
mark_bitmap_end(group_blocks, sb->s_blocksize * 8, bh->b_data);
}
return free_blocks - ext4_group_used_meta_blocks(sb, block_group, gdp);
}
/*
* Protect the filesystem from being mounted more than once.
*/
int ext4_multi_mount_protect(struct super_block *sb,
ext4_fsblk_t mmp_block)
{
struct ext4_super_block *es = EXT4_SB(sb)->s_es;
struct buffer_head *bh = NULL;
struct mmp_struct *mmp = NULL;
struct mmpd_data *mmpd_data;
u32 seq;
unsigned int mmp_check_interval = le16_to_cpu(es->s_mmp_update_interval);
unsigned int wait_time = 0;
int retval;
if (mmp_block < le32_to_cpu(es->s_first_data_block) ||
mmp_block >= ext4_blocks_count(es)) {
ext4_warning(sb, "Invalid MMP block in superblock");
goto failed;
}
retval = read_mmp_block(sb, &bh, mmp_block);
if (retval)
goto failed;
mmp = (struct mmp_struct *)(bh->b_data);
if (mmp_check_interval < EXT4_MMP_MIN_CHECK_INTERVAL)
mmp_check_interval = EXT4_MMP_MIN_CHECK_INTERVAL;
/*
* If check_interval in MMP block is larger, use that instead of
* update_interval from the superblock.
*/
if (le16_to_cpu(mmp->mmp_check_interval) > mmp_check_interval)
mmp_check_interval = le16_to_cpu(mmp->mmp_check_interval);
seq = le32_to_cpu(mmp->mmp_seq);
if (seq == EXT4_MMP_SEQ_CLEAN)
goto skip;
if (seq == EXT4_MMP_SEQ_FSCK) {
dump_mmp_msg(sb, mmp, "fsck is running on the filesystem");
goto failed;
}
wait_time = min(mmp_check_interval * 2 + 1,
mmp_check_interval + 60);
/* Print MMP interval if more than 20 secs. */
if (wait_time > EXT4_MMP_MIN_CHECK_INTERVAL * 4)
ext4_warning(sb, "MMP interval %u higher than expected, please"
" wait.\n", wait_time * 2);
if (schedule_timeout_interruptible(HZ * wait_time) != 0) {
ext4_warning(sb, "MMP startup interrupted, failing mount\n");
goto failed;
}
retval = read_mmp_block(sb, &bh, mmp_block);
if (retval)
goto failed;
mmp = (struct mmp_struct *)(bh->b_data);
if (seq != le32_to_cpu(mmp->mmp_seq)) {
dump_mmp_msg(sb, mmp,
"Device is already active on another node.");
goto failed;
}
skip:
/*
* write a new random sequence number.
*/
seq = mmp_new_seq();
mmp->mmp_seq = cpu_to_le32(seq);
retval = write_mmp_block(sb, bh);
if (retval)
goto failed;
/*
* wait for MMP interval and check mmp_seq.
*/
if (schedule_timeout_interruptible(HZ * wait_time) != 0) {
ext4_warning(sb, "MMP startup interrupted, failing mount\n");
goto failed;
}
retval = read_mmp_block(sb, &bh, mmp_block);
if (retval)
goto failed;
mmp = (struct mmp_struct *)(bh->b_data);
if (seq != le32_to_cpu(mmp->mmp_seq)) {
dump_mmp_msg(sb, mmp,
"Device is already active on another node.");
goto failed;
}
mmpd_data = kmalloc(sizeof(struct mmpd_data), GFP_KERNEL);
if (!mmpd_data) {
ext4_warning(sb, "not enough memory for mmpd_data");
goto failed;
}
mmpd_data->sb = sb;
mmpd_data->bh = bh;
/*
* Start a kernel thread to update the MMP block periodically.
*/
EXT4_SB(sb)->s_mmp_tsk = kthread_run(kmmpd, mmpd_data, "kmmpd-%s",
bdevname(bh->b_bdev,
mmp->mmp_bdevname));
if (IS_ERR(EXT4_SB(sb)->s_mmp_tsk)) {
EXT4_SB(sb)->s_mmp_tsk = NULL;
kfree(mmpd_data);
ext4_warning(sb, "Unable to create kmmpd thread for %s.",
sb->s_id);
goto failed;
}
return 0;
failed:
brelse(bh);
return 1;
}
/*
* Migrate a simple extent-based inode to use the i_blocks[] array
*/
int ext4_ind_migrate(struct inode *inode)
{
struct ext4_extent_header *eh;
struct ext4_super_block *es = EXT4_SB(inode->i_sb)->s_es;
struct ext4_inode_info *ei = EXT4_I(inode);
struct ext4_extent *ex;
unsigned int i, len;
ext4_lblk_t start, end;
ext4_fsblk_t blk;
handle_t *handle;
int ret;
if (!EXT4_HAS_INCOMPAT_FEATURE(inode->i_sb,
EXT4_FEATURE_INCOMPAT_EXTENTS) ||
(!ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)))
return -EINVAL;
if (EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb,
EXT4_FEATURE_RO_COMPAT_BIGALLOC))
return -EOPNOTSUPP;
/*
* In order to get correct extent info, force all delayed allocation
* blocks to be allocated, otherwise delayed allocation blocks may not
* be reflected and bypass the checks on extent header.
*/
if (test_opt(inode->i_sb, DELALLOC))
ext4_alloc_da_blocks(inode);
handle = ext4_journal_start(inode, EXT4_HT_MIGRATE, 1);
if (IS_ERR(handle))
return PTR_ERR(handle);
down_write(&EXT4_I(inode)->i_data_sem);
ret = ext4_ext_check_inode(inode);
if (ret)
goto errout;
eh = ext_inode_hdr(inode);
ex = EXT_FIRST_EXTENT(eh);
if (ext4_blocks_count(es) > EXT4_MAX_BLOCK_FILE_PHYS ||
eh->eh_depth != 0 || le16_to_cpu(eh->eh_entries) > 1) {
ret = -EOPNOTSUPP;
goto errout;
}
if (eh->eh_entries == 0)
blk = len = start = end = 0;
else {
len = le16_to_cpu(ex->ee_len);
blk = ext4_ext_pblock(ex);
start = le32_to_cpu(ex->ee_block);
end = start + len - 1;
if (end >= EXT4_NDIR_BLOCKS) {
ret = -EOPNOTSUPP;
goto errout;
}
}
ext4_clear_inode_flag(inode, EXT4_INODE_EXTENTS);
memset(ei->i_data, 0, sizeof(ei->i_data));
for (i = start; i <= end; i++)
ei->i_data[i] = cpu_to_le32(blk++);
ext4_mark_inode_dirty(handle, inode);
errout:
ext4_journal_stop(handle);
up_write(&EXT4_I(inode)->i_data_sem);
return ret;
}
static void do_reserved_size(char *blk_device, char *fs_type, struct fstab_rec *rec)
{
/* Check for the types of filesystems we know how to check */
if (!strcmp(fs_type, "ext2") || !strcmp(fs_type, "ext3") || !strcmp(fs_type, "ext4")) {
/*
* Some system images do not have tune2fs for licensing reasons
* Detect these and skip reserve blocks.
*/
if (access(TUNE2FS_BIN, X_OK)) {
ERROR("Not running %s on %s (executable not in system image)\n",
TUNE2FS_BIN, blk_device);
} else {
INFO("Running %s on %s\n", TUNE2FS_BIN, blk_device);
int status = 0;
int ret = 0;
unsigned long reserved_blocks = 0;
int fd = TEMP_FAILURE_RETRY(open(blk_device, O_RDONLY | O_CLOEXEC));
if (fd >= 0) {
struct ext4_super_block sb;
ret = read_super_block(fd, &sb);
if (ret < 0) {
ERROR("Can't read '%s' super block: %s\n", blk_device, strerror(errno));
goto out;
}
reserved_blocks = rec->reserved_size / EXT4_BLOCK_SIZE(&sb);
unsigned long reserved_threshold = ext4_blocks_count(&sb) * 0.02;
if (reserved_threshold < reserved_blocks) {
WARNING("Reserved blocks %lu is too large\n", reserved_blocks);
reserved_blocks = reserved_threshold;
}
if (ext4_r_blocks_count(&sb) == reserved_blocks) {
INFO("Have reserved same blocks\n");
goto out;
}
} else {
ERROR("Failed to open '%s': %s\n", blk_device, strerror(errno));
return;
}
char buf[16] = {0};
snprintf(buf, sizeof (buf), "-r %lu", reserved_blocks);
char *tune2fs_argv[] = {
TUNE2FS_BIN,
buf,
blk_device,
};
ret = android_fork_execvp_ext(ARRAY_SIZE(tune2fs_argv), tune2fs_argv,
&status, true, LOG_KLOG | LOG_FILE,
true, NULL, NULL, 0);
if (ret < 0) {
/* No need to check for error in fork, we can't really handle it now */
ERROR("Failed trying to run %s\n", TUNE2FS_BIN);
}
out:
close(fd);
}
}
}
static int find_group_orlov(struct super_block *sb, struct inode *parent)
{
int parent_group = EXT4_I(parent)->i_block_group;
struct ext4_sb_info *sbi = EXT4_SB(sb);
struct ext4_super_block *es = sbi->s_es;
int ngroups = sbi->s_groups_count;
int inodes_per_group = EXT4_INODES_PER_GROUP(sb);
unsigned int freei, avefreei;
ext4_fsblk_t freeb, avefreeb;
ext4_fsblk_t blocks_per_dir;
unsigned int ndirs;
int max_debt, max_dirs, min_inodes;
ext4_grpblk_t min_blocks;
int group = -1, i;
struct ext4_group_desc *desc;
struct buffer_head *bh;
freei = percpu_counter_read_positive(&sbi->s_freeinodes_counter);
avefreei = freei / ngroups;
freeb = percpu_counter_read_positive(&sbi->s_freeblocks_counter);
avefreeb = freeb;
do_div(avefreeb, ngroups);
ndirs = percpu_counter_read_positive(&sbi->s_dirs_counter);
if ((parent == sb->s_root->d_inode) ||
(EXT4_I(parent)->i_flags & EXT4_TOPDIR_FL)) {
int best_ndir = inodes_per_group;
int best_group = -1;
get_random_bytes(&group, sizeof(group));
parent_group = (unsigned)group % ngroups;
for (i = 0; i < ngroups; i++) {
group = (parent_group + i) % ngroups;
desc = ext4_get_group_desc (sb, group, &bh);
if (!desc || !desc->bg_free_inodes_count)
continue;
if (le16_to_cpu(desc->bg_used_dirs_count) >= best_ndir)
continue;
if (le16_to_cpu(desc->bg_free_inodes_count) < avefreei)
continue;
if (le16_to_cpu(desc->bg_free_blocks_count) < avefreeb)
continue;
best_group = group;
best_ndir = le16_to_cpu(desc->bg_used_dirs_count);
}
if (best_group >= 0)
return best_group;
goto fallback;
}
blocks_per_dir = ext4_blocks_count(es) - freeb;
do_div(blocks_per_dir, ndirs);
max_dirs = ndirs / ngroups + inodes_per_group / 16;
min_inodes = avefreei - inodes_per_group / 4;
min_blocks = avefreeb - EXT4_BLOCKS_PER_GROUP(sb) / 4;
max_debt = EXT4_BLOCKS_PER_GROUP(sb);
max_debt /= max_t(int, blocks_per_dir, BLOCK_COST);
if (max_debt * INODE_COST > inodes_per_group)
max_debt = inodes_per_group / INODE_COST;
if (max_debt > 255)
max_debt = 255;
if (max_debt == 0)
max_debt = 1;
for (i = 0; i < ngroups; i++) {
group = (parent_group + i) % ngroups;
desc = ext4_get_group_desc (sb, group, &bh);
if (!desc || !desc->bg_free_inodes_count)
continue;
if (le16_to_cpu(desc->bg_used_dirs_count) >= max_dirs)
continue;
if (le16_to_cpu(desc->bg_free_inodes_count) < min_inodes)
continue;
if (le16_to_cpu(desc->bg_free_blocks_count) < min_blocks)
continue;
return group;
}
fallback:
for (i = 0; i < ngroups; i++) {
group = (parent_group + i) % ngroups;
desc = ext4_get_group_desc (sb, group, &bh);
if (!desc || !desc->bg_free_inodes_count)
continue;
if (le16_to_cpu(desc->bg_free_inodes_count) >= avefreei)
return group;
}
if (avefreei) {
/*
* The free-inodes counter is approximate, and for really small
* filesystems the above test can fail to find any blockgroups
*/
avefreei = 0;
goto fallback;
}
return -1;
}
