static ssize_t
ext4_file_write(struct kiocb *iocb, const struct iovec *iov,
unsigned long nr_segs, loff_t pos)
{
struct inode *inode = iocb->ki_filp->f_path.dentry->d_inode;
int unaligned_aio = 0;
int ret;
/*
* If we have encountered a bitmap-format file, the size limit
* is smaller than s_maxbytes, which is for extent-mapped files.
*/
if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) {
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
size_t length = iov_length(iov, nr_segs);
if ((pos > sbi->s_bitmap_maxbytes ||
(pos == sbi->s_bitmap_maxbytes && length > 0)))
return -EFBIG;
if (pos + length > sbi->s_bitmap_maxbytes) {
nr_segs = iov_shorten((struct iovec *)iov, nr_segs,
sbi->s_bitmap_maxbytes - pos);
}
} else if (unlikely((iocb->ki_filp->f_flags & O_DIRECT) &&
!is_sync_kiocb(iocb))) {
unaligned_aio = ext4_unaligned_aio(inode, iov, nr_segs, pos);
}
/* Unaligned direct AIO must be serialized; see comment above */
if (unaligned_aio) {
static unsigned long unaligned_warn_time;
/* Warn about this once per day */
if (printk_timed_ratelimit(&unaligned_warn_time, 60*60*24*HZ))
ext4_msg(inode->i_sb, KERN_WARNING,
"Unaligned AIO/DIO on inode %ld by %s; "
"performance will be poor.",
inode->i_ino, current->comm);
mutex_lock(ext4_aio_mutex(inode));
ext4_aiodio_wait(inode);
}
ret = generic_file_aio_write(iocb, iov, nr_segs, pos);
if (unaligned_aio)
mutex_unlock(ext4_aio_mutex(inode));
return ret;
}
static int ext4_file_open(struct inode * inode, struct file * filp)
{
struct super_block *sb = inode->i_sb;
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
struct ext4_inode_info *ei = EXT4_I(inode);
struct vfsmount *mnt = filp->f_path.mnt;
struct path path;
char buf[64], *cp;
if (unlikely(!(sbi->s_mount_flags & EXT4_MF_MNTDIR_SAMPLED) &&
!(sb->s_flags & MS_RDONLY))) {
sbi->s_mount_flags |= EXT4_MF_MNTDIR_SAMPLED;
/*
* Sample where the filesystem has been mounted and
* store it in the superblock for sysadmin convenience
* when trying to sort through large numbers of block
* devices or filesystem images.
*/
memset(buf, 0, sizeof(buf));
path.mnt = mnt;
path.dentry = mnt->mnt_root;
cp = d_path(&path, buf, sizeof(buf));
if (!IS_ERR(cp)) {
strlcpy(sbi->s_es->s_last_mounted, cp,
sizeof(sbi->s_es->s_last_mounted));
ext4_mark_super_dirty(sb);
}
}
/*
* Set up the jbd2_inode if we are opening the inode for
* writing and the journal is present
*/
if (sbi->s_journal && !ei->jinode && (filp->f_mode & FMODE_WRITE)) {
struct jbd2_inode *jinode = jbd2_alloc_inode(GFP_KERNEL);
spin_lock(&inode->i_lock);
if (!ei->jinode) {
if (!jinode) {
spin_unlock(&inode->i_lock);
return -ENOMEM;
}
ei->jinode = jinode;
jbd2_journal_init_jbd_inode(ei->jinode, inode);
jinode = NULL;
}
spin_unlock(&inode->i_lock);
if (unlikely(jinode != NULL))
jbd2_free_inode(jinode);
}
return dquot_file_open(inode, filp);
}
/**
* ext4_count_free_blocks() -- count filesystem free blocks
* @sb: superblock
*
* Adds up the number of free blocks from each block group.
*/
ext4_fsblk_t ext4_count_free_blocks(struct super_block *sb)
{
ext4_fsblk_t desc_count;
struct ext4_group_desc *gdp;
ext4_group_t i;
ext4_group_t ngroups = ext4_get_groups_count(sb);
#ifdef EXT4FS_DEBUG
struct ext4_super_block *es;
ext4_fsblk_t bitmap_count;
unsigned int x;
struct buffer_head *bitmap_bh = NULL;
es = EXT4_SB(sb)->s_es;
desc_count = 0;
bitmap_count = 0;
gdp = NULL;
for (i = 0; i < ngroups; i++) {
gdp = ext4_get_group_desc(sb, i, NULL);
if (!gdp)
continue;
desc_count += ext4_free_blks_count(sb, gdp);
brelse(bitmap_bh);
bitmap_bh = ext4_read_block_bitmap(sb, i);
if (bitmap_bh == NULL)
continue;
x = ext4_count_free(bitmap_bh->b_data,
EXT4_BLOCKS_PER_GROUP(sb) / 8);
printk(KERN_DEBUG "group %u: stored = %d, counted = %u\n",
i, ext4_free_blks_count(sb, gdp), x);
bitmap_count += x;
}
brelse(bitmap_bh);
printk(KERN_DEBUG "ext4_count_free_blocks: stored = %llu"
", computed = %llu, %llu\n", ext4_free_blocks_count(es),
desc_count, bitmap_count);
return bitmap_count;
#else
desc_count = 0;
for (i = 0; i < ngroups; i++) {
gdp = ext4_get_group_desc(sb, i, NULL);
if (!gdp)
continue;
desc_count += ext4_free_blks_count(sb, gdp);
}
return desc_count;
#endif
}
int __ext4bf_handle_dirty_metadata(const char *where, unsigned int line,
handle_t *handle, struct inode *inode,
struct buffer_head *bh)
{
int err = 0;
if (ext4bf_handle_valid(handle)) {
#ifdef DCHECKSUM
/* ext4bf: handle cases where it is a data block. */
if (bh && bh->b_blocktype == B_BLOCKTYPE_DATA) {
#endif
#ifdef PARTJ
if (!buffer_new(bh))
err = jbdbf_journal_dirty_metadata(handle, bh);
else
#endif
#ifdef DCHECKSUM
jbdbf_journal_dirty_data(handle, bh);
} else
#endif
err = jbdbf_journal_dirty_metadata(handle, bh);
if (err) {
/* Errors can only happen if there is a bug */
handle->h_err = err;
__ext4bf_journal_stop(where, line, handle);
}
} else {
if (inode)
mark_buffer_dirty_inode(bh, inode);
else
mark_buffer_dirty(bh);
if (inode && inode_needs_sync(inode)) {
sync_dirty_buffer(bh);
if (buffer_req(bh) && !buffer_uptodate(bh)) {
struct ext4bf_super_block *es;
es = EXT4_SB(inode->i_sb)->s_es;
es->s_last_error_block =
cpu_to_le64(bh->b_blocknr);
ext4bf_error_inode(inode, where, line,
bh->b_blocknr,
"IO error syncing itable block");
err = -EIO;
}
}
}
return err;
}
static void reset_inode_seed(struct inode *inode)
{
struct ext4_inode_info *ei = EXT4_I(inode);
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
__le32 inum = cpu_to_le32(inode->i_ino);
__le32 gen = cpu_to_le32(inode->i_generation);
__u32 csum;
if (!ext4_has_metadata_csum(inode->i_sb))
return;
csum = ext4_chksum(sbi, sbi->s_csum_seed, (__u8 *)&inum, sizeof(inum));
ei->i_csum_seed = ext4_chksum(sbi, csum, (__u8 *)&gen, sizeof(gen));
}
/*
* Calculate the block group number and offset, given a block number
*/
void ext4_get_group_no_and_offset(struct super_block *sb, ext4_fsblk_t blocknr,
ext4_group_t *blockgrpp, ext4_grpblk_t *offsetp)
{
struct ext4_super_block *es = EXT4_SB(sb)->s_es;
ext4_grpblk_t offset;
blocknr = blocknr - le32_to_cpu(es->s_first_data_block);
offset = do_div(blocknr, EXT4_BLOCKS_PER_GROUP(sb));
if (offsetp)
*offsetp = offset;
if (blockgrpp)
*blockgrpp = blocknr;
}
static long ext4_ioctl_group_add(struct file *file,
struct ext4_new_group_data *input)
{
struct super_block *sb = file_inode(file)->i_sb;
int err, err2=0;
err = ext4_resize_begin(sb);
if (err)
return err;
if (ext4_has_feature_bigalloc(sb)) {
ext4_msg(sb, KERN_ERR,
"Online resizing not supported with bigalloc");
err = -EOPNOTSUPP;
goto group_add_out;
}
err = mnt_want_write_file(file);
if (err)
goto group_add_out;
err = ext4_group_add(sb, input);
if (EXT4_SB(sb)->s_journal) {
jbd2_journal_lock_updates(EXT4_SB(sb)->s_journal);
err2 = jbd2_journal_flush(EXT4_SB(sb)->s_journal);
jbd2_journal_unlock_updates(EXT4_SB(sb)->s_journal);
}
if (err == 0)
err = err2;
mnt_drop_write_file(file);
if (!err && ext4_has_group_desc_csum(sb) &&
test_opt(sb, INIT_INODE_TABLE))
err = ext4_register_li_request(sb, input->group);
group_add_out:
ext4_resize_end(sb);
return err;
}
int ext4_sync_file(struct file *file, struct dentry *dentry, int datasync)
{
struct inode *inode = dentry->d_inode;
struct ext4_inode_info *ei = EXT4_I(inode);
journal_t *journal = EXT4_SB(inode->i_sb)->s_journal;
int ret;
tid_t commit_tid;
bool needs_barrier = false;
J_ASSERT(ext4_journal_current_handle() == NULL);
trace_ext4_sync_file(file, dentry, datasync);
if (inode->i_sb->s_flags & MS_RDONLY)
return 0;
ret = flush_aio_dio_completed_IO(inode);
if (ret < 0)
return ret;
if (!journal)
return simple_fsync(file, dentry, datasync);
/*
* data=writeback,ordered:
* The caller's filemap_fdatawrite()/wait will sync the data.
* Metadata is in the journal, we wait for proper transaction to
* commit here.
*
* data=journal:
* filemap_fdatawrite won't do anything (the buffers are clean).
* ext4_force_commit will write the file data into the journal and
* will wait on that.
* filemap_fdatawait() will encounter a ton of newly-dirtied pages
* (they were dirtied by commit). But that's OK - the blocks are
* safe in-journal, which is all fsync() needs to ensure.
*/
if (ext4_should_journal_data(inode))
return ext4_force_commit(inode->i_sb);
commit_tid = datasync ? ei->i_datasync_tid : ei->i_sync_tid;
if (journal->j_flags & JBD2_BARRIER &&
!jbd2_trans_will_send_data_barrier(journal, commit_tid))
needs_barrier = true;
ret = jbd2_complete_transaction(journal, commit_tid);
if (needs_barrier)
blkdev_issue_flush(inode->i_sb->s_bdev, NULL);
return ret;
}
void ext4_inode_bitmap_csum_set(struct super_block *sb, ext4_group_t group,
struct ext4_group_desc *gdp,
struct buffer_head *bh, int sz)
{
__u32 csum;
struct ext4_sb_info *sbi = EXT4_SB(sb);
if (!ext4_has_metadata_csum(sb))
return;
csum = ext4_chksum(sbi, sbi->s_csum_seed, (__u8 *)bh->b_data, sz);
gdp->bg_inode_bitmap_csum_lo = cpu_to_le16(csum & 0xFFFF);
if (sbi->s_desc_size >= EXT4_BG_INODE_BITMAP_CSUM_HI_END)
gdp->bg_inode_bitmap_csum_hi = cpu_to_le16(csum >> 16);
}
int __ext4bf_handle_dirty_super(const char *where, unsigned int line,
handle_t *handle, struct super_block *sb)
{
struct buffer_head *bh = EXT4_SB(sb)->s_sbh;
int err = 0;
if (ext4bf_handle_valid(handle)) {
err = jbdbf_journal_dirty_metadata(handle, bh);
if (err)
ext4bf_journal_abort_handle(where, line, __func__,
bh, handle, err);
} else
sb->s_dirt = 1;
return err;
}
int __ext4_handle_dirty_metadata(const char *where, unsigned int line,
handle_t *handle, struct inode *inode,
struct buffer_head *bh)
{
int err = 0;
might_sleep();
set_buffer_meta(bh);
set_buffer_prio(bh);
if (ext4_handle_valid(handle)) {
err = jbd2_journal_dirty_metadata(handle, bh);
/* Errors can only happen if there is a bug */
if (WARN_ON_ONCE(err)) {
ext4_journal_abort_handle(where, line, __func__, bh,
handle, err);
ext4_error_inode(inode, where, line,
bh->b_blocknr,
"journal_dirty_metadata failed: "
"handle type %u started at line %u, "
"credits %u/%u, errcode %d",
handle->h_type,
handle->h_line_no,
handle->h_requested_credits,
handle->h_buffer_credits, err);
}
} else {
if (inode)
mark_buffer_dirty_inode(bh, inode);
else
mark_buffer_dirty(bh);
if (inode && inode_needs_sync(inode)) {
sync_dirty_buffer(bh);
if (buffer_req(bh) && !buffer_uptodate(bh)) {
struct ext4_super_block *es;
es = EXT4_SB(inode->i_sb)->s_es;
es->s_last_error_block =
cpu_to_le64(bh->b_blocknr);
ext4_error_inode(inode, where, line,
bh->b_blocknr,
"IO error syncing itable block");
err = -EIO;
}
}
}
return err;
}
static ssize_t
ext4_file_write(struct kiocb *iocb, const struct iovec *iov,
unsigned long nr_segs, loff_t pos)
{
struct inode *inode = iocb->ki_filp->f_path.dentry->d_inode;
int unaligned_aio = 0;
int ret;
trace_ext4_file_write(iocb->ki_filp->f_path.dentry, iocb->ki_left);
if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) {
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
size_t length = iov_length(iov, nr_segs);
if ((pos > sbi->s_bitmap_maxbytes ||
(pos == sbi->s_bitmap_maxbytes && length > 0)))
return -EFBIG;
if (pos + length > sbi->s_bitmap_maxbytes) {
nr_segs = iov_shorten((struct iovec *)iov, nr_segs,
sbi->s_bitmap_maxbytes - pos);
}
} else if (unlikely((iocb->ki_filp->f_flags & O_DIRECT) &&
!is_sync_kiocb(iocb))) {
unaligned_aio = ext4_unaligned_aio(inode, iov, nr_segs, pos);
}
if (unaligned_aio) {
static unsigned long unaligned_warn_time;
if (printk_timed_ratelimit(&unaligned_warn_time, 60*60*24*HZ))
ext4_msg(inode->i_sb, KERN_WARNING,
"Unaligned AIO/DIO on inode %ld by %s; "
"performance will be poor.",
inode->i_ino, current->comm);
mutex_lock(ext4_aio_mutex(inode));
ext4_aiodio_wait(inode);
}
ret = generic_file_aio_write(iocb, iov, nr_segs, pos);
if (unaligned_aio)
mutex_unlock(ext4_aio_mutex(inode));
return ret;
}
void ext4_block_bitmap_csum_set(struct super_block *sb, ext4_group_t group,
struct ext4_group_desc *gdp,
struct buffer_head *bh, int sz)
{
__u32 csum;
struct ext4_sb_info *sbi = EXT4_SB(sb);
if (!EXT4_HAS_RO_COMPAT_FEATURE(sb,
EXT4_FEATURE_RO_COMPAT_METADATA_CSUM))
return;
csum = ext4_chksum(sbi, sbi->s_csum_seed, (__u8 *)bh->b_data, sz);
gdp->bg_block_bitmap_csum_lo = cpu_to_le16(csum & 0xFFFF);
if (sbi->s_desc_size >= EXT4_BG_BLOCK_BITMAP_CSUM_HI_END)
gdp->bg_block_bitmap_csum_hi = cpu_to_le16(csum >> 16);
}
handle_t *__ext4_journal_start_sb(struct super_block *sb, unsigned int line,
int type, int blocks, int rsv_blocks)
{
journal_t *journal;
int err;
trace_ext4_journal_start(sb, blocks, rsv_blocks, _RET_IP_);
err = ext4_journal_check_start(sb);
if (err < 0)
return ERR_PTR(err);
journal = EXT4_SB(sb)->s_journal;
if (!journal)
return ext4_get_nojournal();
return jbd2__journal_start(journal, blocks, rsv_blocks, GFP_NOFS,
type, line);
}
static int ext4_shutdown(struct super_block *sb, unsigned long arg)
{
struct ext4_sb_info *sbi = EXT4_SB(sb);
__u32 flags;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
if (get_user(flags, (__u32 __user *)arg))
return -EFAULT;
if (flags > EXT4_GOING_FLAGS_NOLOGFLUSH)
return -EINVAL;
if (ext4_forced_shutdown(sbi))
return 0;
ext4_msg(sb, KERN_ALERT, "shut down requested (%d)", flags);
switch (flags) {
case EXT4_GOING_FLAGS_DEFAULT:
freeze_bdev(sb->s_bdev);
set_bit(EXT4_FLAGS_SHUTDOWN, &sbi->s_ext4_flags);
thaw_bdev(sb->s_bdev, sb);
break;
case EXT4_GOING_FLAGS_LOGFLUSH:
set_bit(EXT4_FLAGS_SHUTDOWN, &sbi->s_ext4_flags);
if (sbi->s_journal && !is_journal_aborted(sbi->s_journal)) {
(void) ext4_force_commit(sb);
jbd2_journal_abort(sbi->s_journal, 0);
}
break;
case EXT4_GOING_FLAGS_NOLOGFLUSH:
set_bit(EXT4_FLAGS_SHUTDOWN, &sbi->s_ext4_flags);
if (sbi->s_journal && !is_journal_aborted(sbi->s_journal)) {
msleep(100);
jbd2_journal_abort(sbi->s_journal, 0);
}
break;
default:
return -EINVAL;
}
clear_opt(sb, DISCARD);
return 0;
}
/*
* work on completed aio dio IO, to convert unwritten extents to extents
*/
static void ext4_end_io_work(struct work_struct *work)
{
ext4_io_end_t *io = container_of(work, ext4_io_end_t, work);
struct inode *inode = io->inode;
struct ext4_inode_info *ei = EXT4_I(inode);
unsigned long flags;
spin_lock_irqsave(&ei->i_completed_io_lock, flags);
if (io->flag & EXT4_IO_END_IN_FSYNC)
goto requeue;
if (list_empty(&io->list)) {
spin_unlock_irqrestore(&ei->i_completed_io_lock, flags);
goto free;
}
if (!mutex_trylock(&inode->i_mutex)) {
bool was_queued;
requeue:
was_queued = !!(io->flag & EXT4_IO_END_QUEUED);
io->flag |= EXT4_IO_END_QUEUED;
spin_unlock_irqrestore(&ei->i_completed_io_lock, flags);
/*
* Requeue the work instead of waiting so that the work
* items queued after this can be processed.
*/
queue_work(EXT4_SB(inode->i_sb)->dio_unwritten_wq, &io->work);
/*
* To prevent the ext4-dio-unwritten thread from keeping
* requeueing end_io requests and occupying cpu for too long,
* yield the cpu if it sees an end_io request that has already
* been requeued.
*/
if (was_queued)
yield();
return;
}
list_del_init(&io->list);
spin_unlock_irqrestore(&ei->i_completed_io_lock, flags);
(void) ext4_end_io_nolock(io);
mutex_unlock(&inode->i_mutex);
free:
ext4_free_io_end(io);
}
/*
* Wrappers for jbd2_journal_start/end.
*/
static int ext4_journal_check_start(struct super_block *sb)
{
journal_t *journal;
might_sleep();
if (sb->s_flags & MS_RDONLY)
return -EROFS;
WARN_ON(sb->s_writers.frozen == SB_FREEZE_COMPLETE);
journal = EXT4_SB(sb)->s_journal;
/*
* Special case here: if the journal has aborted behind our
* backs (eg. EIO in the commit thread), then we still need to
* take the FS itself readonly cleanly.
*/
if (journal && is_journal_aborted(journal)) {
ext4_abort(sb, "Detected aborted journal");
return -EROFS;
}
return 0;
}
static int ext4_file_open(struct inode * inode, struct file * filp)
{
struct super_block *sb = inode->i_sb;
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
struct ext4_inode_info *ei = EXT4_I(inode);
struct vfsmount *mnt = filp->f_path.mnt;
struct path path;
char buf[64], *cp;
if (unlikely(!(sbi->s_mount_flags & EXT4_MF_MNTDIR_SAMPLED) &&
!(sb->s_flags & MS_RDONLY))) {
sbi->s_mount_flags |= EXT4_MF_MNTDIR_SAMPLED;
memset(buf, 0, sizeof(buf));
path.mnt = mnt;
path.dentry = mnt->mnt_root;
cp = d_path(&path, buf, sizeof(buf));
if (!IS_ERR(cp)) {
strlcpy(sbi->s_es->s_last_mounted, cp,
sizeof(sbi->s_es->s_last_mounted));
ext4_mark_super_dirty(sb);
}
}
if (sbi->s_journal && !ei->jinode && (filp->f_mode & FMODE_WRITE)) {
struct jbd2_inode *jinode = jbd2_alloc_inode(GFP_KERNEL);
spin_lock(&inode->i_lock);
if (!ei->jinode) {
if (!jinode) {
spin_unlock(&inode->i_lock);
return -ENOMEM;
}
ei->jinode = jinode;
jbd2_journal_init_jbd_inode(ei->jinode, inode);
jinode = NULL;
}
spin_unlock(&inode->i_lock);
if (unlikely(jinode != NULL))
jbd2_free_inode(jinode);
}
return dquot_file_open(inode, filp);
}
int ext4_inode_bitmap_csum_verify(struct super_block *sb, ext4_group_t group,
struct ext4_group_desc *gdp,
struct buffer_head *bh, int sz)
{
__u32 hi;
__u32 provided, calculated;
struct ext4_sb_info *sbi = EXT4_SB(sb);
if (!ext4_has_metadata_csum(sb))
return 1;
provided = le16_to_cpu(gdp->bg_inode_bitmap_csum_lo);
calculated = ext4_chksum(sbi, sbi->s_csum_seed, (__u8 *)bh->b_data, sz);
if (sbi->s_desc_size >= EXT4_BG_INODE_BITMAP_CSUM_HI_END) {
hi = le16_to_cpu(gdp->bg_inode_bitmap_csum_hi);
provided |= (hi << 16);
} else
calculated &= 0xFFFF;
return provided == calculated;
}
int __ext4_handle_dirty_super(const char *where, unsigned int line,
handle_t *handle, struct super_block *sb,
int now)
{
struct buffer_head *bh = EXT4_SB(sb)->s_sbh;
int err = 0;
if (ext4_handle_valid(handle)) {
ext4_superblock_csum_set(sb,
(struct ext4_super_block *)bh->b_data);
err = jbd2_journal_dirty_metadata(handle, bh);
if (err)
ext4_journal_abort_handle(where, line, __func__,
bh, handle, err);
} else if (now) {
ext4_superblock_csum_set(sb,
(struct ext4_super_block *)bh->b_data);
mark_buffer_dirty(bh);
} else
sb->s_dirt = 1;
return err;
}
int __ext4_handle_dirty_metadata(const char *where, unsigned int line,
handle_t *handle, struct inode *inode,
struct buffer_head *bh)
{
int err = 0;
might_sleep();
set_buffer_meta(bh);
set_buffer_prio(bh);
if (ext4_handle_valid(handle)) {
err = jbd2_journal_dirty_metadata(handle, bh);
if (err) {
/* Errors can only happen if there is a bug */
handle->h_err = err;
__ext4_journal_stop(where, line, handle);
}
} else {
if (inode)
mark_buffer_dirty_inode(bh, inode);
else
mark_buffer_dirty(bh);
if (inode && inode_needs_sync(inode)) {
sync_dirty_buffer(bh);
if (buffer_req(bh) && !buffer_uptodate(bh)) {
struct ext4_super_block *es;
es = EXT4_SB(inode->i_sb)->s_es;
es->s_last_error_block =
cpu_to_le64(bh->b_blocknr);
ext4_error_inode(inode, where, line,
bh->b_blocknr,
"IO error syncing itable block");
err = -EIO;
}
}
}
return err;
}
/*
* write the buffer to the inline inode.
* If 'create' is set, we don't need to do the extra copy in the xattr
* value since it is already handled by ext4_xattr_ibody_inline_set.
* That saves us one memcpy.
*/
static void ext4_write_inline_data(struct inode *inode, struct ext4_iloc *iloc,
void *buffer, loff_t pos, unsigned int len)
{
struct ext4_xattr_entry *entry;
struct ext4_xattr_ibody_header *header;
struct ext4_inode *raw_inode;
int cp_len = 0;
if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))
return;
BUG_ON(!EXT4_I(inode)->i_inline_off);
BUG_ON(pos + len > EXT4_I(inode)->i_inline_size);
raw_inode = ext4_raw_inode(iloc);
buffer += pos;
if (pos < EXT4_MIN_INLINE_DATA_SIZE) {
cp_len = pos + len > EXT4_MIN_INLINE_DATA_SIZE ?
EXT4_MIN_INLINE_DATA_SIZE - pos : len;
memcpy((void *)raw_inode->i_block + pos, buffer, cp_len);
len -= cp_len;
buffer += cp_len;
pos += cp_len;
}
if (!len)
return;
pos -= EXT4_MIN_INLINE_DATA_SIZE;
header = IHDR(inode, raw_inode);
entry = (struct ext4_xattr_entry *)((void *)raw_inode +
EXT4_I(inode)->i_inline_off);
memcpy((void *)IFIRST(header) + le16_to_cpu(entry->e_value_offs) + pos,
buffer, len);
}
/*
* ext4_llseek() copied from generic_file_llseek() to handle both
* block-mapped and extent-mapped maxbytes values. This should
* otherwise be identical with generic_file_llseek().
*/
loff_t ext4_llseek(struct file *file, loff_t offset, int origin)
{
struct inode *inode = file->f_mapping->host;
loff_t maxbytes;
if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)))
maxbytes = EXT4_SB(inode->i_sb)->s_bitmap_maxbytes;
else
maxbytes = inode->i_sb->s_maxbytes;
mutex_lock(&inode->i_mutex);
switch (origin) {
case SEEK_END:
offset += inode->i_size;
break;
case SEEK_CUR:
if (offset == 0) {
mutex_unlock(&inode->i_mutex);
return file->f_pos;
}
offset += file->f_pos;
break;
}
if (offset < 0 || offset > maxbytes) {
mutex_unlock(&inode->i_mutex);
return -EINVAL;
}
if (offset != file->f_pos) {
file->f_pos = offset;
file->f_version = 0;
}
mutex_unlock(&inode->i_mutex);
return offset;
}
/**
* ext4_get_group_desc() -- load group descriptor from disk
* @sb: super block
* @block_group: given block group
* @bh: pointer to the buffer head to store the block
* group descriptor
*/
struct ext4_group_desc * ext4_get_group_desc(struct super_block *sb,
ext4_group_t block_group,
struct buffer_head **bh)
{
unsigned int group_desc;
unsigned int offset;
ext4_group_t ngroups = ext4_get_groups_count(sb);
struct ext4_group_desc *desc;
struct ext4_sb_info *sbi = EXT4_SB(sb);
if (block_group >= ngroups) {
ext4_error(sb, "ext4_get_group_desc",
"block_group >= groups_count - "
"block_group = %u, groups_count = %u",
block_group, ngroups);
return NULL;
}
group_desc = block_group >> EXT4_DESC_PER_BLOCK_BITS(sb);
offset = block_group & (EXT4_DESC_PER_BLOCK(sb) - 1);
if (!sbi->s_group_desc[group_desc]) {
ext4_error(sb, "ext4_get_group_desc",
"Group descriptor not loaded - "
"block_group = %u, group_desc = %u, desc = %u",
block_group, group_desc, offset);
return NULL;
}
desc = (struct ext4_group_desc *)(
(__u8 *)sbi->s_group_desc[group_desc]->b_data +
offset * EXT4_DESC_SIZE(sb));
if (bh)
*bh = sbi->s_group_desc[group_desc];
return desc;
}
/**
* Swap the information from the given @inode and the inode
* EXT4_BOOT_LOADER_INO. It will basically swap i_data and all other
* important fields of the inodes.
*
* @sb: the super block of the filesystem
* @inode: the inode to swap with EXT4_BOOT_LOADER_INO
*
*/
static long swap_inode_boot_loader(struct super_block *sb,
struct inode *inode)
{
handle_t *handle;
int err;
struct inode *inode_bl;
struct ext4_inode_info *ei_bl;
struct ext4_sb_info *sbi = EXT4_SB(sb);
if (inode->i_nlink != 1 || !S_ISREG(inode->i_mode)) {
err = -EINVAL;
goto swap_boot_out;
}
if (!inode_owner_or_capable(inode) || !capable(CAP_SYS_ADMIN)) {
err = -EPERM;
goto swap_boot_out;
}
inode_bl = ext4_iget(sb, EXT4_BOOT_LOADER_INO);
if (IS_ERR(inode_bl)) {
err = PTR_ERR(inode_bl);
goto swap_boot_out;
}
ei_bl = EXT4_I(inode_bl);
filemap_flush(inode->i_mapping);
filemap_flush(inode_bl->i_mapping);
/* Protect orig inodes against a truncate and make sure,
* that only 1 swap_inode_boot_loader is running. */
lock_two_nondirectories(inode, inode_bl);
truncate_inode_pages(&inode->i_data, 0);
truncate_inode_pages(&inode_bl->i_data, 0);
/* Wait for all existing dio workers */
ext4_inode_block_unlocked_dio(inode);
ext4_inode_block_unlocked_dio(inode_bl);
inode_dio_wait(inode);
inode_dio_wait(inode_bl);
handle = ext4_journal_start(inode_bl, EXT4_HT_MOVE_EXTENTS, 2);
if (IS_ERR(handle)) {
err = -EINVAL;
goto journal_err_out;
}
/* Protect extent tree against block allocations via delalloc */
ext4_double_down_write_data_sem(inode, inode_bl);
if (inode_bl->i_nlink == 0) {
/* this inode has never been used as a BOOT_LOADER */
set_nlink(inode_bl, 1);
i_uid_write(inode_bl, 0);
i_gid_write(inode_bl, 0);
inode_bl->i_flags = 0;
ei_bl->i_flags = 0;
inode_bl->i_version = 1;
i_size_write(inode_bl, 0);
inode_bl->i_mode = S_IFREG;
if (EXT4_HAS_INCOMPAT_FEATURE(sb,
EXT4_FEATURE_INCOMPAT_EXTENTS)) {
ext4_set_inode_flag(inode_bl, EXT4_INODE_EXTENTS);
ext4_ext_tree_init(handle, inode_bl);
} else
memset(ei_bl->i_data, 0, sizeof(ei_bl->i_data));
}
swap_inode_data(inode, inode_bl);
inode->i_ctime = inode_bl->i_ctime = ext4_current_time(inode);
spin_lock(&sbi->s_next_gen_lock);
inode->i_generation = sbi->s_next_generation++;
inode_bl->i_generation = sbi->s_next_generation++;
spin_unlock(&sbi->s_next_gen_lock);
ext4_discard_preallocations(inode);
err = ext4_mark_inode_dirty(handle, inode);
if (err < 0) {
ext4_warning(inode->i_sb,
"couldn't mark inode #%lu dirty (err %d)",
inode->i_ino, err);
/* Revert all changes: */
swap_inode_data(inode, inode_bl);
} else {
err = ext4_mark_inode_dirty(handle, inode_bl);
if (err < 0) {
ext4_warning(inode_bl->i_sb,
"couldn't mark inode #%lu dirty (err %d)",
inode_bl->i_ino, err);
/* Revert all changes: */
swap_inode_data(inode, inode_bl);
ext4_mark_inode_dirty(handle, inode);
}
}
ext4_journal_stop(handle);
ext4_double_up_write_data_sem(inode, inode_bl);
journal_err_out:
ext4_inode_resume_unlocked_dio(inode);
ext4_inode_resume_unlocked_dio(inode_bl);
unlock_two_nondirectories(inode, inode_bl);
iput(inode_bl);
swap_boot_out:
return err;
}
long ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
{
struct inode *inode = file_inode(filp);
struct super_block *sb = inode->i_sb;
struct ext4_inode_info *ei = EXT4_I(inode);
unsigned int flags;
ext4_debug("cmd = %u, arg = %lu\n", cmd, arg);
switch (cmd) {
case EXT4_IOC_GETFLAGS:
ext4_get_inode_flags(ei);
flags = ei->i_flags & EXT4_FL_USER_VISIBLE;
return put_user(flags, (int __user *) arg);
case EXT4_IOC_SETFLAGS: {
handle_t *handle = NULL;
int err, migrate = 0;
struct ext4_iloc iloc;
unsigned int oldflags, mask, i;
unsigned int jflag;
if (!inode_owner_or_capable(inode))
return -EACCES;
if (get_user(flags, (int __user *) arg))
return -EFAULT;
err = mnt_want_write_file(filp);
if (err)
return err;
flags = ext4_mask_flags(inode->i_mode, flags);
err = -EPERM;
mutex_lock(&inode->i_mutex);
/* Is it quota file? Do not allow user to mess with it */
if (IS_NOQUOTA(inode))
goto flags_out;
oldflags = ei->i_flags;
/* The JOURNAL_DATA flag is modifiable only by root */
jflag = flags & EXT4_JOURNAL_DATA_FL;
/*
* The IMMUTABLE and APPEND_ONLY flags can only be changed by
* the relevant capability.
*
* This test looks nicer. Thanks to Pauline Middelink
*/
if ((flags ^ oldflags) & (EXT4_APPEND_FL | EXT4_IMMUTABLE_FL)) {
if (!capable(CAP_LINUX_IMMUTABLE))
goto flags_out;
}
/*
* The JOURNAL_DATA flag can only be changed by
* the relevant capability.
*/
if ((jflag ^ oldflags) & (EXT4_JOURNAL_DATA_FL)) {
if (!capable(CAP_SYS_RESOURCE))
goto flags_out;
}
if ((flags ^ oldflags) & EXT4_EXTENTS_FL)
migrate = 1;
if (flags & EXT4_EOFBLOCKS_FL) {
/* we don't support adding EOFBLOCKS flag */
if (!(oldflags & EXT4_EOFBLOCKS_FL)) {
err = -EOPNOTSUPP;
goto flags_out;
}
} else if (oldflags & EXT4_EOFBLOCKS_FL)
ext4_truncate(inode);
handle = ext4_journal_start(inode, EXT4_HT_INODE, 1);
if (IS_ERR(handle)) {
err = PTR_ERR(handle);
goto flags_out;
}
if (IS_SYNC(inode))
ext4_handle_sync(handle);
err = ext4_reserve_inode_write(handle, inode, &iloc);
if (err)
goto flags_err;
for (i = 0, mask = 1; i < 32; i++, mask <<= 1) {
if (!(mask & EXT4_FL_USER_MODIFIABLE))
continue;
if (mask & flags)
ext4_set_inode_flag(inode, i);
else
ext4_clear_inode_flag(inode, i);
}
ext4_set_inode_flags(inode);
inode->i_ctime = ext4_current_time(inode);
err = ext4_mark_iloc_dirty(handle, inode, &iloc);
flags_err:
ext4_journal_stop(handle);
if (err)
goto flags_out;
if ((jflag ^ oldflags) & (EXT4_JOURNAL_DATA_FL))
err = ext4_change_inode_journal_flag(inode, jflag);
if (err)
goto flags_out;
if (migrate) {
if (flags & EXT4_EXTENTS_FL)
err = ext4_ext_migrate(inode);
else
err = ext4_ind_migrate(inode);
}
flags_out:
mutex_unlock(&inode->i_mutex);
mnt_drop_write_file(filp);
return err;
}
case EXT4_IOC_GETVERSION:
case EXT4_IOC_GETVERSION_OLD:
return put_user(inode->i_generation, (int __user *) arg);
case EXT4_IOC_SETVERSION:
case EXT4_IOC_SETVERSION_OLD: {
handle_t *handle;
struct ext4_iloc iloc;
__u32 generation;
int err;
if (!inode_owner_or_capable(inode))
return -EPERM;
if (ext4_has_metadata_csum(inode->i_sb)) {
ext4_warning(sb, "Setting inode version is not "
"supported with metadata_csum enabled.");
return -ENOTTY;
}
err = mnt_want_write_file(filp);
if (err)
return err;
if (get_user(generation, (int __user *) arg)) {
err = -EFAULT;
goto setversion_out;
}
mutex_lock(&inode->i_mutex);
handle = ext4_journal_start(inode, EXT4_HT_INODE, 1);
if (IS_ERR(handle)) {
err = PTR_ERR(handle);
goto unlock_out;
}
err = ext4_reserve_inode_write(handle, inode, &iloc);
if (err == 0) {
inode->i_ctime = ext4_current_time(inode);
inode->i_generation = generation;
err = ext4_mark_iloc_dirty(handle, inode, &iloc);
}
ext4_journal_stop(handle);
unlock_out:
mutex_unlock(&inode->i_mutex);
setversion_out:
mnt_drop_write_file(filp);
return err;
}
case EXT4_IOC_GROUP_EXTEND: {
ext4_fsblk_t n_blocks_count;
int err, err2=0;
err = ext4_resize_begin(sb);
if (err)
return err;
if (get_user(n_blocks_count, (__u32 __user *)arg)) {
err = -EFAULT;
goto group_extend_out;
}
if (EXT4_HAS_RO_COMPAT_FEATURE(sb,
EXT4_FEATURE_RO_COMPAT_BIGALLOC)) {
ext4_msg(sb, KERN_ERR,
"Online resizing not supported with bigalloc");
err = -EOPNOTSUPP;
goto group_extend_out;
}
err = mnt_want_write_file(filp);
if (err)
goto group_extend_out;
err = ext4_group_extend(sb, EXT4_SB(sb)->s_es, n_blocks_count);
if (EXT4_SB(sb)->s_journal) {
jbd2_journal_lock_updates(EXT4_SB(sb)->s_journal);
err2 = jbd2_journal_flush(EXT4_SB(sb)->s_journal);
jbd2_journal_unlock_updates(EXT4_SB(sb)->s_journal);
}
if (err == 0)
err = err2;
mnt_drop_write_file(filp);
group_extend_out:
ext4_resize_end(sb);
return err;
}
case EXT4_IOC_MOVE_EXT: {
struct move_extent me;
struct fd donor;
int err;
if (!(filp->f_mode & FMODE_READ) ||
!(filp->f_mode & FMODE_WRITE))
return -EBADF;
if (copy_from_user(&me,
(struct move_extent __user *)arg, sizeof(me)))
return -EFAULT;
me.moved_len = 0;
donor = fdget(me.donor_fd);
if (!donor.file)
return -EBADF;
if (!(donor.file->f_mode & FMODE_WRITE)) {
err = -EBADF;
goto mext_out;
}
if (EXT4_HAS_RO_COMPAT_FEATURE(sb,
EXT4_FEATURE_RO_COMPAT_BIGALLOC)) {
ext4_msg(sb, KERN_ERR,
"Online defrag not supported with bigalloc");
err = -EOPNOTSUPP;
goto mext_out;
}
err = mnt_want_write_file(filp);
if (err)
goto mext_out;
err = ext4_move_extents(filp, donor.file, me.orig_start,
me.donor_start, me.len, &me.moved_len);
mnt_drop_write_file(filp);
if (copy_to_user((struct move_extent __user *)arg,
&me, sizeof(me)))
err = -EFAULT;
mext_out:
fdput(donor);
return err;
}
case EXT4_IOC_GROUP_ADD: {
struct ext4_new_group_data input;
int err, err2=0;
err = ext4_resize_begin(sb);
if (err)
return err;
if (copy_from_user(&input, (struct ext4_new_group_input __user *)arg,
sizeof(input))) {
err = -EFAULT;
goto group_add_out;
}
if (EXT4_HAS_RO_COMPAT_FEATURE(sb,
EXT4_FEATURE_RO_COMPAT_BIGALLOC)) {
ext4_msg(sb, KERN_ERR,
"Online resizing not supported with bigalloc");
err = -EOPNOTSUPP;
goto group_add_out;
}
err = mnt_want_write_file(filp);
if (err)
goto group_add_out;
err = ext4_group_add(sb, &input);
if (EXT4_SB(sb)->s_journal) {
jbd2_journal_lock_updates(EXT4_SB(sb)->s_journal);
err2 = jbd2_journal_flush(EXT4_SB(sb)->s_journal);
jbd2_journal_unlock_updates(EXT4_SB(sb)->s_journal);
}
if (err == 0)
err = err2;
mnt_drop_write_file(filp);
if (!err && ext4_has_group_desc_csum(sb) &&
test_opt(sb, INIT_INODE_TABLE))
err = ext4_register_li_request(sb, input.group);
group_add_out:
ext4_resize_end(sb);
return err;
}
case EXT4_IOC_MIGRATE:
{
int err;
if (!inode_owner_or_capable(inode))
return -EACCES;
err = mnt_want_write_file(filp);
if (err)
return err;
/*
* inode_mutex prevent write and truncate on the file.
* Read still goes through. We take i_data_sem in
* ext4_ext_swap_inode_data before we switch the
* inode format to prevent read.
*/
mutex_lock(&(inode->i_mutex));
err = ext4_ext_migrate(inode);
mutex_unlock(&(inode->i_mutex));
mnt_drop_write_file(filp);
return err;
}
case EXT4_IOC_ALLOC_DA_BLKS:
{
int err;
if (!inode_owner_or_capable(inode))
return -EACCES;
err = mnt_want_write_file(filp);
if (err)
return err;
err = ext4_alloc_da_blocks(inode);
mnt_drop_write_file(filp);
return err;
}
case EXT4_IOC_SWAP_BOOT:
{
int err;
if (!(filp->f_mode & FMODE_WRITE))
return -EBADF;
err = mnt_want_write_file(filp);
if (err)
return err;
err = swap_inode_boot_loader(sb, inode);
mnt_drop_write_file(filp);
return err;
}
case EXT4_IOC_RESIZE_FS: {
ext4_fsblk_t n_blocks_count;
int err = 0, err2 = 0;
ext4_group_t o_group = EXT4_SB(sb)->s_groups_count;
if (EXT4_HAS_RO_COMPAT_FEATURE(sb,
EXT4_FEATURE_RO_COMPAT_BIGALLOC)) {
ext4_msg(sb, KERN_ERR,
"Online resizing not (yet) supported with bigalloc");
return -EOPNOTSUPP;
}
if (copy_from_user(&n_blocks_count, (__u64 __user *)arg,
sizeof(__u64))) {
return -EFAULT;
}
err = ext4_resize_begin(sb);
if (err)
return err;
err = mnt_want_write_file(filp);
if (err)
goto resizefs_out;
err = ext4_resize_fs(sb, n_blocks_count);
if (EXT4_SB(sb)->s_journal) {
jbd2_journal_lock_updates(EXT4_SB(sb)->s_journal);
err2 = jbd2_journal_flush(EXT4_SB(sb)->s_journal);
jbd2_journal_unlock_updates(EXT4_SB(sb)->s_journal);
}
if (err == 0)
err = err2;
mnt_drop_write_file(filp);
if (!err && (o_group > EXT4_SB(sb)->s_groups_count) &&
ext4_has_group_desc_csum(sb) &&
test_opt(sb, INIT_INODE_TABLE))
err = ext4_register_li_request(sb, o_group);
resizefs_out:
ext4_resize_end(sb);
return err;
}
case FIDTRIM:
case FITRIM:
{
struct request_queue *q = bdev_get_queue(sb->s_bdev);
struct fstrim_range range;
int ret = 0;
int flags = cmd == FIDTRIM ? BLKDEV_DISCARD_SECURE : 0;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
if (!blk_queue_discard(q))
return -EOPNOTSUPP;
if ((flags & BLKDEV_DISCARD_SECURE) && !blk_queue_secdiscard(q))
return -EOPNOTSUPP;
if (copy_from_user(&range, (struct fstrim_range __user *)arg,
sizeof(range)))
return -EFAULT;
range.minlen = max((unsigned int)range.minlen,
q->limits.discard_granularity);
ret = ext4_trim_fs(sb, &range, flags);
if (ret < 0)
return ret;
if (copy_to_user((struct fstrim_range __user *)arg, &range,
sizeof(range)))
return -EFAULT;
return 0;
}
case EXT4_IOC_PRECACHE_EXTENTS:
return ext4_ext_precache(inode);
default:
return -ENOTTY;
}
}
static unsigned long ext4_bg_num_gdb_nometa(struct super_block *sb,
ext4_group_t group)
{
return ext4_bg_has_super(sb, group) ? EXT4_SB(sb)->s_gdb_count : 0;
}
/* 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);
}
/**
* ext4_add_groupblocks() -- Add given blocks to an existing group
* @handle: handle to this transaction
* @sb: super block
* @block: start physcial block to add to the block group
* @count: number of blocks to free
*
* This marks the blocks as free in the bitmap. We ask the
* mballoc to reload the buddy after this by setting group
* EXT4_GROUP_INFO_NEED_INIT_BIT flag
*/
void ext4_add_groupblocks(handle_t *handle, struct super_block *sb,
ext4_fsblk_t block, unsigned long count)
{
struct buffer_head *bitmap_bh = NULL;
struct buffer_head *gd_bh;
ext4_group_t block_group;
ext4_grpblk_t bit;
unsigned int i;
struct ext4_group_desc *desc;
struct ext4_sb_info *sbi = EXT4_SB(sb);
int err = 0, ret, blk_free_count;
ext4_grpblk_t blocks_freed;
struct ext4_group_info *grp;
ext4_debug("Adding block(s) %llu-%llu\n", block, block + count - 1);
ext4_get_group_no_and_offset(sb, block, &block_group, &bit);
grp = ext4_get_group_info(sb, block_group);
/*
* Check to see if we are freeing blocks across a group
* boundary.
*/
if (bit + count > EXT4_BLOCKS_PER_GROUP(sb)) {
goto error_return;
}
bitmap_bh = ext4_read_block_bitmap(sb, block_group);
if (!bitmap_bh)
goto error_return;
desc = ext4_get_group_desc(sb, block_group, &gd_bh);
if (!desc)
goto error_return;
if (in_range(ext4_block_bitmap(sb, desc), block, count) ||
in_range(ext4_inode_bitmap(sb, desc), block, count) ||
in_range(block, ext4_inode_table(sb, desc), sbi->s_itb_per_group) ||
in_range(block + count - 1, ext4_inode_table(sb, desc),
sbi->s_itb_per_group)) {
ext4_error(sb, __func__,
"Adding blocks in system zones - "
"Block = %llu, count = %lu",
block, count);
goto error_return;
}
/*
* We are about to add blocks to the bitmap,
* so we need undo access.
*/
BUFFER_TRACE(bitmap_bh, "getting undo access");
err = ext4_journal_get_undo_access(handle, bitmap_bh);
if (err)
goto error_return;
/*
* We are about to modify some metadata. Call the journal APIs
* to unshare ->b_data if a currently-committing transaction is
* using it
*/
BUFFER_TRACE(gd_bh, "get_write_access");
err = ext4_journal_get_write_access(handle, gd_bh);
if (err)
goto error_return;
/*
* make sure we don't allow a parallel init on other groups in the
* same buddy cache
*/
down_write(&grp->alloc_sem);
for (i = 0, blocks_freed = 0; i < count; i++) {
BUFFER_TRACE(bitmap_bh, "clear bit");
if (!ext4_clear_bit_atomic(ext4_group_lock_ptr(sb, block_group),
bit + i, bitmap_bh->b_data)) {
ext4_error(sb, __func__,
"bit already cleared for block %llu",
(ext4_fsblk_t)(block + i));
BUFFER_TRACE(bitmap_bh, "bit already cleared");
} else {
blocks_freed++;
}
}
ext4_lock_group(sb, block_group);
blk_free_count = blocks_freed + ext4_free_blks_count(sb, desc);
ext4_free_blks_set(sb, desc, blk_free_count);
desc->bg_checksum = ext4_group_desc_csum(sbi, block_group, desc);
ext4_unlock_group(sb, block_group);
percpu_counter_mod(&sbi->s_freeblocks_counter, blocks_freed);
if (sbi->s_log_groups_per_flex) {
ext4_group_t flex_group = ext4_flex_group(sbi, block_group);
atomic_add(blocks_freed,
&sbi->s_flex_groups[flex_group].free_blocks);
}
/*
* request to reload the buddy with the
* new bitmap information
*/
set_bit(EXT4_GROUP_INFO_NEED_INIT_BIT, &(grp->bb_state));
grp->bb_free += blocks_freed;
up_write(&grp->alloc_sem);
/* We dirtied the bitmap block */
BUFFER_TRACE(bitmap_bh, "dirtied bitmap block");
err = ext4_handle_dirty_metadata(handle, NULL, bitmap_bh);
/* And the group descriptor block */
BUFFER_TRACE(gd_bh, "dirtied group descriptor block");
ret = ext4_handle_dirty_metadata(handle, NULL, gd_bh);
if (!err)
err = ret;
error_return:
brelse(bitmap_bh);
ext4_std_error(sb, err);
return;
}
int ext4_sync_file(struct file *file, struct dentry *dentry, int datasync)
{
struct inode *inode = dentry->d_inode;
struct ext4_inode_info *ei = EXT4_I(inode);
journal_t *journal = EXT4_SB(inode->i_sb)->s_journal;
int ret;
tid_t commit_tid;
J_ASSERT(ext4_journal_current_handle() == NULL);
trace_ext4_sync_file(file, dentry, datasync);
if (inode->i_sb->s_flags & MS_RDONLY)
return 0;
ret = flush_completed_IO(inode);
if (ret < 0)
return ret;
if (!journal) {
ret = simple_fsync(file, dentry, datasync);
if (!ret && !list_empty(&inode->i_dentry))
ext4_sync_parent(inode);
return ret;
}
/*
* data=writeback,ordered:
* The caller's filemap_fdatawrite()/wait will sync the data.
* Metadata is in the journal, we wait for proper transaction to
* commit here.
*
* data=journal:
* filemap_fdatawrite won't do anything (the buffers are clean).
* ext4_force_commit will write the file data into the journal and
* will wait on that.
* filemap_fdatawait() will encounter a ton of newly-dirtied pages
* (they were dirtied by commit). But that's OK - the blocks are
* safe in-journal, which is all fsync() needs to ensure.
*/
if (ext4_should_journal_data(inode))
return ext4_force_commit(inode->i_sb);
commit_tid = datasync ? ei->i_datasync_tid : ei->i_sync_tid;
if (jbd2_log_start_commit(journal, commit_tid)) {
/*
* When the journal is on a different device than the
* fs data disk, we need to issue the barrier in
* writeback mode. (In ordered mode, the jbd2 layer
* will take care of issuing the barrier. In
* data=journal, all of the data blocks are written to
* the journal device.)
*/
if (ext4_should_writeback_data(inode) &&
(journal->j_fs_dev != journal->j_dev) &&
(journal->j_flags & JBD2_BARRIER))
blkdev_issue_flush(inode->i_sb->s_bdev, NULL);
ret = jbd2_log_wait_commit(journal, commit_tid);
} else if (journal->j_flags & JBD2_BARRIER)
blkdev_issue_flush(inode->i_sb->s_bdev, NULL);
return ret;
}
