/*
* Write the MMP block using WRITE_SYNC to try to get the block on-disk
* faster.
*/
static int write_mmp_block(struct super_block *sb, struct buffer_head *bh)
{
struct mmp_struct *mmp = (struct mmp_struct *)(bh->b_data);
/*
* We protect against freezing so that we don't create dirty buffers
* on frozen filesystem.
*/
sb_start_write(sb);
ext4_mmp_csum_set(sb, mmp);
mark_buffer_dirty(bh);
lock_buffer(bh);
bh->b_end_io = end_buffer_write_sync;
get_bh(bh);
#ifdef FEATURE_STORAGE_META_LOG
if( bh && bh->b_bdev && bh->b_bdev->bd_disk)
set_metadata_rw_status(bh->b_bdev->bd_disk->first_minor, WAIT_WRITE_CNT);
#endif
submit_bh(WRITE_SYNC | REQ_META | REQ_PRIO, bh);
wait_on_buffer(bh);
sb_end_write(sb);
if (unlikely(!buffer_uptodate(bh)))
return 1;
return 0;
}
/* cf. open.c:do_sys_truncate() and do_sys_ftruncate() */
int vfsub_trunc(struct path *h_path, loff_t length, unsigned int attr,
struct file *h_file)
{
int err;
struct inode *h_inode;
struct super_block *h_sb;
if (!h_file) {
err = vfsub_truncate(h_path, length);
goto out;
}
h_inode = h_path->dentry->d_inode;
h_sb = h_inode->i_sb;
lockdep_off();
sb_start_write(h_sb);
lockdep_on();
err = locks_verify_truncate(h_inode, h_file, length);
if (!err)
err = security_path_truncate(h_path);
if (!err) {
lockdep_off();
err = do_truncate(h_path->dentry, length, attr, h_file);
lockdep_on();
}
lockdep_off();
sb_end_write(h_sb);
lockdep_on();
out:
return err;
}
int do_fallocate(struct file *file, int mode, loff_t offset, loff_t len)
{
struct inode *inode = file_inode(file);
long ret;
if (offset < 0 || len <= 0)
return -EINVAL;
/* Return error if mode is not supported */
if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE))
return -EOPNOTSUPP;
/* Punch hole must have keep size set */
if ((mode & FALLOC_FL_PUNCH_HOLE) &&
!(mode & FALLOC_FL_KEEP_SIZE))
return -EOPNOTSUPP;
if (!(file->f_mode & FMODE_WRITE))
return -EBADF;
/* It's not possible punch hole on append only file */
if (mode & FALLOC_FL_PUNCH_HOLE && IS_APPEND(inode))
return -EPERM;
if (IS_IMMUTABLE(inode))
return -EPERM;
/*
* Revalidate the write permissions, in case security policy has
* changed since the files were opened.
*/
ret = security_file_permission(file, MAY_WRITE);
if (ret)
return ret;
if (S_ISFIFO(inode->i_mode))
return -ESPIPE;
/*
* Let individual file system decide if it supports preallocation
* for directories or not.
*/
if (!S_ISREG(inode->i_mode) && !S_ISDIR(inode->i_mode))
return -ENODEV;
/* Check for wrap through zero too */
if (((offset + len) > inode->i_sb->s_maxbytes) || ((offset + len) < 0))
return -EFBIG;
if (!file->f_op->fallocate)
return -EOPNOTSUPP;
sb_start_write(inode->i_sb);
ret = file->f_op->fallocate(file, mode, offset, len);
sb_end_write(inode->i_sb);
return ret;
}
int gfs2_statfs_sync(struct super_block *sb, int type)
{
struct gfs2_sbd *sdp = sb->s_fs_info;
struct gfs2_inode *m_ip = GFS2_I(sdp->sd_statfs_inode);
struct gfs2_inode *l_ip = GFS2_I(sdp->sd_sc_inode);
struct gfs2_statfs_change_host *m_sc = &sdp->sd_statfs_master;
struct gfs2_statfs_change_host *l_sc = &sdp->sd_statfs_local;
struct gfs2_holder gh;
struct buffer_head *m_bh, *l_bh;
int error;
sb_start_write(sb);
error = gfs2_glock_nq_init(m_ip->i_gl, LM_ST_EXCLUSIVE, GL_NOCACHE,
&gh);
if (error)
goto out;
error = gfs2_meta_inode_buffer(m_ip, &m_bh);
if (error)
goto out_unlock;
spin_lock(&sdp->sd_statfs_spin);
gfs2_statfs_change_in(m_sc, m_bh->b_data +
sizeof(struct gfs2_dinode));
if (!l_sc->sc_total && !l_sc->sc_free && !l_sc->sc_dinodes) {
spin_unlock(&sdp->sd_statfs_spin);
goto out_bh;
}
spin_unlock(&sdp->sd_statfs_spin);
error = gfs2_meta_inode_buffer(l_ip, &l_bh);
if (error)
goto out_bh;
error = gfs2_trans_begin(sdp, 2 * RES_DINODE, 0);
if (error)
goto out_bh2;
update_statfs(sdp, m_bh, l_bh);
sdp->sd_statfs_force_sync = 0;
gfs2_trans_end(sdp);
out_bh2:
brelse(l_bh);
out_bh:
brelse(m_bh);
out_unlock:
gfs2_glock_dq_uninit(&gh);
out:
sb_end_write(sb);
return error;
}
STATIC ssize_t
xfs_file_aio_write(
struct kiocb *iocb,
const struct iovec *iovp,
unsigned long nr_segs,
loff_t pos)
{
struct file *file = iocb->ki_filp;
struct address_space *mapping = file->f_mapping;
struct inode *inode = mapping->host;
struct xfs_inode *ip = XFS_I(inode);
ssize_t ret;
size_t ocount = 0;
XFS_STATS_INC(xs_write_calls);
BUG_ON(iocb->ki_pos != pos);
ret = generic_segment_checks(iovp, &nr_segs, &ocount, VERIFY_READ);
if (ret)
return ret;
if (ocount == 0)
return 0;
sb_start_write(inode->i_sb);
if (XFS_FORCED_SHUTDOWN(ip->i_mount)) {
ret = -EIO;
goto out;
}
if (unlikely(file->f_flags & O_DIRECT))
ret = xfs_file_dio_aio_write(iocb, iovp, nr_segs, pos, ocount);
else
ret = xfs_file_buffered_aio_write(iocb, iovp, nr_segs, pos,
ocount);
if (ret > 0) {
ssize_t err;
XFS_STATS_ADD(xs_write_bytes, ret);
/* Handle various SYNC-type writes */
err = generic_write_sync(file, pos, ret);
if (err < 0)
ret = err;
}
out:
sb_end_write(inode->i_sb);
return ret;
}
int do_fallocate(struct file *file, int mode, loff_t offset, loff_t len)
{
struct inode *inode = file_inode(file);
long ret;
if (offset < 0 || len <= 0)
return -EINVAL;
if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE))
return -EOPNOTSUPP;
if ((mode & FALLOC_FL_PUNCH_HOLE) &&
!(mode & FALLOC_FL_KEEP_SIZE))
return -EOPNOTSUPP;
if (!(file->f_mode & FMODE_WRITE))
return -EBADF;
if (mode & FALLOC_FL_PUNCH_HOLE && IS_APPEND(inode))
return -EPERM;
if (IS_IMMUTABLE(inode))
return -EPERM;
ret = security_file_permission(file, MAY_WRITE);
if (ret)
return ret;
if (S_ISFIFO(inode->i_mode))
return -ESPIPE;
if (!S_ISREG(inode->i_mode) && !S_ISDIR(inode->i_mode))
return -ENODEV;
if (((offset + len) > inode->i_sb->s_maxbytes) || ((offset + len) < 0))
return -EFBIG;
if (!file->f_op->fallocate)
return -EOPNOTSUPP;
sb_start_write(inode->i_sb);
ret = file->f_op->fallocate(file, mode, offset, len);
sb_end_write(inode->i_sb);
return ret;
}
static long do_sys_ftruncate(unsigned int fd, loff_t length, int small)
{
struct inode *inode;
struct dentry *dentry;
struct vfsmount *mnt;
struct fd f;
int error;
error = -EINVAL;
if (length < 0)
goto out;
error = -EBADF;
f = fdget(fd);
if (!f.file)
goto out;
/* explicitly opened as large or we are on 64-bit box */
if (f.file->f_flags & O_LARGEFILE)
small = 0;
dentry = f.file->f_path.dentry;
mnt = f.file->f_path.mnt;
inode = dentry->d_inode;
error = -EINVAL;
if (!S_ISREG(inode->i_mode) || !(f.file->f_mode & FMODE_WRITE))
goto out_putf;
error = -EINVAL;
/* Cannot ftruncate over 2^31 bytes without large file support */
if (small && length > MAX_NON_LFS)
goto out_putf;
error = -EPERM;
if (IS_APPEND(inode))
goto out_putf;
sb_start_write(inode->i_sb);
error = locks_verify_truncate(inode, f.file, length);
if (!error)
error = security_path_truncate(&f.file->f_path);
if (!error)
error = do_truncate2(mnt, dentry, length, ATTR_MTIME|ATTR_CTIME, f.file);
sb_end_write(inode->i_sb);
out_putf:
fdput(f);
out:
return error;
}
static long do_sys_ftruncate(unsigned int fd, loff_t length, int small)
{
struct inode *inode;
struct dentry *dentry;
struct fd f;
int error;
error = -EINVAL;
if (length < 0)
goto out;
error = -EBADF;
f = fdget(fd);
if (!f.file)
goto out;
if (f.file->f_flags & O_LARGEFILE)
small = 0;
dentry = f.file->f_path.dentry;
inode = dentry->d_inode;
error = -EINVAL;
if (!S_ISREG(inode->i_mode) || !(f.file->f_mode & FMODE_WRITE))
goto out_putf;
error = -EINVAL;
if (small && length > MAX_NON_LFS)
goto out_putf;
error = -EPERM;
if (IS_APPEND(inode))
goto out_putf;
sb_start_write(inode->i_sb);
error = locks_verify_truncate(inode, f.file, length);
if (!error)
error = security_path_truncate(&f.file->f_path);
if (!error)
error = do_truncate(dentry, length, ATTR_MTIME|ATTR_CTIME, f.file);
sb_end_write(inode->i_sb);
out_putf:
fdput(f);
out:
return error;
}
/**
* Open, mmap and mlock the specified file to be able to read and
* write to it in softirqs.
* Use MAP_SHARED to synchronize the mapping with underlying file.
*
* The function must not be called from softirq!
*/
int
tdb_file_open(TDB *db, unsigned long size)
{
unsigned long ret, addr;
struct file *filp;
struct inode *inode;
filp = filp_open(db->path, O_CREAT | O_RDWR, 0600);
if (IS_ERR(filp)) {
TDB_ERR("Cannot open db file %s\n", db->path);
return PTR_ERR(filp);
}
BUG_ON(!filp || !filp->f_path.dentry);
if (!filp->f_op->fallocate) {
TDB_ERR("TDB requires filesystem with fallocate support\n");
filp_close(db->filp, NULL);
return -EBADF;
}
/* Allocate continuous extents. */
inode = file_inode(filp);
sb_start_write(inode->i_sb);
ret = filp->f_op->fallocate(filp, 0, 0, size);
sb_end_write(inode->i_sb);
if (ret) {
TDB_ERR("Cannot fallocate file, %ld\n", ret);
filp_close(db->filp, NULL);
return ret;
}
addr = tempesta_map_file(filp, size, db->node);
if (IS_ERR((void *)addr)) {
TDB_ERR("Cannot map file\n");
filp_close(filp, NULL);
return (int)addr;
}
db->filp = filp;
db->hdr = (TdbHdr *)addr;
file_accessed(filp);
return 0;
}
/*
* Write the MMP block using WRITE_SYNC to try to get the block on-disk
* faster.
*/
static int write_mmp_block(struct super_block *sb, struct buffer_head *bh)
{
struct mmp_struct *mmp = (struct mmp_struct *)(bh->b_data);
/*
* We protect against freezing so that we don't create dirty buffers
* on frozen filesystem.
*/
sb_start_write(sb);
ext4_mmp_csum_set(sb, mmp);
mark_buffer_dirty(bh);
lock_buffer(bh);
bh->b_end_io = end_buffer_write_sync;
get_bh(bh);
submit_bh(WRITE_SYNC | REQ_META | REQ_PRIO, bh);
wait_on_buffer(bh);
sb_end_write(sb);
if (unlikely(!buffer_uptodate(bh)))
return 1;
return 0;
}
int do_fallocate(struct file *file, int mode, loff_t offset, loff_t len)
{
struct inode *inode = file_inode(file);
long ret;
if (offset < 0 || len <= 0)
return -EINVAL;
/* Return error if mode is not supported */
if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE |
FALLOC_FL_COLLAPSE_RANGE | FALLOC_FL_ZERO_RANGE))
return -EOPNOTSUPP;
/* Punch hole and zero range are mutually exclusive */
if ((mode & (FALLOC_FL_PUNCH_HOLE | FALLOC_FL_ZERO_RANGE)) ==
(FALLOC_FL_PUNCH_HOLE | FALLOC_FL_ZERO_RANGE))
return -EOPNOTSUPP;
/* Punch hole must have keep size set */
if ((mode & FALLOC_FL_PUNCH_HOLE) &&
!(mode & FALLOC_FL_KEEP_SIZE))
return -EOPNOTSUPP;
/* Collapse range should only be used exclusively. */
if ((mode & FALLOC_FL_COLLAPSE_RANGE) &&
(mode & ~FALLOC_FL_COLLAPSE_RANGE))
return -EINVAL;
if (!(file->f_mode & FMODE_WRITE))
return -EBADF;
/*
* We can only allow pure fallocate on append only files
*/
if ((mode & ~FALLOC_FL_KEEP_SIZE) && IS_APPEND(inode))
return -EPERM;
if (IS_IMMUTABLE(inode))
return -EPERM;
/*
* We cannot allow any fallocate operation on an active swapfile
*/
if (IS_SWAPFILE(inode))
return -ETXTBSY;
/*
* Revalidate the write permissions, in case security policy has
* changed since the files were opened.
*/
ret = security_file_permission(file, MAY_WRITE);
if (ret)
return ret;
if (S_ISFIFO(inode->i_mode))
return -ESPIPE;
/*
* Let individual file system decide if it supports preallocation
* for directories or not.
*/
if (!S_ISREG(inode->i_mode) && !S_ISDIR(inode->i_mode))
return -ENODEV;
/* Check for wrap through zero too */
if (((offset + len) > inode->i_sb->s_maxbytes) || ((offset + len) < 0))
return -EFBIG;
if (!file->f_op->fallocate)
return -EOPNOTSUPP;
sb_start_write(inode->i_sb);
ret = file->f_op->fallocate(file, mode, offset, len);
sb_end_write(inode->i_sb);
return ret;
}
/*
* Almost copy of generic_file_splice_write() (added changed_begin/end,
* tux3_iattrdirty()).
*/
static ssize_t tux3_file_splice_write(struct pipe_inode_info *pipe,
struct file *out, loff_t *ppos,
size_t len, unsigned int flags)
{
if(DEBUG_MODE_K==1)
{
printk(KERN_INFO"%25s %25s %4d #in\n",__FILE__,__func__,__LINE__);
}
struct address_space *mapping = out->f_mapping;
struct inode *inode = mapping->host;
struct sb *sb = tux_sb(inode->i_sb);
struct splice_desc sd = {
.total_len = len,
.flags = flags,
.pos = *ppos,
.u.file = out,
};
ssize_t ret;
sb_start_write(inode->i_sb);
pipe_lock(pipe);
splice_from_pipe_begin(&sd);
do {
ret = splice_from_pipe_next(pipe, &sd);
if (ret <= 0)
break;
mutex_lock_nested(&inode->i_mutex, I_MUTEX_CHILD);
/* For each ->write_end() calls change_end(). */
change_begin(sb);
/* For timestamp. FIXME: convert this to ->update_time
* handler? */
tux3_iattrdirty(inode);
ret = file_remove_suid(out);
if (!ret) {
ret = file_update_time(out);
if (!ret)
ret = splice_from_pipe_feed(pipe, &sd,
pipe_to_file);
}
change_end_if_needed(sb);
mutex_unlock(&inode->i_mutex);
} while (ret > 0);
splice_from_pipe_end(pipe, &sd);
pipe_unlock(pipe);
if (sd.num_spliced)
ret = sd.num_spliced;
if (ret > 0) {
int err;
err = generic_write_sync(out, *ppos, ret);
if (err)
ret = err;
else
*ppos += ret;
balance_dirty_pages_ratelimited(mapping);
}
sb_end_write(inode->i_sb);
return ret;
}
static inline void dummy(void){
struct inode i;
sb_start_write(i.i_sb);
sb_end_write(i.i_sb);
}
