/*
* Common pre-write limit and setup checks.
*
* Called with the iolocked held either shared and exclusive according to
* @iolock, and returns with it held. Might upgrade the iolock to exclusive
* if called for a direct write beyond i_size.
*/
STATIC ssize_t
xfs_file_aio_write_checks(
struct file *file,
loff_t *pos,
size_t *count,
int *iolock)
{
struct inode *inode = file->f_mapping->host;
struct xfs_inode *ip = XFS_I(inode);
int error = 0;
restart:
error = generic_write_checks(file, pos, count, S_ISBLK(inode->i_mode));
if (error)
return error;
/*
* If the offset is beyond the size of the file, we need to zero any
* blocks that fall between the existing EOF and the start of this
* write. If zeroing is needed and we are currently holding the
* iolock shared, we need to update it to exclusive which implies
* having to redo all checks before.
*/
if (*pos > i_size_read(inode)) {
if (*iolock == XFS_IOLOCK_SHARED) {
xfs_rw_iunlock(ip, *iolock);
*iolock = XFS_IOLOCK_EXCL;
xfs_rw_ilock(ip, *iolock);
goto restart;
}
error = -xfs_zero_eof(ip, *pos, i_size_read(inode));
if (error)
return error;
}
/*
* Updating the timestamps will grab the ilock again from
* xfs_fs_dirty_inode, so we have to call it after dropping the
* lock above. Eventually we should look into a way to avoid
* the pointless lock roundtrip.
*/
if (likely(!(file->f_mode & FMODE_NOCMTIME))) {
error = file_update_time(file);
if (error)
return error;
}
/*
* If we're writing the file then make sure to clear the setuid and
* setgid bits if the process is not being run by root. This keeps
* people from modifying setuid and setgid binaries.
*/
return file_remove_suid(file);
}
/*
* Common pre-write limit and setup checks.
*
* Called with the iolocked held either shared and exclusive according to
* @iolock, and returns with it held. Might upgrade the iolock to exclusive
* if called for a direct write beyond i_size.
*/
STATIC ssize_t
xfs_file_aio_write_checks(
struct file *file,
loff_t *pos,
size_t *count,
int *iolock)
{
struct inode *inode = file->f_mapping->host;
struct xfs_inode *ip = XFS_I(inode);
int error = 0;
xfs_rw_ilock(ip, XFS_ILOCK_EXCL);
restart:
error = generic_write_checks(file, pos, count, S_ISBLK(inode->i_mode));
if (error) {
xfs_rw_iunlock(ip, XFS_ILOCK_EXCL);
return error;
}
if (likely(!(file->f_mode & FMODE_NOCMTIME)))
file_update_time(file);
/*
* If the offset is beyond the size of the file, we need to zero any
* blocks that fall between the existing EOF and the start of this
* write. If zeroing is needed and we are currently holding the
* iolock shared, we need to update it to exclusive which involves
* dropping all locks and relocking to maintain correct locking order.
* If we do this, restart the function to ensure all checks and values
* are still valid.
*/
if (*pos > i_size_read(inode)) {
if (*iolock == XFS_IOLOCK_SHARED) {
xfs_rw_iunlock(ip, XFS_ILOCK_EXCL | *iolock);
*iolock = XFS_IOLOCK_EXCL;
xfs_rw_ilock(ip, XFS_ILOCK_EXCL | *iolock);
goto restart;
}
error = -xfs_zero_eof(ip, *pos, i_size_read(inode));
}
xfs_rw_iunlock(ip, XFS_ILOCK_EXCL);
if (error)
return error;
/*
* If we're writing the file then make sure to clear the setuid and
* setgid bits if the process is not being run by root. This keeps
* people from modifying setuid and setgid binaries.
*/
return file_remove_suid(file);
}
ssize_t hmfs_xip_file_write(struct file * filp, const char __user * buf,
size_t len, loff_t * ppos)
{
struct address_space *mapping = filp->f_mapping;
struct inode *inode = filp->f_inode;
struct hmfs_sb_info *sbi = HMFS_SB(inode->i_sb);
size_t count = 0, ret;
loff_t pos;
int ilock;
mutex_lock(&inode->i_mutex);
if (!access_ok(VERIFY_READ, buf, len)) {
ret = -EFAULT;
goto out_up;
}
pos = *ppos;
count = len;
current->backing_dev_info = mapping->backing_dev_info;
ret = generic_write_checks(filp, &pos, &count, S_ISBLK(inode->i_mode));
if (ret)
goto out_backing;
if (count == 0)
goto out_backing;
ret = file_remove_suid(filp);
if (ret)
goto out_backing;
ret = file_update_time(filp);
if (ret)
goto out_backing;
inode->i_ctime = inode->i_mtime = CURRENT_TIME_SEC;
ilock = mutex_lock_op(sbi);
ret = __hmfs_xip_file_write(filp, buf, count, pos, ppos);
mutex_unlock_op(sbi, ilock);
mark_inode_dirty(inode);
out_backing:
current->backing_dev_info = NULL;
out_up:
mutex_unlock(&inode->i_mutex);
return ret;
}
/*
* Common pre-write limit and setup checks.
*
* Returns with iolock held according to @iolock.
*/
STATIC ssize_t
xfs_file_aio_write_checks(
struct file *file,
loff_t *pos,
size_t *count,
int *iolock)
{
struct inode *inode = file->f_mapping->host;
struct xfs_inode *ip = XFS_I(inode);
xfs_fsize_t new_size;
int error = 0;
xfs_rw_ilock(ip, XFS_ILOCK_EXCL);
error = generic_write_checks(file, pos, count, S_ISBLK(inode->i_mode));
if (error) {
xfs_rw_iunlock(ip, XFS_ILOCK_EXCL | *iolock);
*iolock = 0;
return error;
}
new_size = *pos + *count;
if (new_size > ip->i_size)
ip->i_new_size = new_size;
if (likely(!(file->f_mode & FMODE_NOCMTIME)))
file_update_time(file);
/*
* If the offset is beyond the size of the file, we need to zero any
* blocks that fall between the existing EOF and the start of this
* write.
*/
if (*pos > ip->i_size)
error = -xfs_zero_eof(ip, *pos, ip->i_size);
xfs_rw_iunlock(ip, XFS_ILOCK_EXCL);
if (error)
return error;
/*
* If we're writing the file then make sure to clear the setuid and
* setgid bits if the process is not being run by root. This keeps
* people from modifying setuid and setgid binaries.
*/
return file_remove_suid(file);
}
STATIC ssize_t
xfs_file_aio_write_checks(
struct file *file,
loff_t *pos,
size_t *count,
int *iolock)
{
struct inode *inode = file->f_mapping->host;
struct xfs_inode *ip = XFS_I(inode);
int error = 0;
xfs_rw_ilock(ip, XFS_ILOCK_EXCL);
restart:
error = generic_write_checks(file, pos, count, S_ISBLK(inode->i_mode));
if (error) {
xfs_rw_iunlock(ip, XFS_ILOCK_EXCL);
return error;
}
if (*pos > i_size_read(inode)) {
if (*iolock == XFS_IOLOCK_SHARED) {
xfs_rw_iunlock(ip, XFS_ILOCK_EXCL | *iolock);
*iolock = XFS_IOLOCK_EXCL;
xfs_rw_ilock(ip, XFS_ILOCK_EXCL | *iolock);
goto restart;
}
error = -xfs_zero_eof(ip, *pos, i_size_read(inode));
}
xfs_rw_iunlock(ip, XFS_ILOCK_EXCL);
if (error)
return error;
if (likely(!(file->f_mode & FMODE_NOCMTIME)))
file_update_time(file);
return file_remove_suid(file);
}
static
ssize_t svfs_file_splice_write(struct pipe_inode_info *pipe,
struct file *out, loff_t *ppos, size_t len,
unsigned int flags)
{
struct address_space *mapping;
struct inode *inode;
struct file *llfs_filp;
struct svfs_inode *si;
struct splice_desc sd = {0,};
ssize_t ret;
svfs_entry(mdc, "pos %lu, len %ld, flags 0x%x\n", (unsigned long)*ppos,
(long)len, flags);
si = SVFS_I(out->f_dentry->d_inode);
if (si->state & SVFS_STATE_DA) {
/* create it now */
ASSERT(!(si->state & SVFS_STATE_CONN));
ret = llfs_create(out->f_dentry);
if (ret)
goto out;
}
if (!(si->state & SVFS_STATE_CONN)) {
/* open it ? */
ret = llfs_lookup(out->f_dentry->d_inode);
if (ret)
goto out;
}
llfs_filp = si->llfs_md.llfs_filp;
ASSERT(llfs_filp);
mapping = llfs_filp->f_mapping;
inode = mapping->host;
sd.total_len = len;
sd.flags = flags;
sd.pos = *ppos;
sd.u.file = llfs_filp;
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);
ret = file_remove_suid(out);
if (!ret)
ret = splice_from_pipe_feed(pipe, &sd, pipe_to_file);
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) {
unsigned long nr_pages;
*ppos += ret;
nr_pages = (ret + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
/*
* If file or inode is SYNC and we actually wrote some data,
* sync it.
*/
if (unlikely((out->f_flags & O_SYNC) || IS_SYNC(inode))) {
int err;
mutex_lock(&inode->i_mutex);
err = generic_osync_inode(inode, mapping,
OSYNC_METADATA|OSYNC_DATA);
mutex_unlock(&inode->i_mutex);
if (err)
ret = err;
}
balance_dirty_pages_ratelimited_nr(mapping, nr_pages);
}
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);
struct xfs_mount *mp = ip->i_mount;
ssize_t ret = 0, error = 0;
int ioflags = 0;
xfs_fsize_t isize, new_size;
int iolock;
int eventsent = 0;
size_t ocount = 0, count;
int need_i_mutex;
XFS_STATS_INC(xs_write_calls);
BUG_ON(iocb->ki_pos != pos);
if (unlikely(file->f_flags & O_DIRECT))
ioflags |= IO_ISDIRECT;
if (file->f_mode & FMODE_NOCMTIME)
ioflags |= IO_INVIS;
error = generic_segment_checks(iovp, &nr_segs, &ocount, VERIFY_READ);
if (error)
return error;
count = ocount;
if (count == 0)
return 0;
xfs_wait_for_freeze(mp, SB_FREEZE_WRITE);
if (XFS_FORCED_SHUTDOWN(mp))
return -EIO;
relock:
if (ioflags & IO_ISDIRECT) {
iolock = XFS_IOLOCK_SHARED;
need_i_mutex = 0;
} else {
iolock = XFS_IOLOCK_EXCL;
need_i_mutex = 1;
mutex_lock(&inode->i_mutex);
}
xfs_ilock(ip, XFS_ILOCK_EXCL|iolock);
start:
error = -generic_write_checks(file, &pos, &count,
S_ISBLK(inode->i_mode));
if (error) {
xfs_iunlock(ip, XFS_ILOCK_EXCL|iolock);
goto out_unlock_mutex;
}
if ((DM_EVENT_ENABLED(ip, DM_EVENT_WRITE) &&
!(ioflags & IO_INVIS) && !eventsent)) {
int dmflags = FILP_DELAY_FLAG(file);
if (need_i_mutex)
dmflags |= DM_FLAGS_IMUX;
xfs_iunlock(ip, XFS_ILOCK_EXCL);
error = XFS_SEND_DATA(ip->i_mount, DM_EVENT_WRITE, ip,
pos, count, dmflags, &iolock);
if (error) {
goto out_unlock_internal;
}
xfs_ilock(ip, XFS_ILOCK_EXCL);
eventsent = 1;
/*
* The iolock was dropped and reacquired in XFS_SEND_DATA
* so we have to recheck the size when appending.
* We will only "goto start;" once, since having sent the
* event prevents another call to XFS_SEND_DATA, which is
* what allows the size to change in the first place.
*/
if ((file->f_flags & O_APPEND) && pos != ip->i_size)
goto start;
}
if (ioflags & IO_ISDIRECT) {
xfs_buftarg_t *target =
XFS_IS_REALTIME_INODE(ip) ?
mp->m_rtdev_targp : mp->m_ddev_targp;
if ((pos & target->bt_smask) || (count & target->bt_smask)) {
xfs_iunlock(ip, XFS_ILOCK_EXCL|iolock);
return XFS_ERROR(-EINVAL);
}
if (!need_i_mutex && (mapping->nrpages || pos > ip->i_size)) {
xfs_iunlock(ip, XFS_ILOCK_EXCL|iolock);
iolock = XFS_IOLOCK_EXCL;
need_i_mutex = 1;
mutex_lock(&inode->i_mutex);
xfs_ilock(ip, XFS_ILOCK_EXCL|iolock);
goto start;
}
}
new_size = pos + count;
if (new_size > ip->i_size)
ip->i_new_size = new_size;
if (likely(!(ioflags & IO_INVIS)))
file_update_time(file);
/*
* If the offset is beyond the size of the file, we have a couple
* of things to do. First, if there is already space allocated
* we need to either create holes or zero the disk or ...
*
* If there is a page where the previous size lands, we need
* to zero it out up to the new size.
*/
if (pos > ip->i_size) {
error = xfs_zero_eof(ip, pos, ip->i_size);
if (error) {
xfs_iunlock(ip, XFS_ILOCK_EXCL);
goto out_unlock_internal;
}
}
xfs_iunlock(ip, XFS_ILOCK_EXCL);
/*
* If we're writing the file then make sure to clear the
* setuid and setgid bits if the process is not being run
* by root. This keeps people from modifying setuid and
* setgid binaries.
*/
error = -file_remove_suid(file);
if (unlikely(error))
goto out_unlock_internal;
/* We can write back this queue in page reclaim */
current->backing_dev_info = mapping->backing_dev_info;
if ((ioflags & IO_ISDIRECT)) {
if (mapping->nrpages) {
WARN_ON(need_i_mutex == 0);
error = xfs_flushinval_pages(ip,
(pos & PAGE_CACHE_MASK),
-1, FI_REMAPF_LOCKED);
if (error)
goto out_unlock_internal;
}
if (need_i_mutex) {
/* demote the lock now the cached pages are gone */
xfs_ilock_demote(ip, XFS_IOLOCK_EXCL);
mutex_unlock(&inode->i_mutex);
iolock = XFS_IOLOCK_SHARED;
need_i_mutex = 0;
}
trace_xfs_file_direct_write(ip, count, iocb->ki_pos, ioflags);
ret = generic_file_direct_write(iocb, iovp,
&nr_segs, pos, &iocb->ki_pos, count, ocount);
/*
* direct-io write to a hole: fall through to buffered I/O
* for completing the rest of the request.
*/
if (ret >= 0 && ret != count) {
XFS_STATS_ADD(xs_write_bytes, ret);
pos += ret;
count -= ret;
ioflags &= ~IO_ISDIRECT;
xfs_iunlock(ip, iolock);
goto relock;
}
} else {
int enospc = 0;
ssize_t ret2 = 0;
write_retry:
trace_xfs_file_buffered_write(ip, count, iocb->ki_pos, ioflags);
ret2 = generic_file_buffered_write(iocb, iovp, nr_segs,
pos, &iocb->ki_pos, count, ret);
/*
* if we just got an ENOSPC, flush the inode now we
* aren't holding any page locks and retry *once*
*/
if (ret2 == -ENOSPC && !enospc) {
error = xfs_flush_pages(ip, 0, -1, 0, FI_NONE);
if (error)
goto out_unlock_internal;
enospc = 1;
goto write_retry;
}
ret = ret2;
}
current->backing_dev_info = NULL;
isize = i_size_read(inode);
if (unlikely(ret < 0 && ret != -EFAULT && iocb->ki_pos > isize))
iocb->ki_pos = isize;
if (iocb->ki_pos > ip->i_size) {
xfs_ilock(ip, XFS_ILOCK_EXCL);
if (iocb->ki_pos > ip->i_size)
ip->i_size = iocb->ki_pos;
xfs_iunlock(ip, XFS_ILOCK_EXCL);
}
if (ret == -ENOSPC &&
DM_EVENT_ENABLED(ip, DM_EVENT_NOSPACE) && !(ioflags & IO_INVIS)) {
xfs_iunlock(ip, iolock);
if (need_i_mutex)
mutex_unlock(&inode->i_mutex);
error = XFS_SEND_NAMESP(ip->i_mount, DM_EVENT_NOSPACE, ip,
DM_RIGHT_NULL, ip, DM_RIGHT_NULL, NULL, NULL,
0, 0, 0); /* Delay flag intentionally unused */
if (need_i_mutex)
mutex_lock(&inode->i_mutex);
xfs_ilock(ip, iolock);
if (error)
goto out_unlock_internal;
goto start;
}
error = -ret;
if (ret <= 0)
goto out_unlock_internal;
XFS_STATS_ADD(xs_write_bytes, ret);
/* Handle various SYNC-type writes */
if ((file->f_flags & O_DSYNC) || IS_SYNC(inode)) {
loff_t end = pos + ret - 1;
int error2;
xfs_iunlock(ip, iolock);
if (need_i_mutex)
mutex_unlock(&inode->i_mutex);
error2 = filemap_write_and_wait_range(mapping, pos, end);
if (!error)
error = error2;
if (need_i_mutex)
mutex_lock(&inode->i_mutex);
xfs_ilock(ip, iolock);
error2 = -xfs_file_fsync(file, file->f_path.dentry,
(file->f_flags & __O_SYNC) ? 0 : 1);
if (!error)
error = error2;
}
out_unlock_internal:
if (ip->i_new_size) {
xfs_ilock(ip, XFS_ILOCK_EXCL);
ip->i_new_size = 0;
/*
* If this was a direct or synchronous I/O that failed (such
* as ENOSPC) then part of the I/O may have been written to
* disk before the error occured. In this case the on-disk
* file size may have been adjusted beyond the in-memory file
* size and now needs to be truncated back.
*/
if (ip->i_d.di_size > ip->i_size)
ip->i_d.di_size = ip->i_size;
xfs_iunlock(ip, XFS_ILOCK_EXCL);
}
xfs_iunlock(ip, iolock);
out_unlock_mutex:
if (need_i_mutex)
mutex_unlock(&inode->i_mutex);
return -error;
}
long ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
{
struct inode *inode = filp->f_dentry->d_inode;
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;
unsigned int jflag;
if (!is_owner_or_cap(inode))
return -EACCES;
if (get_user(flags, (int __user *) arg))
return -EFAULT;
err = mnt_want_write(filp->f_path.mnt);
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 (oldflags & EXT4_EXTENTS_FL) {
/* We don't support clearning extent flags */
if (!(flags & EXT4_EXTENTS_FL)) {
err = -EOPNOTSUPP;
goto flags_out;
}
} else if (flags & EXT4_EXTENTS_FL) {
/* migrate the file */
migrate = 1;
flags &= ~EXT4_EXTENTS_FL;
}
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, 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;
flags = flags & EXT4_FL_USER_MODIFIABLE;
flags |= oldflags & ~EXT4_FL_USER_MODIFIABLE;
ei->i_flags = flags;
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)
err = ext4_ext_migrate(inode);
flags_out:
mutex_unlock(&inode->i_mutex);
mnt_drop_write(filp->f_path.mnt);
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 (!is_owner_or_cap(inode))
return -EPERM;
err = mnt_want_write(filp->f_path.mnt);
if (err)
return err;
if (get_user(generation, (int __user *) arg)) {
err = -EFAULT;
goto setversion_out;
}
handle = ext4_journal_start(inode, 1);
if (IS_ERR(handle)) {
err = PTR_ERR(handle);
goto setversion_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);
setversion_out:
mnt_drop_write(filp->f_path.mnt);
return err;
}
#ifdef CONFIG_JBD2_DEBUG
case EXT4_IOC_WAIT_FOR_READONLY:
/*
* This is racy - by the time we're woken up and running,
* the superblock could be released. And the module could
* have been unloaded. So sue me.
*
* Returns 1 if it slept, else zero.
*/
{
DECLARE_WAITQUEUE(wait, current);
int ret = 0;
set_current_state(TASK_INTERRUPTIBLE);
add_wait_queue(&EXT4_SB(sb)->ro_wait_queue, &wait);
if (timer_pending(&EXT4_SB(sb)->turn_ro_timer)) {
schedule();
ret = 1;
}
remove_wait_queue(&EXT4_SB(sb)->ro_wait_queue, &wait);
return ret;
}
#endif
case EXT4_IOC_GROUP_EXTEND: {
ext4_fsblk_t n_blocks_count;
int err, err2=0;
if (!capable(CAP_SYS_RESOURCE))
return -EPERM;
if (get_user(n_blocks_count, (__u32 __user *)arg))
return -EFAULT;
if (EXT4_HAS_RO_COMPAT_FEATURE(sb,
EXT4_FEATURE_RO_COMPAT_BIGALLOC)) {
ext4_msg(sb, KERN_ERR,
"Online resizing not supported with bigalloc");
return -EOPNOTSUPP;
}
err = mnt_want_write(filp->f_path.mnt);
if (err)
return err;
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(filp->f_path.mnt);
return err;
}
case EXT4_IOC_MOVE_EXT: {
struct move_extent me;
struct file *donor_filp;
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;
donor_filp = fget(me.donor_fd);
if (!donor_filp)
return -EBADF;
if (!(donor_filp->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");
return -EOPNOTSUPP;
}
err = mnt_want_write(filp->f_path.mnt);
if (err)
goto mext_out;
me.moved_len = 0;
err = ext4_move_extents(filp, donor_filp, me.orig_start,
me.donor_start, me.len, &me.moved_len);
mnt_drop_write(filp->f_path.mnt);
if (me.moved_len > 0)
file_remove_suid(donor_filp);
if (copy_to_user((struct move_extent *)arg, &me, sizeof(me)))
err = -EFAULT;
mext_out:
fput(donor_filp);
return err;
}
case EXT4_IOC_GROUP_ADD: {
struct ext4_new_group_data input;
int err, err2=0;
if (!capable(CAP_SYS_RESOURCE))
return -EPERM;
if (copy_from_user(&input, (struct ext4_new_group_input __user *)arg,
sizeof(input)))
return -EFAULT;
if (EXT4_HAS_RO_COMPAT_FEATURE(sb,
EXT4_FEATURE_RO_COMPAT_BIGALLOC)) {
ext4_msg(sb, KERN_ERR,
"Online resizing not supported with bigalloc");
return -EOPNOTSUPP;
}
err = mnt_want_write(filp->f_path.mnt);
if (err)
return err;
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(filp->f_path.mnt);
return err;
}
case EXT4_IOC_MIGRATE:
{
int err;
if (!is_owner_or_cap(inode))
return -EACCES;
err = mnt_want_write(filp->f_path.mnt);
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(filp->f_path.mnt);
return err;
}
case EXT4_IOC_ALLOC_DA_BLKS:
{
int err;
if (!is_owner_or_cap(inode))
return -EACCES;
err = mnt_want_write(filp->f_path.mnt);
if (err)
return err;
err = ext4_alloc_da_blocks(inode);
mnt_drop_write(filp->f_path.mnt);
return err;
}
case FITRIM:
{
struct request_queue *q = bdev_get_queue(sb->s_bdev);
struct fstrim_range range;
int ret = 0;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
if (!blk_queue_discard(q))
return -EOPNOTSUPP;
if (EXT4_HAS_RO_COMPAT_FEATURE(sb,
EXT4_FEATURE_RO_COMPAT_BIGALLOC)) {
ext4_msg(sb, KERN_ERR,
"FITRIM not supported with bigalloc");
return -EOPNOTSUPP;
}
if (copy_from_user(&range, (struct fstrim_range *)arg,
sizeof(range)))
return -EFAULT;
range.minlen = max((unsigned int)range.minlen,
q->limits.discard_granularity);
ret = ext4_trim_fs(sb, &range);
if (ret < 0)
return ret;
if (copy_to_user((struct fstrim_range *)arg, &range,
sizeof(range)))
return -EFAULT;
return 0;
}
default:
return -ENOTTY;
}
}
/*
* 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;
}
ssize_t /* bytes written, or (-) error */
xfs_write(
struct xfs_inode *xip,
struct kiocb *iocb,
const struct iovec *iovp,
unsigned int nsegs,
loff_t *offset,
int ioflags)
{
struct file *file = iocb->ki_filp;
struct address_space *mapping = file->f_mapping;
struct inode *inode = mapping->host;
unsigned long segs = nsegs;
xfs_mount_t *mp;
ssize_t ret = 0, error = 0;
xfs_fsize_t isize, new_size;
int iolock;
int eventsent = 0;
size_t ocount = 0, count;
loff_t pos;
int need_i_mutex;
XFS_STATS_INC(xs_write_calls);
error = generic_segment_checks(iovp, &segs, &ocount, VERIFY_READ);
if (error)
return error;
count = ocount;
pos = *offset;
if (count == 0)
return 0;
mp = xip->i_mount;
xfs_wait_for_freeze(mp, SB_FREEZE_WRITE);
if (XFS_FORCED_SHUTDOWN(mp))
return -EIO;
relock:
if (ioflags & IO_ISDIRECT) {
iolock = XFS_IOLOCK_SHARED;
need_i_mutex = 0;
} else {
iolock = XFS_IOLOCK_EXCL;
need_i_mutex = 1;
mutex_lock(&inode->i_mutex);
}
xfs_ilock(xip, XFS_ILOCK_EXCL|iolock);
start:
error = -generic_write_checks(file, &pos, &count,
S_ISBLK(inode->i_mode));
if (error) {
xfs_iunlock(xip, XFS_ILOCK_EXCL|iolock);
goto out_unlock_mutex;
}
if ((DM_EVENT_ENABLED(xip, DM_EVENT_WRITE) &&
!(ioflags & IO_INVIS) && !eventsent)) {
int dmflags = FILP_DELAY_FLAG(file);
if (need_i_mutex)
dmflags |= DM_FLAGS_IMUX;
xfs_iunlock(xip, XFS_ILOCK_EXCL);
error = XFS_SEND_DATA(xip->i_mount, DM_EVENT_WRITE, xip,
pos, count, dmflags, &iolock);
if (error) {
goto out_unlock_internal;
}
xfs_ilock(xip, XFS_ILOCK_EXCL);
eventsent = 1;
/*
* The iolock was dropped and reacquired in XFS_SEND_DATA
* so we have to recheck the size when appending.
* We will only "goto start;" once, since having sent the
* event prevents another call to XFS_SEND_DATA, which is
* what allows the size to change in the first place.
*/
if ((file->f_flags & O_APPEND) && pos != xip->i_size)
goto start;
}
if (ioflags & IO_ISDIRECT) {
xfs_buftarg_t *target =
XFS_IS_REALTIME_INODE(xip) ?
mp->m_rtdev_targp : mp->m_ddev_targp;
if ((pos & target->bt_smask) || (count & target->bt_smask)) {
xfs_iunlock(xip, XFS_ILOCK_EXCL|iolock);
return XFS_ERROR(-EINVAL);
}
if (!need_i_mutex && (mapping->nrpages || pos > xip->i_size)) {
xfs_iunlock(xip, XFS_ILOCK_EXCL|iolock);
iolock = XFS_IOLOCK_EXCL;
need_i_mutex = 1;
mutex_lock(&inode->i_mutex);
xfs_ilock(xip, XFS_ILOCK_EXCL|iolock);
goto start;
}
}
new_size = pos + count;
if (new_size > xip->i_size)
xip->i_new_size = new_size;
if (likely(!(ioflags & IO_INVIS)))
xfs_ichgtime(xip, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
/*
* If the offset is beyond the size of the file, we have a couple
* of things to do. First, if there is already space allocated
* we need to either create holes or zero the disk or ...
*
* If there is a page where the previous size lands, we need
* to zero it out up to the new size.
*/
if (pos > xip->i_size) {
error = xfs_zero_eof(xip, pos, xip->i_size);
if (error) {
xfs_iunlock(xip, XFS_ILOCK_EXCL);
goto out_unlock_internal;
}
}
xfs_iunlock(xip, XFS_ILOCK_EXCL);
/*
* If we're writing the file then make sure to clear the
* setuid and setgid bits if the process is not being run
* by root. This keeps people from modifying setuid and
* setgid binaries.
*/
if (((xip->i_d.di_mode & S_ISUID) ||
((xip->i_d.di_mode & (S_ISGID | S_IXGRP)) ==
(S_ISGID | S_IXGRP))) &&
!capable(CAP_FSETID)) {
error = xfs_write_clear_setuid(xip);
if (likely(!error))
error = -file_remove_suid(file);
if (unlikely(error)) {
goto out_unlock_internal;
}
}
/* We can write back this queue in page reclaim */
current->backing_dev_info = mapping->backing_dev_info;
if ((ioflags & IO_ISDIRECT)) {
if (mapping->nrpages) {
WARN_ON(need_i_mutex == 0);
xfs_inval_cached_trace(xip, pos, -1,
(pos & PAGE_CACHE_MASK), -1);
error = xfs_flushinval_pages(xip,
(pos & PAGE_CACHE_MASK),
-1, FI_REMAPF_LOCKED);
if (error)
goto out_unlock_internal;
}
if (need_i_mutex) {
/* demote the lock now the cached pages are gone */
xfs_ilock_demote(xip, XFS_IOLOCK_EXCL);
mutex_unlock(&inode->i_mutex);
iolock = XFS_IOLOCK_SHARED;
need_i_mutex = 0;
}
xfs_rw_enter_trace(XFS_DIOWR_ENTER, xip, (void *)iovp, segs,
*offset, ioflags);
ret = generic_file_direct_write(iocb, iovp,
&segs, pos, offset, count, ocount);
/*
* direct-io write to a hole: fall through to buffered I/O
* for completing the rest of the request.
*/
if (ret >= 0 && ret != count) {
XFS_STATS_ADD(xs_write_bytes, ret);
pos += ret;
count -= ret;
ioflags &= ~IO_ISDIRECT;
xfs_iunlock(xip, iolock);
goto relock;
}
} else {
xfs_rw_enter_trace(XFS_WRITE_ENTER, xip, (void *)iovp, segs,
*offset, ioflags);
ret = generic_file_buffered_write(iocb, iovp, segs,
pos, offset, count, ret);
}
current->backing_dev_info = NULL;
if (ret == -EIOCBQUEUED && !(ioflags & IO_ISAIO))
ret = wait_on_sync_kiocb(iocb);
isize = i_size_read(inode);
if (unlikely(ret < 0 && ret != -EFAULT && *offset > isize))
*offset = isize;
if (*offset > xip->i_size) {
xfs_ilock(xip, XFS_ILOCK_EXCL);
if (*offset > xip->i_size)
xip->i_size = *offset;
xfs_iunlock(xip, XFS_ILOCK_EXCL);
}
if (ret == -ENOSPC &&
DM_EVENT_ENABLED(xip, DM_EVENT_NOSPACE) && !(ioflags & IO_INVIS)) {
xfs_iunlock(xip, iolock);
if (need_i_mutex)
mutex_unlock(&inode->i_mutex);
error = XFS_SEND_NAMESP(xip->i_mount, DM_EVENT_NOSPACE, xip,
DM_RIGHT_NULL, xip, DM_RIGHT_NULL, NULL, NULL,
0, 0, 0); /* Delay flag intentionally unused */
if (need_i_mutex)
mutex_lock(&inode->i_mutex);
xfs_ilock(xip, iolock);
if (error)
goto out_unlock_internal;
goto start;
}
error = -ret;
if (ret <= 0)
goto out_unlock_internal;
XFS_STATS_ADD(xs_write_bytes, ret);
/* Handle various SYNC-type writes */
if ((file->f_flags & O_SYNC) || IS_SYNC(inode)) {
int error2;
xfs_iunlock(xip, iolock);
if (need_i_mutex)
mutex_unlock(&inode->i_mutex);
error2 = sync_page_range(inode, mapping, pos, ret);
if (!error)
error = error2;
if (need_i_mutex)
mutex_lock(&inode->i_mutex);
xfs_ilock(xip, iolock);
error2 = xfs_write_sync_logforce(mp, xip);
if (!error)
error = error2;
}
out_unlock_internal:
if (xip->i_new_size) {
xfs_ilock(xip, XFS_ILOCK_EXCL);
xip->i_new_size = 0;
/*
* If this was a direct or synchronous I/O that failed (such
* as ENOSPC) then part of the I/O may have been written to
* disk before the error occured. In this case the on-disk
* file size may have been adjusted beyond the in-memory file
* size and now needs to be truncated back.
*/
if (xip->i_d.di_size > xip->i_size)
xip->i_d.di_size = xip->i_size;
xfs_iunlock(xip, XFS_ILOCK_EXCL);
}
xfs_iunlock(xip, iolock);
out_unlock_mutex:
if (need_i_mutex)
mutex_unlock(&inode->i_mutex);
return -error;
}
/*
* Common pre-write limit and setup checks.
*
* Returns with iolock held according to @iolock.
*/
STATIC ssize_t
xfs_file_aio_write_checks(
struct file *file,
loff_t *pos,
size_t *count,
xfs_fsize_t *new_sizep,
int *iolock)
{
struct inode *inode = file->f_mapping->host;
struct xfs_inode *ip = XFS_I(inode);
xfs_fsize_t new_size;
int error = 0;
xfs_rw_ilock(ip, XFS_ILOCK_EXCL);
*new_sizep = 0;
restart:
error = generic_write_checks(file, pos, count, S_ISBLK(inode->i_mode));
if (error) {
xfs_rw_iunlock(ip, XFS_ILOCK_EXCL | *iolock);
*iolock = 0;
return error;
}
if (likely(!(file->f_mode & FMODE_NOCMTIME)))
file_update_time(file);
/*
* If the offset is beyond the size of the file, we need to zero any
* blocks that fall between the existing EOF and the start of this
* write. There is no need to issue zeroing if another in-flght IO ends
* at or before this one If zeronig is needed and we are currently
* holding the iolock shared, we need to update it to exclusive which
* involves dropping all locks and relocking to maintain correct locking
* order. If we do this, restart the function to ensure all checks and
* values are still valid.
*/
if ((ip->i_new_size && *pos > ip->i_new_size) ||
(!ip->i_new_size && *pos > ip->i_size)) {
if (*iolock == XFS_IOLOCK_SHARED) {
xfs_rw_iunlock(ip, XFS_ILOCK_EXCL | *iolock);
*iolock = XFS_IOLOCK_EXCL;
xfs_rw_ilock(ip, XFS_ILOCK_EXCL | *iolock);
goto restart;
}
error = -xfs_zero_eof(ip, *pos, ip->i_size);
}
/*
* If this IO extends beyond EOF, we may need to update ip->i_new_size.
* We have already zeroed space beyond EOF (if necessary). Only update
* ip->i_new_size if this IO ends beyond any other in-flight writes.
*/
new_size = *pos + *count;
if (new_size > ip->i_size) {
if (new_size > ip->i_new_size)
ip->i_new_size = new_size;
*new_sizep = new_size;
}
xfs_rw_iunlock(ip, XFS_ILOCK_EXCL);
if (error)
return error;
/*
* If we're writing the file then make sure to clear the setuid and
* setgid bits if the process is not being run by root. This keeps
* people from modifying setuid and setgid binaries.
*/
return file_remove_suid(file);
}
ssize_t GSFS_file_write(struct file *filp, const char __user *buf, size_t len, loff_t *off){
struct inode *inode=filp->f_mapping->host;
struct address_space *mapping=filp->f_mapping;
sector_t sec_start,
sec_end,
sec_len;
unsigned long bufstart,
bytes_in_first_buf_page,
bytes_in_last_buf_page,
pagestartbyte,
pageendbyte,
pagelen;
size_t rlen;
struct page *res[2],
*page,
**pages;
unsigned int i,
j,
pages_count,
start_read,
end_read;
gwf(printk("<0>" "File write with inode :%lu len:%lu offset:%llu , filepos:%llu, buf:%lx inode_size:%llu, pid:%u\n",inode->i_ino,len,*off,filp->f_pos,(unsigned long)buf,inode->i_size,current->pid));
if(unlikely(!access_ok(VERIFY_READ,buf,len)))
return -1;
mutex_lock(&inode->i_mutex);
if((*off+len)>inode->i_size){
if((*off+len)>inode->i_sb->s_maxbytes)
return -1;
inode->i_size=(*off+len);
GSFS_truncate(inode);
}
if(filp->f_flags & O_APPEND)
*off=inode->i_size;
current->backing_dev_info=mapping->backing_dev_info;
file_remove_suid(filp);
file_update_time(filp);
//inode_inc_iversion(inode);
sec_start=(*off)>>Block_Size_Bits;
sec_end=(*off+len-1)>>Block_Size_Bits;
sec_len=sec_end-sec_start+1;
pages=kzalloc(sizeof(struct page*) * sec_len, GFP_KERNEL);
bytes_in_first_buf_page=Block_Size-((*off)&((unsigned long)Block_Size-1));
bytes_in_last_buf_page=((*off+len)&((unsigned long)Block_Size-1));
if(bytes_in_last_buf_page==0)
bytes_in_last_buf_page=Block_Size;
start_read=(bytes_in_first_buf_page!=Block_Size)?1:0;
end_read=(bytes_in_last_buf_page!=Block_Size && inode->i_size>(*off+len))?1:0;
gwf(printk("<0>" "GSFS write bytes_in_first_buf_page:%lu, bytes_in_last_buf_page:%lu\n",bytes_in_first_buf_page,bytes_in_last_buf_page));
gwf(printk("<0>" "GSFS write start_read:%u, end_read:%u, sec_start:%lu, sec_end:%lu\n",start_read,end_read,sec_start,sec_end));
if(sec_start==sec_end){
if(start_read || end_read){
res[0]=GSFS_get_data_page_of_inode_with_read(inode, sec_start);
gwf(printk("<0>" "sec_start==sec_end, start_read || end_read , res[0]=%lx",(unsigned long)res[0]));
}
else{
res[0]=GSFS_get_locked_data_page_of_inode_without_read(inode,sec_start);
if(likely(res[0]))
unlock_page(res[0]);
gwf(printk("<0>" "sec_start==sec_end, !(start_read || end_read) , res[0]=%lx",(unsigned long)res[0]));
}
res[1]=0;
if(unlikely(!res[0])){
gwf(printk("<0>" "GSFS write len:-1\n"));
mutex_unlock(&inode->i_mutex);
printk("<1>" "GSFS write len:-1\n");
kfree(pages);
return len;
}
}
else{
if(start_read){
res[0]=GSFS_get_data_page_of_inode_with_read(inode, sec_start);
gwf(printk("<0>" "sec_start!=sec_end, start_read, res[0]=%lx",(unsigned long)res[0]));
}
else{
res[0]=GSFS_get_locked_data_page_of_inode_without_read(inode,sec_start);
if(likely(res[0]))
unlock_page(res[0]);
gwf(printk("<0>" "sec_start!=sec_end, !start_read, res[0]=%lx",(unsigned long)res[0]));
}
}
pages_count=0;
if(sec_len>1)
for(i=sec_start+1;i<=sec_end-1;i++)
pages[pages_count++]=GSFS_get_locked_data_page_of_inode_without_read(inode,i);
if(sec_start != sec_end){
if(end_read){
res[1]=GSFS_get_data_page_of_inode_with_read(inode,sec_end);
gwf(printk("<0>" "sec_start!=sec_end, end_read, res[1]=%lx",(unsigned long)res[1]));
}
else{
res[1]=GSFS_get_locked_data_page_of_inode_without_read(inode,sec_end);
if(likely(res[1]))
unlock_page(res[1]);
gwf(printk("<0>" "sec_start!=sec_end, !end_read, res[1]=%lx",(unsigned long)res[1]));
}
if(unlikely(!res[0] || !res[1])){
gwf(printk("<0>" "GSFS write len:-1\n"));
printk("<1>" "GSFS write len:-1\n");
mutex_unlock(&inode->i_mutex);
kfree(pages);
return len;
}
}
rlen=0;
bufstart=(unsigned long)buf+bytes_in_first_buf_page;
pagelen=Block_Size;
//100% expected complete pages that should be copied
pages_count=0;
if(sec_len>1)
for(i=sec_start+1;i<=sec_end-1;i++){
gwf(printk("<0>" "write page complete pages, i:%u, bufstart:%lx, rlen=%lu\n",i,bufstart,rlen));
page=pages[pages_count++];
if(unlikely(!page))
goto buf_cont;
j=__copy_from_user_inatomic(page_address(page),(void*)bufstart,pagelen);
rlen+=(Block_Size-j);
mark_page_accessed(page);
set_page_dirty(page);
put_page(page);
unlock_page(page);
buf_cont:
bufstart+=pagelen;
}
//first and last page that are not surely complete
for(i=0;i<2 && res[i];i++){
page=res[i];
wait_on_page_locked(page);
lock_page(page);
if(page->index==sec_start){
bufstart=(unsigned long)buf;
pagestartbyte=Block_Size-bytes_in_first_buf_page;
if(sec_start==sec_end)
pageendbyte=pagestartbyte+len-1;
else
pageendbyte=Block_Size-1;
}
else{
bufstart=(unsigned long)buf+bytes_in_first_buf_page+((sec_len-2)<<Block_Size_Bits);
pageendbyte=bytes_in_last_buf_page-1;
pagestartbyte=0;
}
gwf(printk("<0>" "gsfs_write for first and last page, i=%u, page:%lx, bufstart:%lx, pagestartbyte:%lu, pageendbyte:%lu\n",
i,(unsigned long)page,bufstart,pagestartbyte,pageendbyte));
pagelen=pageendbyte-pagestartbyte+1;
j=__copy_from_user_inatomic(page_address(page)+pagestartbyte,(void*)bufstart,pagelen);
rlen+=(pagelen-j);
mark_page_accessed(page);
set_page_dirty(page);
put_page(page);
unlock_page(page);
}
mutex_unlock(&inode->i_mutex);
(*off)+=rlen;
gwf(printk("<0>" "GSFS write rlen:%lu\n",rlen));
kfree(pages);
if(filp->f_flags & O_SYNC){
write_inode_now(inode,1);
}
return rlen;
}