ssize_t /* bytes written, or (-) error */
xfs_write(
bhv_desc_t *bdp,
struct kiocb *iocb,
const struct iovec *iovp,
unsigned int segs,
loff_t *offset,
int ioflags,
cred_t *credp)
{
struct file *file = iocb->ki_filp;
size_t size = 0;
xfs_inode_t *xip;
xfs_mount_t *mp;
ssize_t ret;
int error = 0;
xfs_fsize_t isize, new_size;
xfs_fsize_t n, limit;
xfs_iocore_t *io;
vnode_t *vp;
unsigned long seg;
int iolock;
int eventsent = 0;
vrwlock_t locktype;
XFS_STATS_INC(xs_write_calls);
vp = BHV_TO_VNODE(bdp);
vn_trace_entry(vp, "xfs_write", (inst_t *)__return_address);
xip = XFS_BHVTOI(bdp);
/* START copy & waste from filemap.c */
for (seg = 0; seg < segs; seg++) {
const struct iovec *iv = &iovp[seg];
/*
* If any segment has a negative length, or the cumulative
* length ever wraps negative then return -EINVAL.
*/
size += iv->iov_len;
if (unlikely((ssize_t)(size|iv->iov_len) < 0))
return XFS_ERROR(-EINVAL);
}
/* END copy & waste from filemap.c */
if (size == 0)
return 0;
io = &(xip->i_iocore);
mp = io->io_mount;
xfs_check_frozen(mp, bdp, XFS_FREEZE_WRITE);
if (XFS_FORCED_SHUTDOWN(mp)) {
return -EIO;
}
if (ioflags & IO_ISDIRECT) {
pb_target_t *target =
(xip->i_d.di_flags & XFS_DIFLAG_REALTIME) ?
mp->m_rtdev_targp : mp->m_ddev_targp;
if ((*offset & target->pbr_smask) ||
(size & target->pbr_smask)) {
return XFS_ERROR(-EINVAL);
}
iolock = XFS_IOLOCK_SHARED;
locktype = VRWLOCK_WRITE_DIRECT;
} else {
iolock = XFS_IOLOCK_EXCL;
locktype = VRWLOCK_WRITE;
}
xfs_ilock(xip, XFS_ILOCK_EXCL|iolock);
isize = xip->i_d.di_size;
limit = XFS_MAXIOFFSET(mp);
if (file->f_flags & O_APPEND)
*offset = isize;
start:
n = limit - *offset;
if (n <= 0) {
xfs_iunlock(xip, XFS_ILOCK_EXCL|iolock);
return -EFBIG;
}
if (n < size)
size = n;
new_size = *offset + size;
if (new_size > isize) {
io->io_new_size = new_size;
}
if ((DM_EVENT_ENABLED(vp->v_vfsp, xip, DM_EVENT_WRITE) &&
!(ioflags & IO_INVIS) && !eventsent)) {
loff_t savedsize = *offset;
xfs_iunlock(xip, XFS_ILOCK_EXCL);
error = XFS_SEND_DATA(xip->i_mount, DM_EVENT_WRITE, vp,
*offset, size,
FILP_DELAY_FLAG(file), &locktype);
if (error) {
xfs_iunlock(xip, iolock);
return -error;
}
xfs_ilock(xip, XFS_ILOCK_EXCL);
eventsent = 1;
/*
* The iolock was dropped and reaquired 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) &&
savedsize != xip->i_d.di_size) {
*offset = isize = xip->i_d.di_size;
goto start;
}
}
/*
* On Linux, generic_file_write updates the times even if
* no data is copied in so long as the write had a size.
*
* We must update xfs' times since revalidate will overcopy xfs.
*/
if (size && !(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 (!(ioflags & IO_ISDIRECT) && (*offset > isize && isize)) {
error = xfs_zero_eof(BHV_TO_VNODE(bdp), io, *offset,
isize, *offset + size);
if (error) {
xfs_iunlock(xip, XFS_ILOCK_EXCL|iolock);
return(-error);
}
}
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 (error) {
xfs_iunlock(xip, iolock);
return -error;
}
}
retry:
if (ioflags & IO_ISDIRECT) {
xfs_inval_cached_pages(vp, &xip->i_iocore, *offset, 1, 1);
}
ret = generic_file_aio_write_nolock(iocb, iovp, segs, offset);
if ((ret == -ENOSPC) &&
DM_EVENT_ENABLED(vp->v_vfsp, xip, DM_EVENT_NOSPACE) &&
!(ioflags & IO_INVIS)) {
xfs_rwunlock(bdp, locktype);
error = XFS_SEND_NAMESP(xip->i_mount, DM_EVENT_NOSPACE, vp,
DM_RIGHT_NULL, vp, DM_RIGHT_NULL, NULL, NULL,
0, 0, 0); /* Delay flag intentionally unused */
if (error)
return -error;
xfs_rwlock(bdp, locktype);
*offset = xip->i_d.di_size;
goto retry;
}
if (*offset > xip->i_d.di_size) {
xfs_ilock(xip, XFS_ILOCK_EXCL);
if (*offset > xip->i_d.di_size) {
struct inode *inode = LINVFS_GET_IP(vp);
xip->i_d.di_size = *offset;
i_size_write(inode, *offset);
xip->i_update_core = 1;
xip->i_update_size = 1;
}
xfs_iunlock(xip, XFS_ILOCK_EXCL);
}
if (ret <= 0) {
xfs_rwunlock(bdp, locktype);
return ret;
}
XFS_STATS_ADD(xs_write_bytes, ret);
/* Handle various SYNC-type writes */
if ((file->f_flags & O_SYNC) || IS_SYNC(file->f_dentry->d_inode)) {
/*
* If we're treating this as O_DSYNC and we have not updated the
* size, force the log.
*/
if (!(mp->m_flags & XFS_MOUNT_OSYNCISOSYNC)
&& !(xip->i_update_size)) {
/*
* If an allocation transaction occurred
* without extending the size, then we have to force
* the log up the proper point to ensure that the
* allocation is permanent. We can't count on
* the fact that buffered writes lock out direct I/O
* writes - the direct I/O write could have extended
* the size nontransactionally, then finished before
* we started. xfs_write_file will think that the file
* didn't grow but the update isn't safe unless the
* size change is logged.
*
* Force the log if we've committed a transaction
* against the inode or if someone else has and
* the commit record hasn't gone to disk (e.g.
* the inode is pinned). This guarantees that
* all changes affecting the inode are permanent
* when we return.
*/
xfs_inode_log_item_t *iip;
xfs_lsn_t lsn;
iip = xip->i_itemp;
if (iip && iip->ili_last_lsn) {
lsn = iip->ili_last_lsn;
xfs_log_force(mp, lsn,
XFS_LOG_FORCE | XFS_LOG_SYNC);
} else if (xfs_ipincount(xip) > 0) {
xfs_log_force(mp, (xfs_lsn_t)0,
XFS_LOG_FORCE | XFS_LOG_SYNC);
}
} else {
xfs_trans_t *tp;
/*
* O_SYNC or O_DSYNC _with_ a size update are handled
* the same way.
*
* If the write was synchronous then we need to make
* sure that the inode modification time is permanent.
* We'll have updated the timestamp above, so here
* we use a synchronous transaction to log the inode.
* It's not fast, but it's necessary.
*
* If this a dsync write and the size got changed
* non-transactionally, then we need to ensure that
* the size change gets logged in a synchronous
* transaction.
*/
tp = xfs_trans_alloc(mp, XFS_TRANS_WRITE_SYNC);
if ((error = xfs_trans_reserve(tp, 0,
XFS_SWRITE_LOG_RES(mp),
0, 0, 0))) {
/* Transaction reserve failed */
xfs_trans_cancel(tp, 0);
} else {
/* Transaction reserve successful */
xfs_ilock(xip, XFS_ILOCK_EXCL);
xfs_trans_ijoin(tp, xip, XFS_ILOCK_EXCL);
xfs_trans_ihold(tp, xip);
xfs_trans_log_inode(tp, xip, XFS_ILOG_CORE);
xfs_trans_set_sync(tp);
error = xfs_trans_commit(tp, 0, (xfs_lsn_t)0);
xfs_iunlock(xip, XFS_ILOCK_EXCL);
}
}
} /* (ioflags & O_SYNC) */
xfs_rwunlock(bdp, locktype);
return(ret);
}
static ssize_t raw_file_write(struct file *file, const char *buf,
size_t count, loff_t *ppos)
{
struct iovec local_iov = { .iov_base = (void *)buf, .iov_len = count };
return generic_file_write_nolock(file, &local_iov, 1, ppos);
}
static ssize_t raw_file_aio_write(struct kiocb *iocb, const char *buf,
size_t count, loff_t pos)
{
struct iovec local_iov = { .iov_base = (void *)buf, .iov_len = count };
return generic_file_aio_write_nolock(iocb, &local_iov, 1, &iocb->ki_pos);
}
static struct file_operations raw_fops = {
.read = generic_file_read,
.aio_read = generic_file_aio_read,
.write = raw_file_write,
.aio_write = raw_file_aio_write,
.open = raw_open,
.release= raw_release,
.ioctl = raw_ioctl,
.readv = generic_file_readv,
.writev = generic_file_writev,
.owner = THIS_MODULE,
};
static struct file_operations raw_ctl_fops = {
.ioctl = raw_ctl_ioctl,
.open = raw_open,
.owner = THIS_MODULE,
};
static int __init raw_init(void)
{
int i;
register_chrdev(RAW_MAJOR, "raw", &raw_fops);
devfs_mk_cdev(MKDEV(RAW_MAJOR, 0),
S_IFCHR | S_IRUGO | S_IWUGO,
"raw/rawctl");
for (i = 1; i < MAX_RAW_MINORS; i++)
devfs_mk_cdev(MKDEV(RAW_MAJOR, i),
S_IFCHR | S_IRUGO | S_IWUGO,
"raw/raw%d", i);
return 0;
}
static void __exit raw_exit(void)
{
int i;
for (i = 1; i < MAX_RAW_MINORS; i++)
devfs_remove("raw/raw%d", i);
devfs_remove("raw/rawctl");
devfs_remove("raw");
unregister_chrdev(RAW_MAJOR, "raw");
}
static ssize_t raw_file_write(struct file *file, const char __user *buf,
size_t count, loff_t *ppos)
{
struct iovec local_iov = {
.iov_base = (char __user *)buf,
.iov_len = count
};
return generic_file_write_nolock(file, &local_iov, 1, ppos);
}
static ssize_t raw_file_aio_write(struct kiocb *iocb, const char __user *buf,
size_t count, loff_t pos)
{
struct iovec local_iov = {
.iov_base = (char __user *)buf,
.iov_len = count
};
return generic_file_aio_write_nolock(iocb, &local_iov, 1, &iocb->ki_pos);
}
static struct file_operations raw_fops = {
.read = generic_file_read,
.aio_read = generic_file_aio_read,
.write = raw_file_write,
.aio_write = raw_file_aio_write,
.open = raw_open,
.release= raw_release,
.ioctl = raw_ioctl,
.readv = generic_file_readv,
.writev = generic_file_writev,
.owner = THIS_MODULE,
};
static struct file_operations raw_ctl_fops = {
.ioctl = raw_ctl_ioctl,
.open = raw_open,
.owner = THIS_MODULE,
};
static struct cdev raw_cdev = {
.kobj = {.name = "raw", },
.owner = THIS_MODULE,
};
static int __init raw_init(void)
{
int i;
dev_t dev = MKDEV(RAW_MAJOR, 0);
if (register_chrdev_region(dev, MAX_RAW_MINORS, "raw"))
goto error;
cdev_init(&raw_cdev, &raw_fops);
if (cdev_add(&raw_cdev, dev, MAX_RAW_MINORS)) {
kobject_put(&raw_cdev.kobj);
unregister_chrdev_region(dev, MAX_RAW_MINORS);
goto error;
}
devfs_mk_cdev(MKDEV(RAW_MAJOR, 0),
S_IFCHR | S_IRUGO | S_IWUGO,
"raw/rawctl");
for (i = 1; i < MAX_RAW_MINORS; i++)
devfs_mk_cdev(MKDEV(RAW_MAJOR, i),
S_IFCHR | S_IRUGO | S_IWUGO,
"raw/raw%d", i);
return 0;
error:
printk(KERN_ERR "error register raw device\n");
return 1;
}
