STATIC loff_t
xfs_seek_hole(
struct file *file,
loff_t start)
{
struct inode *inode = file->f_mapping->host;
struct xfs_inode *ip = XFS_I(inode);
struct xfs_mount *mp = ip->i_mount;
loff_t uninitialized_var(offset);
xfs_fsize_t isize;
xfs_fileoff_t fsbno;
xfs_filblks_t end;
uint lock;
int error;
if (XFS_FORCED_SHUTDOWN(mp))
return -XFS_ERROR(EIO);
lock = xfs_ilock_data_map_shared(ip);
isize = i_size_read(inode);
if (start >= isize) {
error = ENXIO;
goto out_unlock;
}
fsbno = XFS_B_TO_FSBT(mp, start);
end = XFS_B_TO_FSB(mp, isize);
for (;;) {
struct xfs_bmbt_irec map[2];
int nmap = 2;
unsigned int i;
error = xfs_bmapi_read(ip, fsbno, end - fsbno, map, &nmap,
XFS_BMAPI_ENTIRE);
if (error)
goto out_unlock;
/* No extents at given offset, must be beyond EOF */
if (nmap == 0) {
error = ENXIO;
goto out_unlock;
}
for (i = 0; i < nmap; i++) {
offset = max_t(loff_t, start,
XFS_FSB_TO_B(mp, map[i].br_startoff));
/* Landed in a hole */
if (map[i].br_startblock == HOLESTARTBLOCK)
goto out;
/*
* Landed in an unwritten extent, try to search hole
* from page cache.
*/
if (map[i].br_state == XFS_EXT_UNWRITTEN) {
if (xfs_find_get_desired_pgoff(inode, &map[i],
HOLE_OFF, &offset))
goto out;
}
}
/*
* map[0] contains data or its unwritten but contains
* data in page cache, probably means that we are
* reading after EOF. We should fix offset to point
* to the end of the file(i.e., there is an implicit
* hole at the end of any file).
*/
if (nmap == 1) {
offset = isize;
break;
}
ASSERT(i > 1);
/*
* Both mappings contains data, proceed to the next round of
* search if the current reading offset not beyond or hit EOF.
*/
fsbno = map[i - 1].br_startoff + map[i - 1].br_blockcount;
start = XFS_FSB_TO_B(mp, fsbno);
if (start >= isize) {
offset = isize;
break;
}
}
out:
/*
* At this point, we must have found a hole. However, the returned
* offset may be bigger than the file size as it may be aligned to
* page boundary for unwritten extents, we need to deal with this
* situation in particular.
*/
offset = min_t(loff_t, offset, isize);
offset = vfs_setpos(file, offset, inode->i_sb->s_maxbytes);
out_unlock:
xfs_iunlock(ip, lock);
if (error)
return -error;
return offset;
}
STATIC ssize_t
xfs_file_aio_read(
struct kiocb *iocb,
const struct iovec *iovp,
unsigned long nr_segs,
loff_t pos)
{
struct file *file = iocb->ki_filp;
struct inode *inode = file->f_mapping->host;
struct xfs_inode *ip = XFS_I(inode);
struct xfs_mount *mp = ip->i_mount;
size_t size = 0;
ssize_t ret = 0;
int ioflags = 0;
xfs_fsize_t n;
XFS_STATS_INC(xs_read_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;
ret = generic_segment_checks(iovp, &nr_segs, &size, VERIFY_WRITE);
if (ret < 0)
return ret;
if (unlikely(ioflags & IO_ISDIRECT)) {
xfs_buftarg_t *target =
XFS_IS_REALTIME_INODE(ip) ?
mp->m_rtdev_targp : mp->m_ddev_targp;
if ((iocb->ki_pos & target->bt_smask) ||
(size & target->bt_smask)) {
if (iocb->ki_pos == i_size_read(inode))
return 0;
return -XFS_ERROR(EINVAL);
}
}
n = mp->m_super->s_maxbytes - iocb->ki_pos;
if (n <= 0 || size == 0)
return 0;
if (n < size)
size = n;
if (XFS_FORCED_SHUTDOWN(mp))
return -EIO;
/*
* Locking is a bit tricky here. If we take an exclusive lock
* for direct IO, we effectively serialise all new concurrent
* read IO to this file and block it behind IO that is currently in
* progress because IO in progress holds the IO lock shared. We only
* need to hold the lock exclusive to blow away the page cache, so
* only take lock exclusively if the page cache needs invalidation.
* This allows the normal direct IO case of no page cache pages to
* proceeed concurrently without serialisation.
*/
xfs_rw_ilock(ip, XFS_IOLOCK_SHARED);
if ((ioflags & IO_ISDIRECT) && inode->i_mapping->nrpages) {
xfs_rw_iunlock(ip, XFS_IOLOCK_SHARED);
xfs_rw_ilock(ip, XFS_IOLOCK_EXCL);
if (inode->i_mapping->nrpages) {
ret = -xfs_flushinval_pages(ip,
(iocb->ki_pos & PAGE_CACHE_MASK),
-1, FI_REMAPF_LOCKED);
if (ret) {
xfs_rw_iunlock(ip, XFS_IOLOCK_EXCL);
return ret;
}
}
xfs_rw_ilock_demote(ip, XFS_IOLOCK_EXCL);
}
trace_xfs_file_read(ip, size, iocb->ki_pos, ioflags);
ret = generic_file_aio_read(iocb, iovp, nr_segs, iocb->ki_pos);
if (ret > 0)
XFS_STATS_ADD(xs_read_bytes, ret);
xfs_rw_iunlock(ip, XFS_IOLOCK_SHARED);
return ret;
}
STATIC loff_t
xfs_seek_data(
struct file *file,
loff_t start,
u32 type)
{
struct inode *inode = file->f_mapping->host;
struct xfs_inode *ip = XFS_I(inode);
struct xfs_mount *mp = ip->i_mount;
struct xfs_bmbt_irec map[2];
int nmap = 2;
loff_t uninitialized_var(offset);
xfs_fsize_t isize;
xfs_fileoff_t fsbno;
xfs_filblks_t end;
uint lock;
int error;
lock = xfs_ilock_map_shared(ip);
isize = i_size_read(inode);
if (start >= isize) {
error = ENXIO;
goto out_unlock;
}
fsbno = XFS_B_TO_FSBT(mp, start);
/*
* Try to read extents from the first block indicated
* by fsbno to the end block of the file.
*/
end = XFS_B_TO_FSB(mp, isize);
error = xfs_bmapi_read(ip, fsbno, end - fsbno, map, &nmap,
XFS_BMAPI_ENTIRE);
if (error)
goto out_unlock;
/*
* Treat unwritten extent as data extent since it might
* contains dirty data in page cache.
*/
if (map[0].br_startblock != HOLESTARTBLOCK) {
offset = max_t(loff_t, start,
XFS_FSB_TO_B(mp, map[0].br_startoff));
} else {
if (nmap == 1) {
error = ENXIO;
goto out_unlock;
}
offset = max_t(loff_t, start,
XFS_FSB_TO_B(mp, map[1].br_startoff));
}
if (offset != file->f_pos)
file->f_pos = offset;
out_unlock:
xfs_iunlock_map_shared(ip, lock);
if (error)
return -error;
return offset;
}
STATIC int
xfs_file_fsync(
struct file *file,
struct dentry *dentry,
int datasync)
{
struct xfs_inode *ip = XFS_I(dentry->d_inode);
struct xfs_trans *tp;
int error = 0;
int log_flushed = 0;
xfs_itrace_entry(ip);
if (XFS_FORCED_SHUTDOWN(ip->i_mount))
return -XFS_ERROR(EIO);
xfs_iflags_clear(ip, XFS_ITRUNCATED);
/*
* We always need to make sure that the required inode state is safe on
* disk. The inode might be clean but we still might need to force the
* log because of committed transactions that haven't hit the disk yet.
* Likewise, there could be unflushed non-transactional changes to the
* inode core that have to go to disk and this requires us to issue
* a synchronous transaction to capture these changes correctly.
*
* This code relies on the assumption that if the i_update_core field
* of the inode is clear and the inode is unpinned then it is clean
* and no action is required.
*/
xfs_ilock(ip, XFS_ILOCK_SHARED);
/*
* First check if the VFS inode is marked dirty. All the dirtying
* of non-transactional updates no goes through mark_inode_dirty*,
* which allows us to distinguish beteeen pure timestamp updates
* and i_size updates which need to be caught for fdatasync.
* After that also theck for the dirty state in the XFS inode, which
* might gets cleared when the inode gets written out via the AIL
* or xfs_iflush_cluster.
*/
if (((dentry->d_inode->i_state & I_DIRTY_DATASYNC) ||
((dentry->d_inode->i_state & I_DIRTY_SYNC) && !datasync)) &&
ip->i_update_core) {
/*
* Kick off a transaction to log the inode core to get the
* updates. The sync transaction will also force the log.
*/
xfs_iunlock(ip, XFS_ILOCK_SHARED);
tp = xfs_trans_alloc(ip->i_mount, XFS_TRANS_FSYNC_TS);
error = xfs_trans_reserve(tp, 0,
XFS_FSYNC_TS_LOG_RES(ip->i_mount), 0, 0, 0);
if (error) {
xfs_trans_cancel(tp, 0);
return -error;
}
xfs_ilock(ip, XFS_ILOCK_EXCL);
/*
* Note - it's possible that we might have pushed ourselves out
* of the way during trans_reserve which would flush the inode.
* But there's no guarantee that the inode buffer has actually
* gone out yet (it's delwri). Plus the buffer could be pinned
* anyway if it's part of an inode in another recent
* transaction. So we play it safe and fire off the
* transaction anyway.
*/
xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
xfs_trans_ihold(tp, ip);
xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
xfs_trans_set_sync(tp);
error = _xfs_trans_commit(tp, 0, &log_flushed);
xfs_iunlock(ip, XFS_ILOCK_EXCL);
} else {
/*
* Timestamps/size haven't changed since last inode flush or
* inode transaction commit. That means either nothing got
* written or a transaction committed which caught the updates.
* If the latter happened and the transaction hasn't hit the
* disk yet, the inode will be still be pinned. If it is,
* force the log.
*/
if (xfs_ipincount(ip)) {
error = _xfs_log_force_lsn(ip->i_mount,
ip->i_itemp->ili_last_lsn,
XFS_LOG_SYNC, &log_flushed);
}
xfs_iunlock(ip, XFS_ILOCK_SHARED);
}
if (ip->i_mount->m_flags & XFS_MOUNT_BARRIER) {
/*
* If the log write didn't issue an ordered tag we need
* to flush the disk cache for the data device now.
*/
if (!log_flushed)
xfs_blkdev_issue_flush(ip->i_mount->m_ddev_targp);
/*
* If this inode is on the RT dev we need to flush that
* cache as well.
*/
if (XFS_IS_REALTIME_INODE(ip))
xfs_blkdev_issue_flush(ip->i_mount->m_rtdev_targp);
}
return -error;
}
STATIC int
xfs_map_blocks(
struct inode *inode,
loff_t offset,
struct xfs_bmbt_irec *imap,
int type,
int nonblocking)
{
struct xfs_inode *ip = XFS_I(inode);
struct xfs_mount *mp = ip->i_mount;
ssize_t count = 1 << inode->i_blkbits;
xfs_fileoff_t offset_fsb, end_fsb;
int error = 0;
int bmapi_flags = XFS_BMAPI_ENTIRE;
int nimaps = 1;
if (XFS_FORCED_SHUTDOWN(mp))
return -XFS_ERROR(EIO);
if (type == IO_UNWRITTEN)
bmapi_flags |= XFS_BMAPI_IGSTATE;
if (!xfs_ilock_nowait(ip, XFS_ILOCK_SHARED)) {
if (nonblocking)
return -XFS_ERROR(EAGAIN);
xfs_ilock(ip, XFS_ILOCK_SHARED);
}
ASSERT(ip->i_d.di_format != XFS_DINODE_FMT_BTREE ||
(ip->i_df.if_flags & XFS_IFEXTENTS));
ASSERT(offset <= mp->m_maxioffset);
if (offset + count > mp->m_maxioffset)
count = mp->m_maxioffset - offset;
end_fsb = XFS_B_TO_FSB(mp, (xfs_ufsize_t)offset + count);
offset_fsb = XFS_B_TO_FSBT(mp, offset);
error = xfs_bmapi_read(ip, offset_fsb, end_fsb - offset_fsb,
imap, &nimaps, bmapi_flags);
xfs_iunlock(ip, XFS_ILOCK_SHARED);
if (error)
return -XFS_ERROR(error);
if (type == IO_DELALLOC &&
(!nimaps || isnullstartblock(imap->br_startblock))) {
error = xfs_iomap_write_allocate(ip, offset, count, imap);
if (!error)
trace_xfs_map_blocks_alloc(ip, offset, count, type, imap);
return -XFS_ERROR(error);
}
#ifdef DEBUG
if (type == IO_UNWRITTEN) {
ASSERT(nimaps);
ASSERT(imap->br_startblock != HOLESTARTBLOCK);
ASSERT(imap->br_startblock != DELAYSTARTBLOCK);
}
#endif
if (nimaps)
trace_xfs_map_blocks_found(ip, offset, count, type, imap);
return 0;
}
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;
int iolock;
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;
xfs_wait_for_freeze(ip->i_mount, SB_FREEZE_WRITE);
if (XFS_FORCED_SHUTDOWN(ip->i_mount))
return -EIO;
if (unlikely(file->f_flags & O_DIRECT))
ret = xfs_file_dio_aio_write(iocb, iovp, nr_segs, pos,
ocount, &iolock);
else
ret = xfs_file_buffered_aio_write(iocb, iovp, nr_segs, pos,
ocount, &iolock);
xfs_aio_write_isize_update(inode, &iocb->ki_pos, ret);
if (ret <= 0)
goto out_unlock;
/* Handle various SYNC-type writes */
if ((file->f_flags & O_DSYNC) || IS_SYNC(inode)) {
loff_t end = pos + ret - 1;
int error, error2;
xfs_rw_iunlock(ip, iolock);
error = filemap_write_and_wait_range(mapping, pos, end);
xfs_rw_ilock(ip, iolock);
error2 = -xfs_file_fsync(file,
(file->f_flags & __O_SYNC) ? 0 : 1);
if (error)
ret = error;
else if (error2)
ret = error2;
}
out_unlock:
xfs_aio_write_newsize_update(ip);
xfs_rw_iunlock(ip, iolock);
return ret;
}
STATIC ssize_t
xfs_file_splice_write(
struct pipe_inode_info *pipe,
struct file *outfilp,
loff_t *ppos,
size_t count,
unsigned int flags)
{
struct inode *inode = outfilp->f_mapping->host;
struct xfs_inode *ip = XFS_I(inode);
struct xfs_mount *mp = ip->i_mount;
xfs_fsize_t isize, new_size;
int ioflags = 0;
ssize_t ret;
XFS_STATS_INC(xs_write_calls);
if (outfilp->f_mode & FMODE_NOCMTIME)
ioflags |= IO_INVIS;
if (XFS_FORCED_SHUTDOWN(ip->i_mount))
return -EIO;
xfs_ilock(ip, XFS_IOLOCK_EXCL);
if (DM_EVENT_ENABLED(ip, DM_EVENT_WRITE) && !(ioflags & IO_INVIS)) {
int iolock = XFS_IOLOCK_EXCL;
int error;
error = XFS_SEND_DATA(mp, DM_EVENT_WRITE, ip, *ppos, count,
FILP_DELAY_FLAG(outfilp), &iolock);
if (error) {
xfs_iunlock(ip, XFS_IOLOCK_EXCL);
return -error;
}
}
new_size = *ppos + count;
xfs_ilock(ip, XFS_ILOCK_EXCL);
if (new_size > ip->i_size)
ip->i_new_size = new_size;
xfs_iunlock(ip, XFS_ILOCK_EXCL);
trace_xfs_file_splice_write(ip, count, *ppos, ioflags);
ret = generic_file_splice_write(pipe, outfilp, ppos, count, flags);
if (ret > 0)
XFS_STATS_ADD(xs_write_bytes, ret);
isize = i_size_read(inode);
if (unlikely(ret < 0 && ret != -EFAULT && *ppos > isize))
*ppos = isize;
if (*ppos > ip->i_size) {
xfs_ilock(ip, XFS_ILOCK_EXCL);
if (*ppos > ip->i_size)
ip->i_size = *ppos;
xfs_iunlock(ip, XFS_ILOCK_EXCL);
}
if (ip->i_new_size) {
xfs_ilock(ip, XFS_ILOCK_EXCL);
ip->i_new_size = 0;
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, XFS_IOLOCK_EXCL);
return ret;
}
STATIC int
xfs_file_readdir(
struct file *filp,
void *dirent,
filldir_t filldir)
{
struct inode *inode = filp->f_path.dentry->d_inode;
xfs_inode_t *ip = XFS_I(inode);
struct hack_callback buf;
struct hack_dirent *de;
int error;
loff_t size;
int eof = 0;
xfs_off_t start_offset, curr_offset, offset;
/*
* Try fairly hard to get memory
*/
buf.len = PAGE_CACHE_SIZE;
do {
buf.dirent = kmalloc(buf.len, GFP_KERNEL);
if (buf.dirent)
break;
buf.len >>= 1;
} while (buf.len >= 1024);
if (!buf.dirent)
return -ENOMEM;
curr_offset = filp->f_pos;
if (curr_offset == 0x7fffffff)
offset = 0xffffffff;
else
offset = filp->f_pos;
while (!eof) {
unsigned int reclen;
start_offset = offset;
buf.used = 0;
error = -xfs_readdir(ip, &buf, buf.len, &offset,
xfs_hack_filldir);
if (error || offset == start_offset) {
size = 0;
break;
}
size = buf.used;
de = (struct hack_dirent *)buf.dirent;
curr_offset = de->offset /* & 0x7fffffff */;
while (size > 0) {
if (filldir(dirent, de->name, de->namlen,
curr_offset & 0x7fffffff,
de->ino, de->d_type)) {
goto done;
}
reclen = ALIGN(sizeof(struct hack_dirent) + de->namlen,
sizeof(u64));
size -= reclen;
de = (struct hack_dirent *)((char *)de + reclen);
curr_offset = de->offset /* & 0x7fffffff */;
}
}
done:
if (!error) {
if (size == 0)
filp->f_pos = offset & 0x7fffffff;
else if (de)
filp->f_pos = curr_offset;
}
kfree(buf.dirent);
return error;
}
/*
* ioctl interface for swapext
*/
int
xfs_swapext(
xfs_swapext_t *sxp)
{
xfs_inode_t *ip, *tip;
struct file *file, *tmp_file;
int error = 0;
/* Pull information for the target fd */
file = fget((int)sxp->sx_fdtarget);
if (!file) {
error = XFS_ERROR(EINVAL);
goto out;
}
if (!(file->f_mode & FMODE_WRITE) ||
!(file->f_mode & FMODE_READ) ||
(file->f_flags & O_APPEND)) {
error = XFS_ERROR(EBADF);
goto out_put_file;
}
tmp_file = fget((int)sxp->sx_fdtmp);
if (!tmp_file) {
error = XFS_ERROR(EINVAL);
goto out_put_file;
}
if (!(tmp_file->f_mode & FMODE_WRITE) ||
!(tmp_file->f_mode & FMODE_READ) ||
(tmp_file->f_flags & O_APPEND)) {
error = XFS_ERROR(EBADF);
goto out_put_tmp_file;
}
if (IS_SWAPFILE(file->f_path.dentry->d_inode) ||
IS_SWAPFILE(tmp_file->f_path.dentry->d_inode)) {
error = XFS_ERROR(EINVAL);
goto out_put_tmp_file;
}
ip = XFS_I(file->f_path.dentry->d_inode);
tip = XFS_I(tmp_file->f_path.dentry->d_inode);
if (ip->i_mount != tip->i_mount) {
error = XFS_ERROR(EINVAL);
goto out_put_tmp_file;
}
if (ip->i_ino == tip->i_ino) {
error = XFS_ERROR(EINVAL);
goto out_put_tmp_file;
}
if (XFS_FORCED_SHUTDOWN(ip->i_mount)) {
error = XFS_ERROR(EIO);
goto out_put_tmp_file;
}
error = xfs_swap_extents(ip, tip, sxp);
out_put_tmp_file:
fput(tmp_file);
out_put_file:
fput(file);
out:
return error;
}
STATIC int
xfs_vn_mknod(
struct inode *dir,
struct dentry *dentry,
int mode,
dev_t rdev)
{
struct inode *ip;
bhv_vnode_t *vp = NULL, *dvp = vn_from_inode(dir);
xfs_acl_t *default_acl = NULL;
attrexists_t test_default_acl = _ACL_DEFAULT_EXISTS;
int error;
/*
* Irix uses Missed'em'V split, but doesn't want to see
* the upper 5 bits of (14bit) major.
*/
if (unlikely(!sysv_valid_dev(rdev) || MAJOR(rdev) & ~0x1ff))
return -EINVAL;
if (unlikely(test_default_acl && test_default_acl(dvp))) {
if (!_ACL_ALLOC(default_acl)) {
return -ENOMEM;
}
if (!_ACL_GET_DEFAULT(dvp, default_acl)) {
_ACL_FREE(default_acl);
default_acl = NULL;
}
}
if (IS_POSIXACL(dir) && !default_acl && xfs_has_fs_struct(current))
mode &= ~current->fs->umask;
switch (mode & S_IFMT) {
case S_IFCHR: case S_IFBLK: case S_IFIFO: case S_IFSOCK:
rdev = sysv_encode_dev(rdev);
case S_IFREG:
error = xfs_create(XFS_I(dir), dentry, mode, rdev, &vp, NULL);
break;
case S_IFDIR:
error = xfs_mkdir(XFS_I(dir), dentry, mode, &vp, NULL);
break;
default:
error = EINVAL;
break;
}
if (unlikely(!error)) {
error = xfs_init_security(vp, dir);
if (error)
xfs_cleanup_inode(dir, vp, dentry, mode);
}
if (unlikely(default_acl)) {
if (!error) {
error = _ACL_INHERIT(vp, mode, default_acl);
if (!error)
xfs_iflags_set(XFS_I(vp), XFS_IMODIFIED);
else
xfs_cleanup_inode(dir, vp, dentry, mode);
}
_ACL_FREE(default_acl);
}
if (likely(!error)) {
ASSERT(vp);
ip = vn_to_inode(vp);
if (S_ISDIR(mode))
xfs_validate_fields(ip);
d_instantiate(dentry, ip);
xfs_validate_fields(dir);
}
return -error;
}
struct posix_acl *
xfs_get_acl(struct inode *inode, int type)
{
struct xfs_inode *ip = XFS_I(inode);
struct posix_acl *acl;
struct xfs_acl *xfs_acl;
unsigned char *ea_name;
int error;
int len;
acl = get_cached_acl(inode, type);
if (acl != ACL_NOT_CACHED)
return acl;
trace_xfs_get_acl(ip);
switch (type) {
case ACL_TYPE_ACCESS:
ea_name = SGI_ACL_FILE;
break;
case ACL_TYPE_DEFAULT:
ea_name = SGI_ACL_DEFAULT;
break;
default:
BUG();
}
/*
* If we have a cached ACLs value just return it, not need to
* go out to the disk.
*/
len = XFS_ACL_MAX_SIZE(ip->i_mount);
xfs_acl = kzalloc(len, GFP_KERNEL);
if (!xfs_acl)
return ERR_PTR(-ENOMEM);
error = -xfs_attr_get(ip, ea_name, (unsigned char *)xfs_acl,
&len, ATTR_ROOT);
if (error) {
/*
* If the attribute doesn't exist make sure we have a negative
* cache entry, for any other error assume it is transient and
* leave the cache entry as ACL_NOT_CACHED.
*/
if (error == -ENOATTR) {
acl = NULL;
goto out_update_cache;
}
goto out;
}
acl = xfs_acl_from_disk(xfs_acl, XFS_ACL_MAX_ENTRIES(ip->i_mount));
if (IS_ERR(acl))
goto out;
out_update_cache:
set_cached_acl(inode, type, acl);
out:
kfree(xfs_acl);
return acl;
}
STATIC ssize_t
xfs_file_aio_read(
struct kiocb *iocb,
const struct iovec *iovp,
unsigned long nr_segs,
loff_t pos)
{
struct file *file = iocb->ki_filp;
struct inode *inode = file->f_mapping->host;
struct xfs_inode *ip = XFS_I(inode);
struct xfs_mount *mp = ip->i_mount;
size_t size = 0;
ssize_t ret = 0;
int ioflags = 0;
xfs_fsize_t n;
XFS_STATS_INC(xs_read_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;
ret = generic_segment_checks(iovp, &nr_segs, &size, VERIFY_WRITE);
if (ret < 0)
return ret;
if (unlikely(ioflags & IO_ISDIRECT)) {
xfs_buftarg_t *target =
XFS_IS_REALTIME_INODE(ip) ?
mp->m_rtdev_targp : mp->m_ddev_targp;
/* DIO must be aligned to device logical sector size */
if ((pos | size) & target->bt_logical_sectormask) {
if (pos == i_size_read(inode))
return 0;
return -XFS_ERROR(EINVAL);
}
}
n = mp->m_super->s_maxbytes - pos;
if (n <= 0 || size == 0)
return 0;
if (n < size)
size = n;
if (XFS_FORCED_SHUTDOWN(mp))
return -EIO;
/*
* Locking is a bit tricky here. If we take an exclusive lock
* for direct IO, we effectively serialise all new concurrent
* read IO to this file and block it behind IO that is currently in
* progress because IO in progress holds the IO lock shared. We only
* need to hold the lock exclusive to blow away the page cache, so
* only take lock exclusively if the page cache needs invalidation.
* This allows the normal direct IO case of no page cache pages to
* proceeed concurrently without serialisation.
*/
xfs_rw_ilock(ip, XFS_IOLOCK_SHARED);
if ((ioflags & IO_ISDIRECT) && inode->i_mapping->nrpages) {
xfs_rw_iunlock(ip, XFS_IOLOCK_SHARED);
xfs_rw_ilock(ip, XFS_IOLOCK_EXCL);
if (inode->i_mapping->nrpages) {
ret = filemap_write_and_wait_range(
VFS_I(ip)->i_mapping,
pos, pos + size - 1);
if (ret) {
xfs_rw_iunlock(ip, XFS_IOLOCK_EXCL);
return ret;
}
/*
* Invalidate whole pages. This can return an error if
* we fail to invalidate a page, but this should never
* happen on XFS. Warn if it does fail.
*/
ret = invalidate_inode_pages2_range(VFS_I(ip)->i_mapping,
pos >> PAGE_CACHE_SHIFT,
(pos + size - 1) >> PAGE_CACHE_SHIFT);
WARN_ON_ONCE(ret);
ret = 0;
}
int
xfs_ioc_space(
struct file *filp,
unsigned int cmd,
xfs_flock64_t *bf)
{
struct inode *inode = file_inode(filp);
struct xfs_inode *ip = XFS_I(inode);
struct iattr iattr;
enum xfs_prealloc_flags flags = 0;
uint iolock = XFS_IOLOCK_EXCL;
int error;
/*
* Only allow the sys admin to reserve space unless
* unwritten extents are enabled.
*/
if (!xfs_sb_version_hasextflgbit(&ip->i_mount->m_sb) &&
!capable(CAP_SYS_ADMIN))
return -EPERM;
if (inode->i_flags & (S_IMMUTABLE|S_APPEND))
return -EPERM;
if (!(filp->f_mode & FMODE_WRITE))
return -EBADF;
if (!S_ISREG(inode->i_mode))
return -EINVAL;
if (filp->f_flags & O_DSYNC)
flags |= XFS_PREALLOC_SYNC;
if (filp->f_mode & FMODE_NOCMTIME)
flags |= XFS_PREALLOC_INVISIBLE;
error = mnt_want_write_file(filp);
if (error)
return error;
xfs_ilock(ip, iolock);
error = xfs_break_layouts(inode, &iolock);
if (error)
goto out_unlock;
xfs_ilock(ip, XFS_MMAPLOCK_EXCL);
iolock |= XFS_MMAPLOCK_EXCL;
switch (bf->l_whence) {
case 0: /*SEEK_SET*/
break;
case 1: /*SEEK_CUR*/
bf->l_start += filp->f_pos;
break;
case 2: /*SEEK_END*/
bf->l_start += XFS_ISIZE(ip);
break;
default:
error = -EINVAL;
goto out_unlock;
}
/*
* length of <= 0 for resv/unresv/zero is invalid. length for
* alloc/free is ignored completely and we have no idea what userspace
* might have set it to, so set it to zero to allow range
* checks to pass.
*/
switch (cmd) {
case XFS_IOC_ZERO_RANGE:
case XFS_IOC_RESVSP:
case XFS_IOC_RESVSP64:
case XFS_IOC_UNRESVSP:
case XFS_IOC_UNRESVSP64:
if (bf->l_len <= 0) {
error = -EINVAL;
goto out_unlock;
}
break;
default:
bf->l_len = 0;
break;
}
if (bf->l_start < 0 ||
bf->l_start > inode->i_sb->s_maxbytes ||
bf->l_start + bf->l_len < 0 ||
bf->l_start + bf->l_len >= inode->i_sb->s_maxbytes) {
error = -EINVAL;
goto out_unlock;
}
switch (cmd) {
case XFS_IOC_ZERO_RANGE:
flags |= XFS_PREALLOC_SET;
error = xfs_zero_file_space(ip, bf->l_start, bf->l_len);
break;
case XFS_IOC_RESVSP:
case XFS_IOC_RESVSP64:
flags |= XFS_PREALLOC_SET;
error = xfs_alloc_file_space(ip, bf->l_start, bf->l_len,
XFS_BMAPI_PREALLOC);
break;
case XFS_IOC_UNRESVSP:
case XFS_IOC_UNRESVSP64:
error = xfs_free_file_space(ip, bf->l_start, bf->l_len);
break;
case XFS_IOC_ALLOCSP:
case XFS_IOC_ALLOCSP64:
case XFS_IOC_FREESP:
case XFS_IOC_FREESP64:
flags |= XFS_PREALLOC_CLEAR;
if (bf->l_start > XFS_ISIZE(ip)) {
error = xfs_alloc_file_space(ip, XFS_ISIZE(ip),
bf->l_start - XFS_ISIZE(ip), 0);
if (error)
goto out_unlock;
}
iattr.ia_valid = ATTR_SIZE;
iattr.ia_size = bf->l_start;
error = xfs_vn_setattr_size(file_dentry(filp), &iattr);
break;
default:
ASSERT(0);
error = -EINVAL;
}
if (error)
goto out_unlock;
error = xfs_update_prealloc_flags(ip, flags);
out_unlock:
xfs_iunlock(ip, iolock);
mnt_drop_write_file(filp);
return error;
}
STATIC long
xfs_file_fallocate(
struct file *file,
int mode,
loff_t offset,
loff_t len)
{
struct inode *inode = file_inode(file);
struct xfs_inode *ip = XFS_I(inode);
struct xfs_trans *tp;
long error;
loff_t new_size = 0;
if (!S_ISREG(inode->i_mode))
return -EINVAL;
if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE |
FALLOC_FL_COLLAPSE_RANGE | FALLOC_FL_ZERO_RANGE))
return -EOPNOTSUPP;
xfs_ilock(ip, XFS_IOLOCK_EXCL);
if (mode & FALLOC_FL_PUNCH_HOLE) {
error = xfs_free_file_space(ip, offset, len);
if (error)
goto out_unlock;
} else if (mode & FALLOC_FL_COLLAPSE_RANGE) {
unsigned blksize_mask = (1 << inode->i_blkbits) - 1;
if (offset & blksize_mask || len & blksize_mask) {
error = -EINVAL;
goto out_unlock;
}
ASSERT(offset + len < i_size_read(inode));
new_size = i_size_read(inode) - len;
error = xfs_collapse_file_space(ip, offset, len);
if (error)
goto out_unlock;
} else {
if (!(mode & FALLOC_FL_KEEP_SIZE) &&
offset + len > i_size_read(inode)) {
new_size = offset + len;
error = -inode_newsize_ok(inode, new_size);
if (error)
goto out_unlock;
}
if (mode & FALLOC_FL_ZERO_RANGE)
error = xfs_zero_file_space(ip, offset, len);
else
error = xfs_alloc_file_space(ip, offset, len,
XFS_BMAPI_PREALLOC);
if (error)
goto out_unlock;
}
tp = xfs_trans_alloc(ip->i_mount, XFS_TRANS_WRITEID);
error = xfs_trans_reserve(tp, &M_RES(ip->i_mount)->tr_writeid, 0, 0);
if (error) {
xfs_trans_cancel(tp, 0);
goto out_unlock;
}
xfs_ilock(ip, XFS_ILOCK_EXCL);
xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
ip->i_d.di_mode &= ~S_ISUID;
if (ip->i_d.di_mode & S_IXGRP)
ip->i_d.di_mode &= ~S_ISGID;
if (!(mode & (FALLOC_FL_PUNCH_HOLE | FALLOC_FL_COLLAPSE_RANGE)))
ip->i_d.di_flags |= XFS_DIFLAG_PREALLOC;
xfs_trans_ichgtime(tp, ip, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
if (file->f_flags & O_DSYNC)
xfs_trans_set_sync(tp);
error = xfs_trans_commit(tp, 0);
if (error)
goto out_unlock;
/* Change file size if needed */
if (new_size) {
struct iattr iattr;
iattr.ia_valid = ATTR_SIZE;
iattr.ia_size = new_size;
error = xfs_setattr_size(ip, &iattr);
}
out_unlock:
xfs_iunlock(ip, XFS_IOLOCK_EXCL);
return -error;
}
/*
* xfs_find_handle maps from userspace xfs_fsop_handlereq structure to
* a file or fs handle.
*
* XFS_IOC_PATH_TO_FSHANDLE
* returns fs handle for a mount point or path within that mount point
* XFS_IOC_FD_TO_HANDLE
* returns full handle for a FD opened in user space
* XFS_IOC_PATH_TO_HANDLE
* returns full handle for a path
*/
STATIC int
xfs_find_handle(
unsigned int cmd,
void __user *arg)
{
int hsize;
xfs_handle_t handle;
xfs_fsop_handlereq_t hreq;
struct inode *inode;
if (copy_from_user(&hreq, arg, sizeof(hreq)))
return -XFS_ERROR(EFAULT);
memset((char *)&handle, 0, sizeof(handle));
switch (cmd) {
case XFS_IOC_PATH_TO_FSHANDLE:
case XFS_IOC_PATH_TO_HANDLE: {
struct nameidata nd;
int error;
error = user_path_walk_link((const char __user *)hreq.path, &nd);
if (error)
return error;
ASSERT(nd.path.dentry);
ASSERT(nd.path.dentry->d_inode);
inode = igrab(nd.path.dentry->d_inode);
path_put(&nd.path);
break;
}
case XFS_IOC_FD_TO_HANDLE: {
struct file *file;
file = fget(hreq.fd);
if (!file)
return -EBADF;
ASSERT(file->f_path.dentry);
ASSERT(file->f_path.dentry->d_inode);
inode = igrab(file->f_path.dentry->d_inode);
fput(file);
break;
}
default:
ASSERT(0);
return -XFS_ERROR(EINVAL);
}
if (inode->i_sb->s_magic != XFS_SB_MAGIC) {
/* we're not in XFS anymore, Toto */
iput(inode);
return -XFS_ERROR(EINVAL);
}
switch (inode->i_mode & S_IFMT) {
case S_IFREG:
case S_IFDIR:
case S_IFLNK:
break;
default:
iput(inode);
return -XFS_ERROR(EBADF);
}
/* now we can grab the fsid */
memcpy(&handle.ha_fsid, XFS_I(inode)->i_mount->m_fixedfsid,
sizeof(xfs_fsid_t));
hsize = sizeof(xfs_fsid_t);
if (cmd != XFS_IOC_PATH_TO_FSHANDLE) {
xfs_inode_t *ip = XFS_I(inode);
int lock_mode;
/* need to get access to the xfs_inode to read the generation */
lock_mode = xfs_ilock_map_shared(ip);
/* fill in fid section of handle from inode */
handle.ha_fid.fid_len = sizeof(xfs_fid_t) -
sizeof(handle.ha_fid.fid_len);
handle.ha_fid.fid_pad = 0;
handle.ha_fid.fid_gen = ip->i_d.di_gen;
handle.ha_fid.fid_ino = ip->i_ino;
xfs_iunlock_map_shared(ip, lock_mode);
hsize = XFS_HSIZE(handle);
}
/* now copy our handle into the user buffer & write out the size */
if (copy_to_user(hreq.ohandle, &handle, hsize) ||
copy_to_user(hreq.ohandlen, &hsize, sizeof(__s32))) {
iput(inode);
return -XFS_ERROR(EFAULT);
}
iput(inode);
return 0;
}
/*
* Link a range of blocks from one file to another.
*/
int
xfs_reflink_remap_range(
struct file *file_in,
loff_t pos_in,
struct file *file_out,
loff_t pos_out,
u64 len,
bool is_dedupe)
{
struct inode *inode_in = file_inode(file_in);
struct xfs_inode *src = XFS_I(inode_in);
struct inode *inode_out = file_inode(file_out);
struct xfs_inode *dest = XFS_I(inode_out);
struct xfs_mount *mp = src->i_mount;
bool same_inode = (inode_in == inode_out);
xfs_fileoff_t sfsbno, dfsbno;
xfs_filblks_t fsblen;
xfs_extlen_t cowextsize;
ssize_t ret;
if (!xfs_sb_version_hasreflink(&mp->m_sb))
return -EOPNOTSUPP;
if (XFS_FORCED_SHUTDOWN(mp))
return -EIO;
/* Lock both files against IO */
lock_two_nondirectories(inode_in, inode_out);
if (same_inode)
xfs_ilock(src, XFS_MMAPLOCK_EXCL);
else
xfs_lock_two_inodes(src, dest, XFS_MMAPLOCK_EXCL);
/* Check file eligibility and prepare for block sharing. */
ret = -EINVAL;
/* Don't reflink realtime inodes */
if (XFS_IS_REALTIME_INODE(src) || XFS_IS_REALTIME_INODE(dest))
goto out_unlock;
/* Don't share DAX file data for now. */
if (IS_DAX(inode_in) || IS_DAX(inode_out))
goto out_unlock;
ret = vfs_clone_file_prep_inodes(inode_in, pos_in, inode_out, pos_out,
&len, is_dedupe);
if (ret <= 0)
goto out_unlock;
trace_xfs_reflink_remap_range(src, pos_in, len, dest, pos_out);
/* Set flags and remap blocks. */
ret = xfs_reflink_set_inode_flag(src, dest);
if (ret)
goto out_unlock;
dfsbno = XFS_B_TO_FSBT(mp, pos_out);
sfsbno = XFS_B_TO_FSBT(mp, pos_in);
fsblen = XFS_B_TO_FSB(mp, len);
ret = xfs_reflink_remap_blocks(src, sfsbno, dest, dfsbno, fsblen,
pos_out + len);
if (ret)
goto out_unlock;
/* Zap any page cache for the destination file's range. */
truncate_inode_pages_range(&inode_out->i_data, pos_out,
PAGE_ALIGN(pos_out + len) - 1);
/*
* Carry the cowextsize hint from src to dest if we're sharing the
* entire source file to the entire destination file, the source file
* has a cowextsize hint, and the destination file does not.
*/
cowextsize = 0;
if (pos_in == 0 && len == i_size_read(inode_in) &&
(src->i_d.di_flags2 & XFS_DIFLAG2_COWEXTSIZE) &&
pos_out == 0 && len >= i_size_read(inode_out) &&
!(dest->i_d.di_flags2 & XFS_DIFLAG2_COWEXTSIZE))
cowextsize = src->i_d.di_cowextsize;
ret = xfs_reflink_update_dest(dest, pos_out + len, cowextsize,
is_dedupe);
out_unlock:
xfs_iunlock(src, XFS_MMAPLOCK_EXCL);
if (!same_inode)
xfs_iunlock(dest, XFS_MMAPLOCK_EXCL);
unlock_two_nondirectories(inode_in, inode_out);
if (ret)
trace_xfs_reflink_remap_range_error(dest, ret, _RET_IP_);
return ret;
}
/*
* xfs_file_dio_aio_write - handle direct IO writes
*
* Lock the inode appropriately to prepare for and issue a direct IO write.
* By separating it from the buffered write path we remove all the tricky to
* follow locking changes and looping.
*
* If there are cached pages or we're extending the file, we need IOLOCK_EXCL
* until we're sure the bytes at the new EOF have been zeroed and/or the cached
* pages are flushed out.
*
* In most cases the direct IO writes will be done holding IOLOCK_SHARED
* allowing them to be done in parallel with reads and other direct IO writes.
* However, if the IO is not aligned to filesystem blocks, the direct IO layer
* needs to do sub-block zeroing and that requires serialisation against other
* direct IOs to the same block. In this case we need to serialise the
* submission of the unaligned IOs so that we don't get racing block zeroing in
* the dio layer. To avoid the problem with aio, we also need to wait for
* outstanding IOs to complete so that unwritten extent conversion is completed
* before we try to map the overlapping block. This is currently implemented by
* hitting it with a big hammer (i.e. xfs_ioend_wait()).
*
* Returns with locks held indicated by @iolock and errors indicated by
* negative return values.
*/
STATIC ssize_t
xfs_file_dio_aio_write(
struct kiocb *iocb,
const struct iovec *iovp,
unsigned long nr_segs,
loff_t pos,
size_t ocount,
int *iolock)
{
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;
size_t count = ocount;
int unaligned_io = 0;
struct xfs_buftarg *target = XFS_IS_REALTIME_INODE(ip) ?
mp->m_rtdev_targp : mp->m_ddev_targp;
*iolock = 0;
if ((pos & target->bt_smask) || (count & target->bt_smask))
return -XFS_ERROR(EINVAL);
if ((pos & mp->m_blockmask) || ((pos + count) & mp->m_blockmask))
unaligned_io = 1;
if (unaligned_io || mapping->nrpages || pos > ip->i_size)
*iolock = XFS_IOLOCK_EXCL;
else
*iolock = XFS_IOLOCK_SHARED;
xfs_rw_ilock(ip, XFS_ILOCK_EXCL | *iolock);
ret = xfs_file_aio_write_checks(file, &pos, &count, iolock);
if (ret)
return ret;
if (mapping->nrpages) {
WARN_ON(*iolock != XFS_IOLOCK_EXCL);
ret = -xfs_flushinval_pages(ip, (pos & PAGE_CACHE_MASK), -1,
FI_REMAPF_LOCKED);
if (ret)
return ret;
}
/*
* If we are doing unaligned IO, wait for all other IO to drain,
* otherwise demote the lock if we had to flush cached pages
*/
if (unaligned_io)
xfs_ioend_wait(ip);
else if (*iolock == XFS_IOLOCK_EXCL) {
xfs_rw_ilock_demote(ip, XFS_IOLOCK_EXCL);
*iolock = XFS_IOLOCK_SHARED;
}
trace_xfs_file_direct_write(ip, count, iocb->ki_pos, 0);
ret = generic_file_direct_write(iocb, iovp,
&nr_segs, pos, &iocb->ki_pos, count, ocount);
/* No fallback to buffered IO on errors for XFS. */
ASSERT(ret < 0 || ret == count);
return ret;
}
STATIC int
xfs_file_fsync(
struct file *file,
loff_t start,
loff_t end,
int datasync)
{
struct inode *inode = file->f_mapping->host;
struct xfs_inode *ip = XFS_I(inode);
struct xfs_mount *mp = ip->i_mount;
struct xfs_trans *tp;
int error = 0;
int log_flushed = 0;
trace_xfs_file_fsync(ip);
error = filemap_write_and_wait_range(inode->i_mapping, start, end);
if (error)
return error;
if (XFS_FORCED_SHUTDOWN(mp))
return -XFS_ERROR(EIO);
xfs_iflags_clear(ip, XFS_ITRUNCATED);
xfs_ilock(ip, XFS_IOLOCK_SHARED);
xfs_ioend_wait(ip);
xfs_iunlock(ip, XFS_IOLOCK_SHARED);
if (mp->m_flags & XFS_MOUNT_BARRIER) {
/*
* If we have an RT and/or log subvolume we need to make sure
* to flush the write cache the device used for file data
* first. This is to ensure newly written file data make
* it to disk before logging the new inode size in case of
* an extending write.
*/
if (XFS_IS_REALTIME_INODE(ip))
xfs_blkdev_issue_flush(mp->m_rtdev_targp);
else if (mp->m_logdev_targp != mp->m_ddev_targp)
xfs_blkdev_issue_flush(mp->m_ddev_targp);
}
/*
* We always need to make sure that the required inode state is safe on
* disk. The inode might be clean but we still might need to force the
* log because of committed transactions that haven't hit the disk yet.
* Likewise, there could be unflushed non-transactional changes to the
* inode core that have to go to disk and this requires us to issue
* a synchronous transaction to capture these changes correctly.
*
* This code relies on the assumption that if the i_update_core field
* of the inode is clear and the inode is unpinned then it is clean
* and no action is required.
*/
xfs_ilock(ip, XFS_ILOCK_SHARED);
/*
* First check if the VFS inode is marked dirty. All the dirtying
* of non-transactional updates no goes through mark_inode_dirty*,
* which allows us to distinguish beteeen pure timestamp updates
* and i_size updates which need to be caught for fdatasync.
* After that also theck for the dirty state in the XFS inode, which
* might gets cleared when the inode gets written out via the AIL
* or xfs_iflush_cluster.
*/
if (((inode->i_state & I_DIRTY_DATASYNC) ||
((inode->i_state & I_DIRTY_SYNC) && !datasync)) &&
ip->i_update_core) {
/*
* Kick off a transaction to log the inode core to get the
* updates. The sync transaction will also force the log.
*/
xfs_iunlock(ip, XFS_ILOCK_SHARED);
tp = xfs_trans_alloc(mp, XFS_TRANS_FSYNC_TS);
error = xfs_trans_reserve(tp, 0,
XFS_FSYNC_TS_LOG_RES(mp), 0, 0, 0);
if (error) {
xfs_trans_cancel(tp, 0);
return -error;
}
xfs_ilock(ip, XFS_ILOCK_EXCL);
/*
* Note - it's possible that we might have pushed ourselves out
* of the way during trans_reserve which would flush the inode.
* But there's no guarantee that the inode buffer has actually
* gone out yet (it's delwri). Plus the buffer could be pinned
* anyway if it's part of an inode in another recent
* transaction. So we play it safe and fire off the
* transaction anyway.
*/
xfs_trans_ijoin(tp, ip);
xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
xfs_trans_set_sync(tp);
error = _xfs_trans_commit(tp, 0, &log_flushed);
xfs_iunlock(ip, XFS_ILOCK_EXCL);
} else {
/*
* Timestamps/size haven't changed since last inode flush or
* inode transaction commit. That means either nothing got
* written or a transaction committed which caught the updates.
* If the latter happened and the transaction hasn't hit the
* disk yet, the inode will be still be pinned. If it is,
* force the log.
*/
if (xfs_ipincount(ip)) {
error = _xfs_log_force_lsn(mp,
ip->i_itemp->ili_last_lsn,
XFS_LOG_SYNC, &log_flushed);
}
xfs_iunlock(ip, XFS_ILOCK_SHARED);
}
/*
* If we only have a single device, and the log force about was
* a no-op we might have to flush the data device cache here.
* This can only happen for fdatasync/O_DSYNC if we were overwriting
* an already allocated file and thus do not have any metadata to
* commit.
*/
if ((mp->m_flags & XFS_MOUNT_BARRIER) &&
mp->m_logdev_targp == mp->m_ddev_targp &&
!XFS_IS_REALTIME_INODE(ip) &&
!log_flushed)
xfs_blkdev_issue_flush(mp->m_ddev_targp);
return -error;
}
STATIC ssize_t
xfs_file_aio_read(
struct kiocb *iocb,
const struct iovec *iovp,
unsigned long nr_segs,
loff_t pos)
{
struct file *file = iocb->ki_filp;
struct inode *inode = file->f_mapping->host;
struct xfs_inode *ip = XFS_I(inode);
struct xfs_mount *mp = ip->i_mount;
size_t size = 0;
ssize_t ret = 0;
int ioflags = 0;
xfs_fsize_t n;
unsigned long seg;
XFS_STATS_INC(xs_read_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;
/* START copy & waste from filemap.c */
for (seg = 0; seg < nr_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 (unlikely(ioflags & IO_ISDIRECT)) {
xfs_buftarg_t *target =
XFS_IS_REALTIME_INODE(ip) ?
mp->m_rtdev_targp : mp->m_ddev_targp;
if ((iocb->ki_pos & target->bt_smask) ||
(size & target->bt_smask)) {
if (iocb->ki_pos == ip->i_size)
return 0;
return -XFS_ERROR(EINVAL);
}
}
n = XFS_MAXIOFFSET(mp) - iocb->ki_pos;
if (n <= 0 || size == 0)
return 0;
if (n < size)
size = n;
if (XFS_FORCED_SHUTDOWN(mp))
return -EIO;
if (unlikely(ioflags & IO_ISDIRECT))
mutex_lock(&inode->i_mutex);
xfs_ilock(ip, XFS_IOLOCK_SHARED);
if (DM_EVENT_ENABLED(ip, DM_EVENT_READ) && !(ioflags & IO_INVIS)) {
int dmflags = FILP_DELAY_FLAG(file) | DM_SEM_FLAG_RD(ioflags);
int iolock = XFS_IOLOCK_SHARED;
ret = -XFS_SEND_DATA(mp, DM_EVENT_READ, ip, iocb->ki_pos, size,
dmflags, &iolock);
if (ret) {
xfs_iunlock(ip, XFS_IOLOCK_SHARED);
if (unlikely(ioflags & IO_ISDIRECT))
mutex_unlock(&inode->i_mutex);
return ret;
}
}
if (unlikely(ioflags & IO_ISDIRECT)) {
if (inode->i_mapping->nrpages) {
ret = -xfs_flushinval_pages(ip,
(iocb->ki_pos & PAGE_CACHE_MASK),
-1, FI_REMAPF_LOCKED);
}
mutex_unlock(&inode->i_mutex);
if (ret) {
xfs_iunlock(ip, XFS_IOLOCK_SHARED);
return ret;
}
}
trace_xfs_file_read(ip, size, iocb->ki_pos, ioflags);
ret = generic_file_aio_read(iocb, iovp, nr_segs, iocb->ki_pos);
if (ret > 0)
XFS_STATS_ADD(xs_read_bytes, ret);
xfs_iunlock(ip, XFS_IOLOCK_SHARED);
return ret;
}
/*
* xfs_find_handle maps from userspace xfs_fsop_handlereq structure to
* a file or fs handle.
*
* XFS_IOC_PATH_TO_FSHANDLE
* returns fs handle for a mount point or path within that mount point
* XFS_IOC_FD_TO_HANDLE
* returns full handle for a FD opened in user space
* XFS_IOC_PATH_TO_HANDLE
* returns full handle for a path
*/
int
xfs_find_handle(
unsigned int cmd,
xfs_fsop_handlereq_t *hreq)
{
int hsize;
xfs_handle_t handle;
struct inode *inode;
struct fd f = {0};
struct path path;
int error;
struct xfs_inode *ip;
if (cmd == XFS_IOC_FD_TO_HANDLE) {
f = fdget(hreq->fd);
if (!f.file)
return -EBADF;
inode = file_inode(f.file);
} else {
error = user_lpath((const char __user *)hreq->path, &path);
if (error)
return error;
inode = path.dentry->d_inode;
}
ip = XFS_I(inode);
/*
* We can only generate handles for inodes residing on a XFS filesystem,
* and only for regular files, directories or symbolic links.
*/
error = -EINVAL;
if (inode->i_sb->s_magic != XFS_SB_MAGIC)
goto out_put;
error = -EBADF;
if (!S_ISREG(inode->i_mode) &&
!S_ISDIR(inode->i_mode) &&
!S_ISLNK(inode->i_mode))
goto out_put;
memcpy(&handle.ha_fsid, ip->i_mount->m_fixedfsid, sizeof(xfs_fsid_t));
if (cmd == XFS_IOC_PATH_TO_FSHANDLE) {
/*
* This handle only contains an fsid, zero the rest.
*/
memset(&handle.ha_fid, 0, sizeof(handle.ha_fid));
hsize = sizeof(xfs_fsid_t);
} else {
int lock_mode;
lock_mode = xfs_ilock_map_shared(ip);
handle.ha_fid.fid_len = sizeof(xfs_fid_t) -
sizeof(handle.ha_fid.fid_len);
handle.ha_fid.fid_pad = 0;
handle.ha_fid.fid_gen = ip->i_d.di_gen;
handle.ha_fid.fid_ino = ip->i_ino;
xfs_iunlock_map_shared(ip, lock_mode);
hsize = XFS_HSIZE(handle);
}
error = -EFAULT;
if (hsize > sizeof handle || copy_to_user(hreq->ohandle, &handle, hsize) ||
copy_to_user(hreq->ohandlen, &hsize, sizeof(__s32)))
goto out_put;
error = 0;
out_put:
if (cmd == XFS_IOC_FD_TO_HANDLE)
fdput(f);
else
path_put(&path);
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);
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;
}
STATIC int
xfs_generic_create(
struct inode *dir,
struct dentry *dentry,
umode_t mode,
dev_t rdev,
bool tmpfile) /* unnamed file */
{
struct inode *inode;
struct xfs_inode *ip = NULL;
struct posix_acl *default_acl, *acl;
struct xfs_name name;
int error;
/*
* Irix uses Missed'em'V split, but doesn't want to see
* the upper 5 bits of (14bit) major.
*/
if (S_ISCHR(mode) || S_ISBLK(mode)) {
if (unlikely(!sysv_valid_dev(rdev) || MAJOR(rdev) & ~0x1ff))
return -EINVAL;
rdev = sysv_encode_dev(rdev);
} else {
rdev = 0;
}
error = posix_acl_create(dir, &mode, &default_acl, &acl);
if (error)
return error;
if (!tmpfile) {
xfs_dentry_to_name(&name, dentry, mode);
error = xfs_create(XFS_I(dir), &name, mode, rdev, &ip);
} else {
error = xfs_create_tmpfile(XFS_I(dir), dentry, mode, &ip);
}
if (unlikely(error))
goto out_free_acl;
inode = VFS_I(ip);
error = xfs_init_security(inode, dir, &dentry->d_name);
if (unlikely(error))
goto out_cleanup_inode;
#ifdef CONFIG_XFS_POSIX_ACL
if (default_acl) {
error = xfs_set_acl(inode, default_acl, ACL_TYPE_DEFAULT);
if (error)
goto out_cleanup_inode;
}
if (acl) {
error = xfs_set_acl(inode, acl, ACL_TYPE_ACCESS);
if (error)
goto out_cleanup_inode;
}
#endif
xfs_setup_iops(ip);
if (tmpfile)
d_tmpfile(dentry, inode);
else
d_instantiate(dentry, inode);
xfs_finish_inode_setup(ip);
out_free_acl:
if (default_acl)
posix_acl_release(default_acl);
if (acl)
posix_acl_release(acl);
return error;
out_cleanup_inode:
xfs_finish_inode_setup(ip);
if (!tmpfile)
xfs_cleanup_inode(dir, inode, dentry);
iput(inode);
goto out_free_acl;
}
/*
* Fast and loose check if this write could update the on-disk inode size.
*/
static inline bool xfs_ioend_is_append(struct xfs_ioend *ioend)
{
return ioend->io_offset + ioend->io_size >
XFS_I(ioend->io_inode)->i_d.di_size;
}
STATIC int
xfs_vn_mknod(
struct inode *dir,
struct dentry *dentry,
int mode,
dev_t rdev)
{
struct inode *inode;
struct xfs_inode *ip = NULL;
struct posix_acl *default_acl = NULL;
struct xfs_name name;
int error;
/*
* Irix uses Missed'em'V split, but doesn't want to see
* the upper 5 bits of (14bit) major.
*/
if (S_ISCHR(mode) || S_ISBLK(mode)) {
if (unlikely(!sysv_valid_dev(rdev) || MAJOR(rdev) & ~0x1ff))
return -EINVAL;
rdev = sysv_encode_dev(rdev);
} else {
rdev = 0;
}
if (IS_POSIXACL(dir)) {
default_acl = xfs_get_acl(dir, ACL_TYPE_DEFAULT);
if (IS_ERR(default_acl))
return PTR_ERR(default_acl);
if (!default_acl)
mode &= ~current_umask();
}
xfs_dentry_to_name(&name, dentry);
error = xfs_create(XFS_I(dir), &name, mode, rdev, &ip);
if (unlikely(error))
goto out_free_acl;
inode = VFS_I(ip);
error = xfs_init_security(inode, dir, &dentry->d_name);
if (unlikely(error))
goto out_cleanup_inode;
if (default_acl) {
error = -xfs_inherit_acl(inode, default_acl);
if (unlikely(error))
goto out_cleanup_inode;
posix_acl_release(default_acl);
}
d_instantiate(dentry, inode);
return -error;
out_cleanup_inode:
xfs_cleanup_inode(dir, inode, dentry);
out_free_acl:
posix_acl_release(default_acl);
return -error;
}
STATIC int
xfs_file_fsync(
struct file *file,
loff_t start,
loff_t end,
int datasync)
{
struct inode *inode = file->f_mapping->host;
struct xfs_inode *ip = XFS_I(inode);
struct xfs_mount *mp = ip->i_mount;
int error = 0;
int log_flushed = 0;
xfs_lsn_t lsn = 0;
trace_xfs_file_fsync(ip);
error = filemap_write_and_wait_range(inode->i_mapping, start, end);
if (error)
return error;
if (XFS_FORCED_SHUTDOWN(mp))
return -XFS_ERROR(EIO);
xfs_iflags_clear(ip, XFS_ITRUNCATED);
if (mp->m_flags & XFS_MOUNT_BARRIER) {
/*
* If we have an RT and/or log subvolume we need to make sure
* to flush the write cache the device used for file data
* first. This is to ensure newly written file data make
* it to disk before logging the new inode size in case of
* an extending write.
*/
if (XFS_IS_REALTIME_INODE(ip))
xfs_blkdev_issue_flush(mp->m_rtdev_targp);
else if (mp->m_logdev_targp != mp->m_ddev_targp)
xfs_blkdev_issue_flush(mp->m_ddev_targp);
}
/*
* All metadata updates are logged, which means that we just have
* to flush the log up to the latest LSN that touched the inode.
*/
xfs_ilock(ip, XFS_ILOCK_SHARED);
if (xfs_ipincount(ip)) {
if (!datasync ||
(ip->i_itemp->ili_fields & ~XFS_ILOG_TIMESTAMP))
lsn = ip->i_itemp->ili_last_lsn;
}
xfs_iunlock(ip, XFS_ILOCK_SHARED);
if (lsn)
error = _xfs_log_force_lsn(mp, lsn, XFS_LOG_SYNC, &log_flushed);
/*
* If we only have a single device, and the log force about was
* a no-op we might have to flush the data device cache here.
* This can only happen for fdatasync/O_DSYNC if we were overwriting
* an already allocated file and thus do not have any metadata to
* commit.
*/
if ((mp->m_flags & XFS_MOUNT_BARRIER) &&
mp->m_logdev_targp == mp->m_ddev_targp &&
!XFS_IS_REALTIME_INODE(ip) &&
!log_flushed)
xfs_blkdev_issue_flush(mp->m_ddev_targp);
return -error;
}
STATIC int
xfs_fs_encode_fh(
struct dentry *dentry,
__u32 *fh,
int *max_len,
int connectable)
{
struct fid *fid = (struct fid *)fh;
struct xfs_fid64 *fid64 = (struct xfs_fid64 *)fh;
struct inode *inode = dentry->d_inode;
int fileid_type;
int len;
/* Directories don't need their parent encoded, they have ".." */
if (S_ISDIR(inode->i_mode) || !connectable)
fileid_type = FILEID_INO32_GEN;
else
fileid_type = FILEID_INO32_GEN_PARENT;
/*
* If the the filesystem may contain 64bit inode numbers, we need
* to use larger file handles that can represent them.
*
* While we only allocate inodes that do not fit into 32 bits any
* large enough filesystem may contain them, thus the slightly
* confusing looking conditional below.
*/
if (!(XFS_M(inode->i_sb)->m_flags & XFS_MOUNT_SMALL_INUMS) ||
(XFS_M(inode->i_sb)->m_flags & XFS_MOUNT_32BITINODES))
fileid_type |= XFS_FILEID_TYPE_64FLAG;
/*
* Only encode if there is enough space given. In practice
* this means we can't export a filesystem with 64bit inodes
* over NFSv2 with the subtree_check export option; the other
* seven combinations work. The real answer is "don't use v2".
*/
len = xfs_fileid_length(fileid_type);
if (*max_len < len) {
*max_len = len;
return 255;
}
*max_len = len;
switch (fileid_type) {
case FILEID_INO32_GEN_PARENT:
spin_lock(&dentry->d_lock);
fid->i32.parent_ino = XFS_I(dentry->d_parent->d_inode)->i_ino;
fid->i32.parent_gen = dentry->d_parent->d_inode->i_generation;
spin_unlock(&dentry->d_lock);
/*FALLTHRU*/
case FILEID_INO32_GEN:
fid->i32.ino = XFS_I(inode)->i_ino;
fid->i32.gen = inode->i_generation;
break;
case FILEID_INO32_GEN_PARENT | XFS_FILEID_TYPE_64FLAG:
spin_lock(&dentry->d_lock);
fid64->parent_ino = XFS_I(dentry->d_parent->d_inode)->i_ino;
fid64->parent_gen = dentry->d_parent->d_inode->i_generation;
spin_unlock(&dentry->d_lock);
/*FALLTHRU*/
case FILEID_INO32_GEN | XFS_FILEID_TYPE_64FLAG:
fid64->ino = XFS_I(inode)->i_ino;
fid64->gen = inode->i_generation;
break;
}
return fileid_type;
}
/*
* xfs_file_dio_aio_write - handle direct IO writes
*
* Lock the inode appropriately to prepare for and issue a direct IO write.
* By separating it from the buffered write path we remove all the tricky to
* follow locking changes and looping.
*
* If there are cached pages or we're extending the file, we need IOLOCK_EXCL
* until we're sure the bytes at the new EOF have been zeroed and/or the cached
* pages are flushed out.
*
* In most cases the direct IO writes will be done holding IOLOCK_SHARED
* allowing them to be done in parallel with reads and other direct IO writes.
* However, if the IO is not aligned to filesystem blocks, the direct IO layer
* needs to do sub-block zeroing and that requires serialisation against other
* direct IOs to the same block. In this case we need to serialise the
* submission of the unaligned IOs so that we don't get racing block zeroing in
* the dio layer. To avoid the problem with aio, we also need to wait for
* outstanding IOs to complete so that unwritten extent conversion is completed
* before we try to map the overlapping block. This is currently implemented by
* hitting it with a big hammer (i.e. inode_dio_wait()).
*
* Returns with locks held indicated by @iolock and errors indicated by
* negative return values.
*/
STATIC ssize_t
xfs_file_dio_aio_write(
struct kiocb *iocb,
const struct iovec *iovp,
unsigned long nr_segs,
loff_t pos,
size_t ocount)
{
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;
size_t count = ocount;
int unaligned_io = 0;
int iolock;
struct xfs_buftarg *target = XFS_IS_REALTIME_INODE(ip) ?
mp->m_rtdev_targp : mp->m_ddev_targp;
if ((pos & target->bt_smask) || (count & target->bt_smask))
return -XFS_ERROR(EINVAL);
if ((pos & mp->m_blockmask) || ((pos + count) & mp->m_blockmask))
unaligned_io = 1;
/*
* We don't need to take an exclusive lock unless there page cache needs
* to be invalidated or unaligned IO is being executed. We don't need to
* consider the EOF extension case here because
* xfs_file_aio_write_checks() will relock the inode as necessary for
* EOF zeroing cases and fill out the new inode size as appropriate.
*/
if (unaligned_io || mapping->nrpages)
iolock = XFS_IOLOCK_EXCL;
else
iolock = XFS_IOLOCK_SHARED;
xfs_rw_ilock(ip, iolock);
/*
* Recheck if there are cached pages that need invalidate after we got
* the iolock to protect against other threads adding new pages while
* we were waiting for the iolock.
*/
if (mapping->nrpages && iolock == XFS_IOLOCK_SHARED) {
xfs_rw_iunlock(ip, iolock);
iolock = XFS_IOLOCK_EXCL;
xfs_rw_ilock(ip, iolock);
}
ret = xfs_file_aio_write_checks(file, &pos, &count, &iolock);
if (ret)
goto out;
if (mapping->nrpages) {
ret = -xfs_flushinval_pages(ip, (pos & PAGE_CACHE_MASK), -1,
FI_REMAPF_LOCKED);
if (ret)
goto out;
}
/*
* If we are doing unaligned IO, wait for all other IO to drain,
* otherwise demote the lock if we had to flush cached pages
*/
if (unaligned_io)
inode_dio_wait(inode);
else if (iolock == XFS_IOLOCK_EXCL) {
xfs_rw_ilock_demote(ip, XFS_IOLOCK_EXCL);
iolock = XFS_IOLOCK_SHARED;
}
trace_xfs_file_direct_write(ip, count, iocb->ki_pos, 0);
ret = generic_file_direct_write(iocb, iovp,
&nr_segs, pos, &iocb->ki_pos, count, ocount);
out:
xfs_rw_iunlock(ip, iolock);
/* No fallback to buffered IO on errors for XFS. */
ASSERT(ret < 0 || ret == count);
return ret;
}
int
xfs_ioctl(
xfs_inode_t *ip,
struct file *filp,
int ioflags,
unsigned int cmd,
void __user *arg)
{
struct inode *inode = filp->f_path.dentry->d_inode;
xfs_mount_t *mp = ip->i_mount;
int error;
xfs_itrace_entry(XFS_I(inode));
switch (cmd) {
case XFS_IOC_ALLOCSP:
case XFS_IOC_FREESP:
case XFS_IOC_RESVSP:
case XFS_IOC_UNRESVSP:
case XFS_IOC_ALLOCSP64:
case XFS_IOC_FREESP64:
case XFS_IOC_RESVSP64:
case XFS_IOC_UNRESVSP64:
/*
* Only allow the sys admin to reserve space unless
* unwritten extents are enabled.
*/
if (!xfs_sb_version_hasextflgbit(&mp->m_sb) &&
!capable(CAP_SYS_ADMIN))
return -EPERM;
return xfs_ioc_space(ip, inode, filp, ioflags, cmd, arg);
case XFS_IOC_DIOINFO: {
struct dioattr da;
xfs_buftarg_t *target =
XFS_IS_REALTIME_INODE(ip) ?
mp->m_rtdev_targp : mp->m_ddev_targp;
da.d_mem = da.d_miniosz = 1 << target->bt_sshift;
da.d_maxiosz = INT_MAX & ~(da.d_miniosz - 1);
if (copy_to_user(arg, &da, sizeof(da)))
return -XFS_ERROR(EFAULT);
return 0;
}
case XFS_IOC_FSBULKSTAT_SINGLE:
case XFS_IOC_FSBULKSTAT:
case XFS_IOC_FSINUMBERS:
return xfs_ioc_bulkstat(mp, cmd, arg);
case XFS_IOC_FSGEOMETRY_V1:
return xfs_ioc_fsgeometry_v1(mp, arg);
case XFS_IOC_FSGEOMETRY:
return xfs_ioc_fsgeometry(mp, arg);
case XFS_IOC_GETVERSION:
return put_user(inode->i_generation, (int __user *)arg);
case XFS_IOC_FSGETXATTR:
return xfs_ioc_fsgetxattr(ip, 0, arg);
case XFS_IOC_FSGETXATTRA:
return xfs_ioc_fsgetxattr(ip, 1, arg);
case XFS_IOC_FSSETXATTR:
return xfs_ioc_fssetxattr(ip, filp, arg);
case XFS_IOC_GETXFLAGS:
return xfs_ioc_getxflags(ip, arg);
case XFS_IOC_SETXFLAGS:
return xfs_ioc_setxflags(ip, filp, arg);
case XFS_IOC_FSSETDM: {
struct fsdmidata dmi;
if (copy_from_user(&dmi, arg, sizeof(dmi)))
return -XFS_ERROR(EFAULT);
error = xfs_set_dmattrs(ip, dmi.fsd_dmevmask,
dmi.fsd_dmstate);
return -error;
}
case XFS_IOC_GETBMAP:
case XFS_IOC_GETBMAPA:
return xfs_ioc_getbmap(ip, ioflags, cmd, arg);
case XFS_IOC_GETBMAPX:
return xfs_ioc_getbmapx(ip, arg);
case XFS_IOC_FD_TO_HANDLE:
case XFS_IOC_PATH_TO_HANDLE:
case XFS_IOC_PATH_TO_FSHANDLE:
return xfs_find_handle(cmd, arg);
case XFS_IOC_OPEN_BY_HANDLE:
return xfs_open_by_handle(mp, arg, filp, inode);
case XFS_IOC_FSSETDM_BY_HANDLE:
return xfs_fssetdm_by_handle(mp, arg, inode);
case XFS_IOC_READLINK_BY_HANDLE:
return xfs_readlink_by_handle(mp, arg, inode);
case XFS_IOC_ATTRLIST_BY_HANDLE:
return xfs_attrlist_by_handle(mp, arg, inode);
case XFS_IOC_ATTRMULTI_BY_HANDLE:
return xfs_attrmulti_by_handle(mp, arg, inode);
case XFS_IOC_SWAPEXT: {
error = xfs_swapext((struct xfs_swapext __user *)arg);
return -error;
}
case XFS_IOC_FSCOUNTS: {
xfs_fsop_counts_t out;
error = xfs_fs_counts(mp, &out);
if (error)
return -error;
if (copy_to_user(arg, &out, sizeof(out)))
return -XFS_ERROR(EFAULT);
return 0;
}
case XFS_IOC_SET_RESBLKS: {
xfs_fsop_resblks_t inout;
__uint64_t in;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
if (copy_from_user(&inout, arg, sizeof(inout)))
return -XFS_ERROR(EFAULT);
/* input parameter is passed in resblks field of structure */
in = inout.resblks;
error = xfs_reserve_blocks(mp, &in, &inout);
if (error)
return -error;
if (copy_to_user(arg, &inout, sizeof(inout)))
return -XFS_ERROR(EFAULT);
return 0;
}
case XFS_IOC_GET_RESBLKS: {
xfs_fsop_resblks_t out;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
error = xfs_reserve_blocks(mp, NULL, &out);
if (error)
return -error;
if (copy_to_user(arg, &out, sizeof(out)))
return -XFS_ERROR(EFAULT);
return 0;
}
case XFS_IOC_FSGROWFSDATA: {
xfs_growfs_data_t in;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
if (copy_from_user(&in, arg, sizeof(in)))
return -XFS_ERROR(EFAULT);
error = xfs_growfs_data(mp, &in);
return -error;
}
case XFS_IOC_FSGROWFSLOG: {
xfs_growfs_log_t in;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
if (copy_from_user(&in, arg, sizeof(in)))
return -XFS_ERROR(EFAULT);
error = xfs_growfs_log(mp, &in);
return -error;
}
case XFS_IOC_FSGROWFSRT: {
xfs_growfs_rt_t in;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
if (copy_from_user(&in, arg, sizeof(in)))
return -XFS_ERROR(EFAULT);
error = xfs_growfs_rt(mp, &in);
return -error;
}
case XFS_IOC_FREEZE:
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
if (inode->i_sb->s_frozen == SB_UNFROZEN)
freeze_bdev(inode->i_sb->s_bdev);
return 0;
case XFS_IOC_THAW:
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
if (inode->i_sb->s_frozen != SB_UNFROZEN)
thaw_bdev(inode->i_sb->s_bdev, inode->i_sb);
return 0;
case XFS_IOC_GOINGDOWN: {
__uint32_t in;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
if (get_user(in, (__uint32_t __user *)arg))
return -XFS_ERROR(EFAULT);
error = xfs_fs_goingdown(mp, in);
return -error;
}
case XFS_IOC_ERROR_INJECTION: {
xfs_error_injection_t in;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
if (copy_from_user(&in, arg, sizeof(in)))
return -XFS_ERROR(EFAULT);
error = xfs_errortag_add(in.errtag, mp);
return -error;
}
case XFS_IOC_ERROR_CLEARALL:
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
error = xfs_errortag_clearall(mp, 1);
return -error;
default:
return -ENOTTY;
}
}
/*
* Note: some of the ioctl's return positive numbers as a
* byte count indicating success, such as readlink_by_handle.
* So we don't "sign flip" like most other routines. This means
* true errors need to be returned as a negative value.
*/
long
xfs_file_ioctl(
struct file *filp,
unsigned int cmd,
unsigned long p)
{
struct inode *inode = filp->f_path.dentry->d_inode;
struct xfs_inode *ip = XFS_I(inode);
struct xfs_mount *mp = ip->i_mount;
void __user *arg = (void __user *)p;
int ioflags = 0;
int error;
if (filp->f_mode & FMODE_NOCMTIME)
ioflags |= IO_INVIS;
trace_xfs_file_ioctl(ip);
switch (cmd) {
case XFS_IOC_ALLOCSP:
case XFS_IOC_FREESP:
case XFS_IOC_RESVSP:
case XFS_IOC_UNRESVSP:
case XFS_IOC_ALLOCSP64:
case XFS_IOC_FREESP64:
case XFS_IOC_RESVSP64:
case XFS_IOC_UNRESVSP64: {
xfs_flock64_t bf;
if (copy_from_user(&bf, arg, sizeof(bf)))
return -XFS_ERROR(EFAULT);
return xfs_ioc_space(ip, inode, filp, ioflags, cmd, &bf);
}
case XFS_IOC_DIOINFO: {
struct dioattr da;
xfs_buftarg_t *target =
XFS_IS_REALTIME_INODE(ip) ?
mp->m_rtdev_targp : mp->m_ddev_targp;
da.d_mem = da.d_miniosz = 1 << target->bt_sshift;
da.d_maxiosz = INT_MAX & ~(da.d_miniosz - 1);
if (copy_to_user(arg, &da, sizeof(da)))
return -XFS_ERROR(EFAULT);
return 0;
}
case XFS_IOC_FSBULKSTAT_SINGLE:
case XFS_IOC_FSBULKSTAT:
case XFS_IOC_FSINUMBERS:
return xfs_ioc_bulkstat(mp, cmd, arg);
case XFS_IOC_FSGEOMETRY_V1:
return xfs_ioc_fsgeometry_v1(mp, arg);
case XFS_IOC_FSGEOMETRY:
return xfs_ioc_fsgeometry(mp, arg);
case XFS_IOC_GETVERSION:
return put_user(inode->i_generation, (int __user *)arg);
case XFS_IOC_FSGETXATTR:
return xfs_ioc_fsgetxattr(ip, 0, arg);
case XFS_IOC_FSGETXATTRA:
return xfs_ioc_fsgetxattr(ip, 1, arg);
case XFS_IOC_FSSETXATTR:
return xfs_ioc_fssetxattr(ip, filp, arg);
case XFS_IOC_GETXFLAGS:
return xfs_ioc_getxflags(ip, arg);
case XFS_IOC_SETXFLAGS:
return xfs_ioc_setxflags(ip, filp, arg);
case XFS_IOC_FSSETDM: {
struct fsdmidata dmi;
if (copy_from_user(&dmi, arg, sizeof(dmi)))
return -XFS_ERROR(EFAULT);
error = xfs_set_dmattrs(ip, dmi.fsd_dmevmask,
dmi.fsd_dmstate);
return -error;
}
case XFS_IOC_GETBMAP:
case XFS_IOC_GETBMAPA:
return xfs_ioc_getbmap(ip, ioflags, cmd, arg);
case XFS_IOC_GETBMAPX:
return xfs_ioc_getbmapx(ip, arg);
case XFS_IOC_FD_TO_HANDLE:
case XFS_IOC_PATH_TO_HANDLE:
case XFS_IOC_PATH_TO_FSHANDLE: {
xfs_fsop_handlereq_t hreq;
if (copy_from_user(&hreq, arg, sizeof(hreq)))
return -XFS_ERROR(EFAULT);
return xfs_find_handle(cmd, &hreq);
}
case XFS_IOC_OPEN_BY_HANDLE: {
xfs_fsop_handlereq_t hreq;
if (copy_from_user(&hreq, arg, sizeof(xfs_fsop_handlereq_t)))
return -XFS_ERROR(EFAULT);
return xfs_open_by_handle(filp, &hreq);
}
case XFS_IOC_FSSETDM_BY_HANDLE:
return xfs_fssetdm_by_handle(filp, arg);
case XFS_IOC_READLINK_BY_HANDLE: {
xfs_fsop_handlereq_t hreq;
if (copy_from_user(&hreq, arg, sizeof(xfs_fsop_handlereq_t)))
return -XFS_ERROR(EFAULT);
return xfs_readlink_by_handle(filp, &hreq);
}
case XFS_IOC_ATTRLIST_BY_HANDLE:
return xfs_attrlist_by_handle(filp, arg);
case XFS_IOC_ATTRMULTI_BY_HANDLE:
return xfs_attrmulti_by_handle(filp, arg);
case XFS_IOC_SWAPEXT: {
struct xfs_swapext sxp;
if (copy_from_user(&sxp, arg, sizeof(xfs_swapext_t)))
return -XFS_ERROR(EFAULT);
error = xfs_swapext(&sxp);
return -error;
}
case XFS_IOC_FSCOUNTS: {
xfs_fsop_counts_t out;
error = xfs_fs_counts(mp, &out);
if (error)
return -error;
if (copy_to_user(arg, &out, sizeof(out)))
return -XFS_ERROR(EFAULT);
return 0;
}
case XFS_IOC_SET_RESBLKS: {
xfs_fsop_resblks_t inout;
__uint64_t in;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
if (mp->m_flags & XFS_MOUNT_RDONLY)
return -XFS_ERROR(EROFS);
if (copy_from_user(&inout, arg, sizeof(inout)))
return -XFS_ERROR(EFAULT);
/* input parameter is passed in resblks field of structure */
in = inout.resblks;
error = xfs_reserve_blocks(mp, &in, &inout);
if (error)
return -error;
if (copy_to_user(arg, &inout, sizeof(inout)))
return -XFS_ERROR(EFAULT);
return 0;
}
case XFS_IOC_GET_RESBLKS: {
xfs_fsop_resblks_t out;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
error = xfs_reserve_blocks(mp, NULL, &out);
if (error)
return -error;
if (copy_to_user(arg, &out, sizeof(out)))
return -XFS_ERROR(EFAULT);
return 0;
}
case XFS_IOC_FSGROWFSDATA: {
xfs_growfs_data_t in;
if (copy_from_user(&in, arg, sizeof(in)))
return -XFS_ERROR(EFAULT);
error = xfs_growfs_data(mp, &in);
return -error;
}
case XFS_IOC_FSGROWFSLOG: {
xfs_growfs_log_t in;
if (copy_from_user(&in, arg, sizeof(in)))
return -XFS_ERROR(EFAULT);
error = xfs_growfs_log(mp, &in);
return -error;
}
case XFS_IOC_FSGROWFSRT: {
xfs_growfs_rt_t in;
if (copy_from_user(&in, arg, sizeof(in)))
return -XFS_ERROR(EFAULT);
error = xfs_growfs_rt(mp, &in);
return -error;
}
case XFS_IOC_GOINGDOWN: {
__uint32_t in;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
if (get_user(in, (__uint32_t __user *)arg))
return -XFS_ERROR(EFAULT);
error = xfs_fs_goingdown(mp, in);
return -error;
}
case XFS_IOC_ERROR_INJECTION: {
xfs_error_injection_t in;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
if (copy_from_user(&in, arg, sizeof(in)))
return -XFS_ERROR(EFAULT);
error = xfs_errortag_add(in.errtag, mp);
return -error;
}
case XFS_IOC_ERROR_CLEARALL:
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
error = xfs_errortag_clearall(mp, 1);
return -error;
default:
return -ENOTTY;
}
}
STATIC loff_t
xfs_seek_data(
struct file *file,
loff_t start)
{
struct inode *inode = file->f_mapping->host;
struct xfs_inode *ip = XFS_I(inode);
struct xfs_mount *mp = ip->i_mount;
loff_t uninitialized_var(offset);
xfs_fsize_t isize;
xfs_fileoff_t fsbno;
xfs_filblks_t end;
uint lock;
int error;
lock = xfs_ilock_data_map_shared(ip);
isize = i_size_read(inode);
if (start >= isize) {
error = ENXIO;
goto out_unlock;
}
/*
* Try to read extents from the first block indicated
* by fsbno to the end block of the file.
*/
fsbno = XFS_B_TO_FSBT(mp, start);
end = XFS_B_TO_FSB(mp, isize);
for (;;) {
struct xfs_bmbt_irec map[2];
int nmap = 2;
unsigned int i;
error = xfs_bmapi_read(ip, fsbno, end - fsbno, map, &nmap,
XFS_BMAPI_ENTIRE);
if (error)
goto out_unlock;
/* No extents at given offset, must be beyond EOF */
if (nmap == 0) {
error = ENXIO;
goto out_unlock;
}
for (i = 0; i < nmap; i++) {
offset = max_t(loff_t, start,
XFS_FSB_TO_B(mp, map[i].br_startoff));
/* Landed in a data extent */
if (map[i].br_startblock == DELAYSTARTBLOCK ||
(map[i].br_state == XFS_EXT_NORM &&
!isnullstartblock(map[i].br_startblock)))
goto out;
/*
* Landed in an unwritten extent, try to search data
* from page cache.
*/
if (map[i].br_state == XFS_EXT_UNWRITTEN) {
if (xfs_find_get_desired_pgoff(inode, &map[i],
DATA_OFF, &offset))
goto out;
}
}
/*
* map[0] is hole or its an unwritten extent but
* without data in page cache. Probably means that
* we are reading after EOF if nothing in map[1].
*/
if (nmap == 1) {
error = ENXIO;
goto out_unlock;
}
ASSERT(i > 1);
/*
* Nothing was found, proceed to the next round of search
* if reading offset not beyond or hit EOF.
*/
fsbno = map[i - 1].br_startoff + map[i - 1].br_blockcount;
start = XFS_FSB_TO_B(mp, fsbno);
if (start >= isize) {
error = ENXIO;
goto out_unlock;
}
}
out:
offset = vfs_setpos(file, offset, inode->i_sb->s_maxbytes);
out_unlock:
xfs_iunlock(ip, lock);
if (error)
return -error;
return offset;
}
