STATIC int
xfs_qm_scall_trunc_qfile(
struct xfs_mount *mp,
xfs_ino_t ino)
{
struct xfs_inode *ip;
struct xfs_trans *tp;
int error;
if (ino == NULLFSINO)
return 0;
error = xfs_iget(mp, NULL, ino, 0, 0, &ip);
if (error)
return error;
xfs_ilock(ip, XFS_IOLOCK_EXCL);
tp = xfs_trans_alloc(mp, XFS_TRANS_TRUNCATE_FILE);
error = xfs_trans_reserve(tp, &M_RES(mp)->tr_itruncate, 0, 0);
if (error) {
xfs_trans_cancel(tp, 0);
xfs_iunlock(ip, XFS_IOLOCK_EXCL);
goto out_put;
}
xfs_ilock(ip, XFS_ILOCK_EXCL);
xfs_trans_ijoin(tp, ip, 0);
ip->i_d.di_size = 0;
xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
error = xfs_itruncate_extents(&tp, ip, XFS_DATA_FORK, 0);
if (error) {
xfs_trans_cancel(tp, XFS_TRANS_RELEASE_LOG_RES |
XFS_TRANS_ABORT);
goto out_unlock;
}
ASSERT(ip->i_d.di_nextents == 0);
xfs_trans_ichgtime(tp, ip, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
error = xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES);
out_unlock:
xfs_iunlock(ip, XFS_ILOCK_EXCL | XFS_IOLOCK_EXCL);
out_put:
IRELE(ip);
return error;
}
void
libxfs_trans_ijoin_ref(
xfs_trans_t *tp,
xfs_inode_t *ip,
int lock_flags)
{
ASSERT(ip->i_transp == tp);
ASSERT(ip->i_itemp != NULL);
xfs_trans_ijoin(tp, ip, lock_flags);
#ifdef XACT_DEBUG
fprintf(stderr, "ijoin_ref'd inode %llu, transaction %p\n", ip->i_ino, tp);
#endif
}
/*
* Cancel CoW reservations for some byte range of an inode.
*
* If cancel_real is true this function cancels all COW fork extents for the
* inode; if cancel_real is false, real extents are not cleared.
*/
int
xfs_reflink_cancel_cow_range(
struct xfs_inode *ip,
xfs_off_t offset,
xfs_off_t count,
bool cancel_real)
{
struct xfs_trans *tp;
xfs_fileoff_t offset_fsb;
xfs_fileoff_t end_fsb;
int error;
trace_xfs_reflink_cancel_cow_range(ip, offset, count);
ASSERT(xfs_is_reflink_inode(ip));
offset_fsb = XFS_B_TO_FSBT(ip->i_mount, offset);
if (count == NULLFILEOFF)
end_fsb = NULLFILEOFF;
else
end_fsb = XFS_B_TO_FSB(ip->i_mount, offset + count);
/* Start a rolling transaction to remove the mappings */
error = xfs_trans_alloc(ip->i_mount, &M_RES(ip->i_mount)->tr_write,
0, 0, 0, &tp);
if (error)
goto out;
xfs_ilock(ip, XFS_ILOCK_EXCL);
xfs_trans_ijoin(tp, ip, 0);
/* Scrape out the old CoW reservations */
error = xfs_reflink_cancel_cow_blocks(ip, &tp, offset_fsb, end_fsb,
cancel_real);
if (error)
goto out_cancel;
error = xfs_trans_commit(tp);
xfs_iunlock(ip, XFS_ILOCK_EXCL);
return error;
out_cancel:
xfs_trans_cancel(tp);
xfs_iunlock(ip, XFS_ILOCK_EXCL);
out:
trace_xfs_reflink_cancel_cow_range_error(ip, error, _RET_IP_);
return error;
}
/*
* Update destination inode size & cowextsize hint, if necessary.
*/
STATIC int
xfs_reflink_update_dest(
struct xfs_inode *dest,
xfs_off_t newlen,
xfs_extlen_t cowextsize,
bool is_dedupe)
{
struct xfs_mount *mp = dest->i_mount;
struct xfs_trans *tp;
int error;
if (is_dedupe && newlen <= i_size_read(VFS_I(dest)) && cowextsize == 0)
return 0;
error = xfs_trans_alloc(mp, &M_RES(mp)->tr_ichange, 0, 0, 0, &tp);
if (error)
goto out_error;
xfs_ilock(dest, XFS_ILOCK_EXCL);
xfs_trans_ijoin(tp, dest, XFS_ILOCK_EXCL);
if (newlen > i_size_read(VFS_I(dest))) {
trace_xfs_reflink_update_inode_size(dest, newlen);
i_size_write(VFS_I(dest), newlen);
dest->i_d.di_size = newlen;
}
if (cowextsize) {
dest->i_d.di_cowextsize = cowextsize;
dest->i_d.di_flags2 |= XFS_DIFLAG2_COWEXTSIZE;
}
if (!is_dedupe) {
xfs_trans_ichgtime(tp, dest,
XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
}
xfs_trans_log_inode(tp, dest, XFS_ILOG_CORE);
error = xfs_trans_commit(tp);
if (error)
goto out_error;
return error;
out_error:
trace_xfs_reflink_update_inode_size_error(dest, error, _RET_IP_);
return error;
}
/*
* Set up the transaction structure for the setattr operation, checking that we
* have permission to do so. On success, return a clean transaction and the
* inode locked exclusively ready for further operation specific checks. On
* failure, return an error without modifying or locking the inode.
*
* The inode might already be IO locked on call. If this is the case, it is
* indicated in @join_flags and we take full responsibility for ensuring they
* are unlocked from now on. Hence if we have an error here, we still have to
* unlock them. Otherwise, once they are joined to the transaction, they will
* be unlocked on commit/cancel.
*/
static struct xfs_trans *
xfs_ioctl_setattr_get_trans(
struct xfs_inode *ip,
int join_flags)
{
struct xfs_mount *mp = ip->i_mount;
struct xfs_trans *tp;
int error = -EROFS;
if (mp->m_flags & XFS_MOUNT_RDONLY)
goto out_unlock;
error = -EIO;
if (XFS_FORCED_SHUTDOWN(mp))
goto out_unlock;
tp = xfs_trans_alloc(mp, XFS_TRANS_SETATTR_NOT_SIZE);
error = xfs_trans_reserve(tp, &M_RES(mp)->tr_ichange, 0, 0);
if (error)
goto out_cancel;
xfs_ilock(ip, XFS_ILOCK_EXCL);
xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL | join_flags);
join_flags = 0;
/*
* CAP_FOWNER overrides the following restrictions:
*
* The user ID of the calling process must be equal to the file owner
* ID, except in cases where the CAP_FSETID capability is applicable.
*/
if (!inode_owner_or_capable(VFS_I(ip))) {
error = -EPERM;
goto out_cancel;
}
if (mp->m_flags & XFS_MOUNT_WSYNC)
xfs_trans_set_sync(tp);
return tp;
out_cancel:
xfs_trans_cancel(tp);
out_unlock:
if (join_flags)
xfs_iunlock(ip, join_flags);
return ERR_PTR(error);
}
STATIC int
xfs_qm_scall_trunc_qfile(
struct xfs_mount *mp,
xfs_ino_t ino)
{
struct xfs_inode *ip;
struct xfs_trans *tp;
int error;
if (ino == NULLFSINO)
return 0;
error = xfs_iget(mp, NULL, ino, 0, 0, &ip);
if (error)
return error;
xfs_ilock(ip, XFS_IOLOCK_EXCL);
tp = xfs_trans_alloc(mp, XFS_TRANS_TRUNCATE_FILE);
error = xfs_trans_reserve(tp, 0, XFS_ITRUNCATE_LOG_RES(mp), 0,
XFS_TRANS_PERM_LOG_RES,
XFS_ITRUNCATE_LOG_COUNT);
if (error) {
xfs_trans_cancel(tp, 0);
xfs_iunlock(ip, XFS_IOLOCK_EXCL);
goto out_put;
}
xfs_ilock(ip, XFS_ILOCK_EXCL);
xfs_trans_ijoin(tp, ip);
error = xfs_itruncate_data(&tp, ip, 0);
if (error) {
xfs_trans_cancel(tp, XFS_TRANS_RELEASE_LOG_RES |
XFS_TRANS_ABORT);
goto out_unlock;
}
xfs_trans_ichgtime(tp, ip, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
error = xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES);
out_unlock:
xfs_iunlock(ip, XFS_ILOCK_EXCL | XFS_IOLOCK_EXCL);
out_put:
IRELE(ip);
return error;
}
/*
* Get an inode and join it to the transaction.
*/
int
xfs_trans_iget(
xfs_mount_t *mp,
xfs_trans_t *tp,
xfs_ino_t ino,
uint flags,
uint lock_flags,
xfs_inode_t **ipp)
{
int error;
error = xfs_iget(mp, tp, ino, flags, lock_flags, ipp);
if (!error && tp) {
xfs_trans_ijoin(tp, *ipp);
(*ipp)->i_itemp->ili_lock_flags = lock_flags;
}
return error;
}
STATIC int
xfs_vn_update_time(
struct inode *inode,
struct timespec *now,
int flags)
{
struct xfs_inode *ip = XFS_I(inode);
struct xfs_mount *mp = ip->i_mount;
struct xfs_trans *tp;
int error;
trace_xfs_update_time(ip);
tp = xfs_trans_alloc(mp, XFS_TRANS_FSYNC_TS);
error = xfs_trans_reserve(tp, &M_RES(mp)->tr_fsyncts, 0, 0);
if (error) {
xfs_trans_cancel(tp, 0);
return -error;
}
xfs_ilock(ip, XFS_ILOCK_EXCL);
if (flags & S_CTIME) {
inode->i_ctime = *now;
ip->i_d.di_ctime.t_sec = (__int32_t)now->tv_sec;
ip->i_d.di_ctime.t_nsec = (__int32_t)now->tv_nsec;
}
if (flags & S_MTIME) {
inode->i_mtime = *now;
ip->i_d.di_mtime.t_sec = (__int32_t)now->tv_sec;
ip->i_d.di_mtime.t_nsec = (__int32_t)now->tv_nsec;
}
if (flags & S_ATIME) {
inode->i_atime = *now;
ip->i_d.di_atime.t_sec = (__int32_t)now->tv_sec;
ip->i_d.di_atime.t_nsec = (__int32_t)now->tv_nsec;
}
xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
xfs_trans_log_inode(tp, ip, XFS_ILOG_TIMESTAMP);
return -xfs_trans_commit(tp, 0);
}
/*
* This is a subroutine for xfs_write() and other writers (xfs_ioctl)
* which clears the setuid and setgid bits when a file is written.
*/
int
xfs_write_clear_setuid(
xfs_inode_t *ip)
{
xfs_mount_t *mp;
xfs_trans_t *tp;
int error;
mp = ip->i_mount;
tp = xfs_trans_alloc(mp, XFS_TRANS_WRITEID);
if ((error = xfs_trans_reserve(tp, 0,
XFS_WRITEID_LOG_RES(mp),
0, 0, 0))) {
xfs_trans_cancel(tp, 0);
return error;
}
xfs_ilock(ip, XFS_ILOCK_EXCL);
xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
xfs_trans_ihold(tp, ip);
ip->i_d.di_mode &= ~S_ISUID;
/*
* Note that we don't have to worry about mandatory
* file locking being disabled here because we only
* clear the S_ISGID bit if the Group execute bit is
* on, but if it was on then mandatory locking wouldn't
* have been enabled.
*/
if (ip->i_d.di_mode & S_IXGRP) {
ip->i_d.di_mode &= ~S_ISGID;
}
xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
xfs_trans_set_sync(tp);
error = xfs_trans_commit(tp, 0, NULL);
xfs_iunlock(ip, XFS_ILOCK_EXCL);
return 0;
}
STATIC int
xfs_commit_dummy_trans(
struct xfs_mount *mp,
uint flags)
{
struct xfs_inode *ip = mp->m_rootip;
struct xfs_trans *tp;
int error;
int log_flags = XFS_LOG_FORCE;
if (flags & SYNC_WAIT)
log_flags |= XFS_LOG_SYNC;
/*
* Put a dummy transaction in the log to tell recovery
* that all others are OK.
*/
tp = xfs_trans_alloc(mp, XFS_TRANS_DUMMY1);
error = xfs_trans_reserve(tp, 0, XFS_ICHANGE_LOG_RES(mp), 0, 0, 0);
if (error) {
xfs_trans_cancel(tp, 0);
return error;
}
xfs_ilock(ip, XFS_ILOCK_EXCL);
xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
xfs_trans_ihold(tp, ip);
xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
error = xfs_trans_commit(tp, 0);
xfs_iunlock(ip, XFS_ILOCK_EXCL);
/* the log force ensures this transaction is pushed to disk */
xfs_log_force(mp, 0, log_flags);
return error;
}
/*
* This is called by xfs_inactive to free any blocks beyond eof
* when the link count isn't zero and by xfs_dm_punch_hole() when
* punching a hole to EOF.
*/
int
xfs_free_eofblocks(
xfs_mount_t *mp,
xfs_inode_t *ip,
bool need_iolock)
{
xfs_trans_t *tp;
int error;
xfs_fileoff_t end_fsb;
xfs_fileoff_t last_fsb;
xfs_filblks_t map_len;
int nimaps;
xfs_bmbt_irec_t imap;
/*
* Figure out if there are any blocks beyond the end
* of the file. If not, then there is nothing to do.
*/
end_fsb = XFS_B_TO_FSB(mp, (xfs_ufsize_t)XFS_ISIZE(ip));
last_fsb = XFS_B_TO_FSB(mp, mp->m_super->s_maxbytes);
if (last_fsb <= end_fsb)
return 0;
map_len = last_fsb - end_fsb;
nimaps = 1;
xfs_ilock(ip, XFS_ILOCK_SHARED);
error = xfs_bmapi_read(ip, end_fsb, map_len, &imap, &nimaps, 0);
xfs_iunlock(ip, XFS_ILOCK_SHARED);
if (!error && (nimaps != 0) &&
(imap.br_startblock != HOLESTARTBLOCK ||
ip->i_delayed_blks)) {
/*
* Attach the dquots to the inode up front.
*/
error = xfs_qm_dqattach(ip, 0);
if (error)
return error;
/*
* There are blocks after the end of file.
* Free them up now by truncating the file to
* its current size.
*/
tp = xfs_trans_alloc(mp, XFS_TRANS_INACTIVE);
if (need_iolock) {
if (!xfs_ilock_nowait(ip, XFS_IOLOCK_EXCL)) {
xfs_trans_cancel(tp, 0);
return EAGAIN;
}
}
error = xfs_trans_reserve(tp, &M_RES(mp)->tr_itruncate, 0, 0);
if (error) {
ASSERT(XFS_FORCED_SHUTDOWN(mp));
xfs_trans_cancel(tp, 0);
if (need_iolock)
xfs_iunlock(ip, XFS_IOLOCK_EXCL);
return error;
}
xfs_ilock(ip, XFS_ILOCK_EXCL);
xfs_trans_ijoin(tp, ip, 0);
/*
* Do not update the on-disk file size. If we update the
* on-disk file size and then the system crashes before the
* contents of the file are flushed to disk then the files
* may be full of holes (ie NULL files bug).
*/
error = xfs_itruncate_extents(&tp, ip, XFS_DATA_FORK,
XFS_ISIZE(ip));
if (error) {
/*
* If we get an error at this point we simply don't
* bother truncating the file.
*/
xfs_trans_cancel(tp,
(XFS_TRANS_RELEASE_LOG_RES |
XFS_TRANS_ABORT));
} else {
error = xfs_trans_commit(tp,
XFS_TRANS_RELEASE_LOG_RES);
if (!error)
xfs_inode_clear_eofblocks_tag(ip);
}
xfs_iunlock(ip, XFS_ILOCK_EXCL);
if (need_iolock)
xfs_iunlock(ip, XFS_IOLOCK_EXCL);
}
return error;
}
int
xfs_swap_extents(
xfs_inode_t *ip, /* target inode */
xfs_inode_t *tip, /* tmp inode */
xfs_swapext_t *sxp)
{
xfs_mount_t *mp = ip->i_mount;
xfs_trans_t *tp;
xfs_bstat_t *sbp = &sxp->sx_stat;
xfs_ifork_t *tempifp, *ifp, *tifp;
int src_log_flags, target_log_flags;
int error = 0;
int aforkblks = 0;
int taforkblks = 0;
__uint64_t tmp;
tempifp = kmem_alloc(sizeof(xfs_ifork_t), KM_MAYFAIL);
if (!tempifp) {
error = XFS_ERROR(ENOMEM);
goto out;
}
/*
* we have to do two separate lock calls here to keep lockdep
* happy. If we try to get all the locks in one call, lock will
* report false positives when we drop the ILOCK and regain them
* below.
*/
xfs_lock_two_inodes(ip, tip, XFS_IOLOCK_EXCL);
xfs_lock_two_inodes(ip, tip, XFS_ILOCK_EXCL);
/* Verify that both files have the same format */
if ((ip->i_d.di_mode & S_IFMT) != (tip->i_d.di_mode & S_IFMT)) {
error = XFS_ERROR(EINVAL);
goto out_unlock;
}
/* Verify both files are either real-time or non-realtime */
if (XFS_IS_REALTIME_INODE(ip) != XFS_IS_REALTIME_INODE(tip)) {
error = XFS_ERROR(EINVAL);
goto out_unlock;
}
error = -filemap_write_and_wait(VFS_I(tip)->i_mapping);
if (error)
goto out_unlock;
truncate_pagecache_range(VFS_I(tip), 0, -1);
/* Verify O_DIRECT for ftmp */
if (VN_CACHED(VFS_I(tip)) != 0) {
error = XFS_ERROR(EINVAL);
goto out_unlock;
}
/* Verify all data are being swapped */
if (sxp->sx_offset != 0 ||
sxp->sx_length != ip->i_d.di_size ||
sxp->sx_length != tip->i_d.di_size) {
error = XFS_ERROR(EFAULT);
goto out_unlock;
}
trace_xfs_swap_extent_before(ip, 0);
trace_xfs_swap_extent_before(tip, 1);
/* check inode formats now that data is flushed */
error = xfs_swap_extents_check_format(ip, tip);
if (error) {
xfs_notice(mp,
"%s: inode 0x%llx format is incompatible for exchanging.",
__func__, ip->i_ino);
goto out_unlock;
}
/*
* Compare the current change & modify times with that
* passed in. If they differ, we abort this swap.
* This is the mechanism used to ensure the calling
* process that the file was not changed out from
* under it.
*/
if ((sbp->bs_ctime.tv_sec != VFS_I(ip)->i_ctime.tv_sec) ||
(sbp->bs_ctime.tv_nsec != VFS_I(ip)->i_ctime.tv_nsec) ||
(sbp->bs_mtime.tv_sec != VFS_I(ip)->i_mtime.tv_sec) ||
(sbp->bs_mtime.tv_nsec != VFS_I(ip)->i_mtime.tv_nsec)) {
error = XFS_ERROR(EBUSY);
goto out_unlock;
}
/* We need to fail if the file is memory mapped. Once we have tossed
* all existing pages, the page fault will have no option
* but to go to the filesystem for pages. By making the page fault call
* vop_read (or write in the case of autogrow) they block on the iolock
* until we have switched the extents.
*/
if (VN_MAPPED(VFS_I(ip))) {
error = XFS_ERROR(EBUSY);
goto out_unlock;
}
xfs_iunlock(ip, XFS_ILOCK_EXCL);
xfs_iunlock(tip, XFS_ILOCK_EXCL);
/*
* There is a race condition here since we gave up the
* ilock. However, the data fork will not change since
* we have the iolock (locked for truncation too) so we
* are safe. We don't really care if non-io related
* fields change.
*/
truncate_pagecache_range(VFS_I(ip), 0, -1);
tp = xfs_trans_alloc(mp, XFS_TRANS_SWAPEXT);
error = xfs_trans_reserve(tp, &M_RES(mp)->tr_ichange, 0, 0);
if (error) {
xfs_iunlock(ip, XFS_IOLOCK_EXCL);
xfs_iunlock(tip, XFS_IOLOCK_EXCL);
xfs_trans_cancel(tp, 0);
goto out;
}
xfs_lock_two_inodes(ip, tip, XFS_ILOCK_EXCL);
/*
* Count the number of extended attribute blocks
*/
if ( ((XFS_IFORK_Q(ip) != 0) && (ip->i_d.di_anextents > 0)) &&
(ip->i_d.di_aformat != XFS_DINODE_FMT_LOCAL)) {
error = xfs_bmap_count_blocks(tp, ip, XFS_ATTR_FORK, &aforkblks);
if (error)
goto out_trans_cancel;
}
if ( ((XFS_IFORK_Q(tip) != 0) && (tip->i_d.di_anextents > 0)) &&
(tip->i_d.di_aformat != XFS_DINODE_FMT_LOCAL)) {
error = xfs_bmap_count_blocks(tp, tip, XFS_ATTR_FORK,
&taforkblks);
if (error)
goto out_trans_cancel;
}
xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL | XFS_IOLOCK_EXCL);
xfs_trans_ijoin(tp, tip, XFS_ILOCK_EXCL | XFS_IOLOCK_EXCL);
/*
* Before we've swapped the forks, lets set the owners of the forks
* appropriately. We have to do this as we are demand paging the btree
* buffers, and so the validation done on read will expect the owner
* field to be correctly set. Once we change the owners, we can swap the
* inode forks.
*
* Note the trickiness in setting the log flags - we set the owner log
* flag on the opposite inode (i.e. the inode we are setting the new
* owner to be) because once we swap the forks and log that, log
* recovery is going to see the fork as owned by the swapped inode,
* not the pre-swapped inodes.
*/
src_log_flags = XFS_ILOG_CORE;
target_log_flags = XFS_ILOG_CORE;
if (ip->i_d.di_version == 3 &&
ip->i_d.di_format == XFS_DINODE_FMT_BTREE) {
target_log_flags |= XFS_ILOG_DOWNER;
error = xfs_bmbt_change_owner(tp, ip, XFS_DATA_FORK,
tip->i_ino, NULL);
if (error)
goto out_trans_cancel;
}
if (tip->i_d.di_version == 3 &&
tip->i_d.di_format == XFS_DINODE_FMT_BTREE) {
src_log_flags |= XFS_ILOG_DOWNER;
error = xfs_bmbt_change_owner(tp, tip, XFS_DATA_FORK,
ip->i_ino, NULL);
if (error)
goto out_trans_cancel;
}
/*
* Swap the data forks of the inodes
*/
ifp = &ip->i_df;
tifp = &tip->i_df;
*tempifp = *ifp; /* struct copy */
*ifp = *tifp; /* struct copy */
*tifp = *tempifp; /* struct copy */
/*
* Fix the on-disk inode values
*/
tmp = (__uint64_t)ip->i_d.di_nblocks;
ip->i_d.di_nblocks = tip->i_d.di_nblocks - taforkblks + aforkblks;
tip->i_d.di_nblocks = tmp + taforkblks - aforkblks;
tmp = (__uint64_t) ip->i_d.di_nextents;
ip->i_d.di_nextents = tip->i_d.di_nextents;
tip->i_d.di_nextents = tmp;
tmp = (__uint64_t) ip->i_d.di_format;
ip->i_d.di_format = tip->i_d.di_format;
tip->i_d.di_format = tmp;
/*
* The extents in the source inode could still contain speculative
* preallocation beyond EOF (e.g. the file is open but not modified
* while defrag is in progress). In that case, we need to copy over the
* number of delalloc blocks the data fork in the source inode is
* tracking beyond EOF so that when the fork is truncated away when the
* temporary inode is unlinked we don't underrun the i_delayed_blks
* counter on that inode.
*/
ASSERT(tip->i_delayed_blks == 0);
tip->i_delayed_blks = ip->i_delayed_blks;
ip->i_delayed_blks = 0;
switch (ip->i_d.di_format) {
case XFS_DINODE_FMT_EXTENTS:
/* If the extents fit in the inode, fix the
* pointer. Otherwise it's already NULL or
* pointing to the extent.
*/
if (ip->i_d.di_nextents <= XFS_INLINE_EXTS) {
ifp->if_u1.if_extents =
ifp->if_u2.if_inline_ext;
}
src_log_flags |= XFS_ILOG_DEXT;
break;
case XFS_DINODE_FMT_BTREE:
ASSERT(ip->i_d.di_version < 3 ||
(src_log_flags & XFS_ILOG_DOWNER));
src_log_flags |= XFS_ILOG_DBROOT;
break;
}
switch (tip->i_d.di_format) {
case XFS_DINODE_FMT_EXTENTS:
/* If the extents fit in the inode, fix the
* pointer. Otherwise it's already NULL or
* pointing to the extent.
*/
if (tip->i_d.di_nextents <= XFS_INLINE_EXTS) {
tifp->if_u1.if_extents =
tifp->if_u2.if_inline_ext;
}
target_log_flags |= XFS_ILOG_DEXT;
break;
case XFS_DINODE_FMT_BTREE:
target_log_flags |= XFS_ILOG_DBROOT;
ASSERT(tip->i_d.di_version < 3 ||
(target_log_flags & XFS_ILOG_DOWNER));
break;
}
xfs_trans_log_inode(tp, ip, src_log_flags);
xfs_trans_log_inode(tp, tip, target_log_flags);
/*
* If this is a synchronous mount, make sure that the
* transaction goes to disk before returning to the user.
*/
if (mp->m_flags & XFS_MOUNT_WSYNC)
xfs_trans_set_sync(tp);
error = xfs_trans_commit(tp, 0);
trace_xfs_swap_extent_after(ip, 0);
trace_xfs_swap_extent_after(tip, 1);
out:
kmem_free(tempifp);
return error;
out_unlock:
xfs_iunlock(ip, XFS_ILOCK_EXCL | XFS_IOLOCK_EXCL);
xfs_iunlock(tip, XFS_ILOCK_EXCL | XFS_IOLOCK_EXCL);
goto out;
out_trans_cancel:
xfs_trans_cancel(tp, 0);
goto out_unlock;
}
int
xfs_bmap_rtalloc(
struct xfs_bmalloca *ap) /* bmap alloc argument struct */
{
xfs_alloctype_t atype = 0; /* type for allocation routines */
int error; /* error return value */
xfs_mount_t *mp; /* mount point structure */
xfs_extlen_t prod = 0; /* product factor for allocators */
xfs_extlen_t ralen = 0; /* realtime allocation length */
xfs_extlen_t align; /* minimum allocation alignment */
xfs_rtblock_t rtb;
mp = ap->ip->i_mount;
align = xfs_get_extsz_hint(ap->ip);
prod = align / mp->m_sb.sb_rextsize;
error = xfs_bmap_extsize_align(mp, &ap->got, &ap->prev,
align, 1, ap->eof, 0,
ap->conv, &ap->offset, &ap->length);
if (error)
return error;
ASSERT(ap->length);
ASSERT(ap->length % mp->m_sb.sb_rextsize == 0);
/*
* If the offset & length are not perfectly aligned
* then kill prod, it will just get us in trouble.
*/
if (do_mod(ap->offset, align) || ap->length % align)
prod = 1;
/*
* Set ralen to be the actual requested length in rtextents.
*/
ralen = ap->length / mp->m_sb.sb_rextsize;
/*
* If the old value was close enough to MAXEXTLEN that
* we rounded up to it, cut it back so it's valid again.
* Note that if it's a really large request (bigger than
* MAXEXTLEN), we don't hear about that number, and can't
* adjust the starting point to match it.
*/
if (ralen * mp->m_sb.sb_rextsize >= MAXEXTLEN)
ralen = MAXEXTLEN / mp->m_sb.sb_rextsize;
/*
* Lock out other modifications to the RT bitmap inode.
*/
xfs_ilock(mp->m_rbmip, XFS_ILOCK_EXCL);
xfs_trans_ijoin(ap->tp, mp->m_rbmip, XFS_ILOCK_EXCL);
/*
* If it's an allocation to an empty file at offset 0,
* pick an extent that will space things out in the rt area.
*/
if (ap->eof && ap->offset == 0) {
xfs_rtblock_t uninitialized_var(rtx); /* realtime extent no */
error = xfs_rtpick_extent(mp, ap->tp, ralen, &rtx);
if (error)
return error;
ap->blkno = rtx * mp->m_sb.sb_rextsize;
} else {
ap->blkno = 0;
}
xfs_bmap_adjacent(ap);
/*
* Realtime allocation, done through xfs_rtallocate_extent.
*/
atype = ap->blkno == 0 ? XFS_ALLOCTYPE_ANY_AG : XFS_ALLOCTYPE_NEAR_BNO;
do_div(ap->blkno, mp->m_sb.sb_rextsize);
rtb = ap->blkno;
ap->length = ralen;
if ((error = xfs_rtallocate_extent(ap->tp, ap->blkno, 1, ap->length,
&ralen, atype, ap->wasdel, prod, &rtb)))
return error;
if (rtb == NULLFSBLOCK && prod > 1 &&
(error = xfs_rtallocate_extent(ap->tp, ap->blkno, 1,
ap->length, &ralen, atype,
ap->wasdel, 1, &rtb)))
return error;
ap->blkno = rtb;
if (ap->blkno != NULLFSBLOCK) {
ap->blkno *= mp->m_sb.sb_rextsize;
ralen *= mp->m_sb.sb_rextsize;
ap->length = ralen;
ap->ip->i_d.di_nblocks += ralen;
xfs_trans_log_inode(ap->tp, ap->ip, XFS_ILOG_CORE);
if (ap->wasdel)
ap->ip->i_delayed_blks -= ralen;
/*
* Adjust the disk quota also. This was reserved
* earlier.
*/
xfs_trans_mod_dquot_byino(ap->tp, ap->ip,
ap->wasdel ? XFS_TRANS_DQ_DELRTBCOUNT :
XFS_TRANS_DQ_RTBCOUNT, (long) ralen);
} else {
ap->length = 0;
}
return 0;
}
int
xfs_free_file_space(
struct xfs_inode *ip,
xfs_off_t offset,
xfs_off_t len)
{
int committed;
int done;
xfs_fileoff_t endoffset_fsb;
int error;
xfs_fsblock_t firstfsb;
xfs_bmap_free_t free_list;
xfs_bmbt_irec_t imap;
xfs_off_t ioffset;
xfs_extlen_t mod=0;
xfs_mount_t *mp;
int nimap;
uint resblks;
xfs_off_t rounding;
int rt;
xfs_fileoff_t startoffset_fsb;
xfs_trans_t *tp;
mp = ip->i_mount;
trace_xfs_free_file_space(ip);
error = xfs_qm_dqattach(ip, 0);
if (error)
return error;
error = 0;
if (len <= 0) /* if nothing being freed */
return error;
rt = XFS_IS_REALTIME_INODE(ip);
startoffset_fsb = XFS_B_TO_FSB(mp, offset);
endoffset_fsb = XFS_B_TO_FSBT(mp, offset + len);
/* wait for the completion of any pending DIOs */
inode_dio_wait(VFS_I(ip));
rounding = max_t(xfs_off_t, 1 << mp->m_sb.sb_blocklog, PAGE_CACHE_SIZE);
ioffset = offset & ~(rounding - 1);
error = -filemap_write_and_wait_range(VFS_I(ip)->i_mapping,
ioffset, -1);
if (error)
goto out;
truncate_pagecache_range(VFS_I(ip), ioffset, -1);
/*
* Need to zero the stuff we're not freeing, on disk.
* If it's a realtime file & can't use unwritten extents then we
* actually need to zero the extent edges. Otherwise xfs_bunmapi
* will take care of it for us.
*/
if (rt && !xfs_sb_version_hasextflgbit(&mp->m_sb)) {
nimap = 1;
error = xfs_bmapi_read(ip, startoffset_fsb, 1,
&imap, &nimap, 0);
if (error)
goto out;
ASSERT(nimap == 0 || nimap == 1);
if (nimap && imap.br_startblock != HOLESTARTBLOCK) {
xfs_daddr_t block;
ASSERT(imap.br_startblock != DELAYSTARTBLOCK);
block = imap.br_startblock;
mod = do_div(block, mp->m_sb.sb_rextsize);
if (mod)
startoffset_fsb += mp->m_sb.sb_rextsize - mod;
}
nimap = 1;
error = xfs_bmapi_read(ip, endoffset_fsb - 1, 1,
&imap, &nimap, 0);
if (error)
goto out;
ASSERT(nimap == 0 || nimap == 1);
if (nimap && imap.br_startblock != HOLESTARTBLOCK) {
ASSERT(imap.br_startblock != DELAYSTARTBLOCK);
mod++;
if (mod && (mod != mp->m_sb.sb_rextsize))
endoffset_fsb -= mod;
}
}
if ((done = (endoffset_fsb <= startoffset_fsb)))
/*
* One contiguous piece to clear
*/
error = xfs_zero_remaining_bytes(ip, offset, offset + len - 1);
else {
/*
* Some full blocks, possibly two pieces to clear
*/
if (offset < XFS_FSB_TO_B(mp, startoffset_fsb))
error = xfs_zero_remaining_bytes(ip, offset,
XFS_FSB_TO_B(mp, startoffset_fsb) - 1);
if (!error &&
XFS_FSB_TO_B(mp, endoffset_fsb) < offset + len)
error = xfs_zero_remaining_bytes(ip,
XFS_FSB_TO_B(mp, endoffset_fsb),
offset + len - 1);
}
/*
* free file space until done or until there is an error
*/
resblks = XFS_DIOSTRAT_SPACE_RES(mp, 0);
while (!error && !done) {
/*
* allocate and setup the transaction. Allow this
* transaction to dip into the reserve blocks to ensure
* the freeing of the space succeeds at ENOSPC.
*/
tp = xfs_trans_alloc(mp, XFS_TRANS_DIOSTRAT);
tp->t_flags |= XFS_TRANS_RESERVE;
error = xfs_trans_reserve(tp, &M_RES(mp)->tr_write, resblks, 0);
/*
* check for running out of space
*/
if (error) {
/*
* Free the transaction structure.
*/
ASSERT(error == ENOSPC || XFS_FORCED_SHUTDOWN(mp));
xfs_trans_cancel(tp, 0);
break;
}
xfs_ilock(ip, XFS_ILOCK_EXCL);
error = xfs_trans_reserve_quota(tp, mp,
ip->i_udquot, ip->i_gdquot, ip->i_pdquot,
resblks, 0, XFS_QMOPT_RES_REGBLKS);
if (error)
goto error1;
xfs_trans_ijoin(tp, ip, 0);
/*
* issue the bunmapi() call to free the blocks
*/
xfs_bmap_init(&free_list, &firstfsb);
error = xfs_bunmapi(tp, ip, startoffset_fsb,
endoffset_fsb - startoffset_fsb,
0, 2, &firstfsb, &free_list, &done);
if (error) {
goto error0;
}
/*
* complete the transaction
*/
error = xfs_bmap_finish(&tp, &free_list, &committed);
if (error) {
goto error0;
}
error = xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES);
xfs_iunlock(ip, XFS_ILOCK_EXCL);
}
out:
return error;
error0:
xfs_bmap_cancel(&free_list);
error1:
xfs_trans_cancel(tp, XFS_TRANS_RELEASE_LOG_RES | XFS_TRANS_ABORT);
xfs_iunlock(ip, XFS_ILOCK_EXCL);
goto out;
}
STATIC int
xfs_ioctl_setattr(
xfs_inode_t *ip,
struct fsxattr *fa,
int mask)
{
struct xfs_mount *mp = ip->i_mount;
struct xfs_trans *tp;
unsigned int lock_flags = 0;
struct xfs_dquot *udqp = NULL;
struct xfs_dquot *gdqp = NULL;
struct xfs_dquot *olddquot = NULL;
int code;
trace_xfs_ioctl_setattr(ip);
if (mp->m_flags & XFS_MOUNT_RDONLY)
return XFS_ERROR(EROFS);
if (XFS_FORCED_SHUTDOWN(mp))
return XFS_ERROR(EIO);
/*
* Disallow 32bit project ids when projid32bit feature is not enabled.
*/
if ((mask & FSX_PROJID) && (fa->fsx_projid > (__uint16_t)-1) &&
!xfs_sb_version_hasprojid32bit(&ip->i_mount->m_sb))
return XFS_ERROR(EINVAL);
/*
* If disk quotas is on, we make sure that the dquots do exist on disk,
* before we start any other transactions. Trying to do this later
* is messy. We don't care to take a readlock to look at the ids
* in inode here, because we can't hold it across the trans_reserve.
* If the IDs do change before we take the ilock, we're covered
* because the i_*dquot fields will get updated anyway.
*/
if (XFS_IS_QUOTA_ON(mp) && (mask & FSX_PROJID)) {
code = xfs_qm_vop_dqalloc(ip, ip->i_d.di_uid,
ip->i_d.di_gid, fa->fsx_projid,
XFS_QMOPT_PQUOTA, &udqp, &gdqp);
if (code)
return code;
}
/*
* For the other attributes, we acquire the inode lock and
* first do an error checking pass.
*/
tp = xfs_trans_alloc(mp, XFS_TRANS_SETATTR_NOT_SIZE);
code = xfs_trans_reserve(tp, 0, XFS_ICHANGE_LOG_RES(mp), 0, 0, 0);
if (code)
goto error_return;
lock_flags = XFS_ILOCK_EXCL;
xfs_ilock(ip, lock_flags);
/*
* CAP_FOWNER overrides the following restrictions:
*
* The user ID of the calling process must be equal
* to the file owner ID, except in cases where the
* CAP_FSETID capability is applicable.
*/
if (current_fsuid() != ip->i_d.di_uid && !capable(CAP_FOWNER)) {
code = XFS_ERROR(EPERM);
goto error_return;
}
/*
* Do a quota reservation only if projid is actually going to change.
*/
if (mask & FSX_PROJID) {
if (XFS_IS_QUOTA_RUNNING(mp) &&
XFS_IS_PQUOTA_ON(mp) &&
xfs_get_projid(ip) != fa->fsx_projid) {
ASSERT(tp);
code = xfs_qm_vop_chown_reserve(tp, ip, udqp, gdqp,
capable(CAP_FOWNER) ?
XFS_QMOPT_FORCE_RES : 0);
if (code) /* out of quota */
goto error_return;
}
}
if (mask & FSX_EXTSIZE) {
/*
* Can't change extent size if any extents are allocated.
*/
if (ip->i_d.di_nextents &&
((ip->i_d.di_extsize << mp->m_sb.sb_blocklog) !=
fa->fsx_extsize)) {
code = XFS_ERROR(EINVAL); /* EFBIG? */
goto error_return;
}
/*
* Extent size must be a multiple of the appropriate block
* size, if set at all. It must also be smaller than the
* maximum extent size supported by the filesystem.
*
* Also, for non-realtime files, limit the extent size hint to
* half the size of the AGs in the filesystem so alignment
* doesn't result in extents larger than an AG.
*/
if (fa->fsx_extsize != 0) {
xfs_extlen_t size;
xfs_fsblock_t extsize_fsb;
extsize_fsb = XFS_B_TO_FSB(mp, fa->fsx_extsize);
if (extsize_fsb > MAXEXTLEN) {
code = XFS_ERROR(EINVAL);
goto error_return;
}
if (XFS_IS_REALTIME_INODE(ip) ||
((mask & FSX_XFLAGS) &&
(fa->fsx_xflags & XFS_XFLAG_REALTIME))) {
size = mp->m_sb.sb_rextsize <<
mp->m_sb.sb_blocklog;
} else {
size = mp->m_sb.sb_blocksize;
if (extsize_fsb > mp->m_sb.sb_agblocks / 2) {
code = XFS_ERROR(EINVAL);
goto error_return;
}
}
if (fa->fsx_extsize % size) {
code = XFS_ERROR(EINVAL);
goto error_return;
}
}
}
if (mask & FSX_XFLAGS) {
/*
* Can't change realtime flag if any extents are allocated.
*/
if ((ip->i_d.di_nextents || ip->i_delayed_blks) &&
(XFS_IS_REALTIME_INODE(ip)) !=
(fa->fsx_xflags & XFS_XFLAG_REALTIME)) {
code = XFS_ERROR(EINVAL); /* EFBIG? */
goto error_return;
}
/*
* If realtime flag is set then must have realtime data.
*/
if ((fa->fsx_xflags & XFS_XFLAG_REALTIME)) {
if ((mp->m_sb.sb_rblocks == 0) ||
(mp->m_sb.sb_rextsize == 0) ||
(ip->i_d.di_extsize % mp->m_sb.sb_rextsize)) {
code = XFS_ERROR(EINVAL);
goto error_return;
}
}
/*
* Can't modify an immutable/append-only file unless
* we have appropriate permission.
*/
if ((ip->i_d.di_flags &
(XFS_DIFLAG_IMMUTABLE|XFS_DIFLAG_APPEND) ||
(fa->fsx_xflags &
(XFS_XFLAG_IMMUTABLE | XFS_XFLAG_APPEND))) &&
!capable(CAP_LINUX_IMMUTABLE)) {
code = XFS_ERROR(EPERM);
goto error_return;
}
}
xfs_trans_ijoin(tp, ip, 0);
/*
* Change file ownership. Must be the owner or privileged.
*/
if (mask & FSX_PROJID) {
/*
* CAP_FSETID overrides the following restrictions:
*
* The set-user-ID and set-group-ID bits of a file will be
* cleared upon successful return from chown()
*/
if ((ip->i_d.di_mode & (S_ISUID|S_ISGID)) &&
!capable(CAP_FSETID))
ip->i_d.di_mode &= ~(S_ISUID|S_ISGID);
/*
* Change the ownerships and register quota modifications
* in the transaction.
*/
if (xfs_get_projid(ip) != fa->fsx_projid) {
if (XFS_IS_QUOTA_RUNNING(mp) && XFS_IS_PQUOTA_ON(mp)) {
olddquot = xfs_qm_vop_chown(tp, ip,
&ip->i_gdquot, gdqp);
}
xfs_set_projid(ip, fa->fsx_projid);
/*
* We may have to rev the inode as well as
* the superblock version number since projids didn't
* exist before DINODE_VERSION_2 and SB_VERSION_NLINK.
*/
if (ip->i_d.di_version == 1)
xfs_bump_ino_vers2(tp, ip);
}
}
if (mask & FSX_EXTSIZE)
ip->i_d.di_extsize = fa->fsx_extsize >> mp->m_sb.sb_blocklog;
if (mask & FSX_XFLAGS) {
xfs_set_diflags(ip, fa->fsx_xflags);
xfs_diflags_to_linux(ip);
}
xfs_trans_ichgtime(tp, ip, XFS_ICHGTIME_CHG);
xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
XFS_STATS_INC(xs_ig_attrchg);
/*
* If this is a synchronous mount, make sure that the
* transaction goes to disk before returning to the user.
* This is slightly sub-optimal in that truncates require
* two sync transactions instead of one for wsync filesystems.
* One for the truncate and one for the timestamps since we
* don't want to change the timestamps unless we're sure the
* truncate worked. Truncates are less than 1% of the laddis
* mix so this probably isn't worth the trouble to optimize.
*/
if (mp->m_flags & XFS_MOUNT_WSYNC)
xfs_trans_set_sync(tp);
code = xfs_trans_commit(tp, 0);
xfs_iunlock(ip, lock_flags);
/*
* Release any dquot(s) the inode had kept before chown.
*/
xfs_qm_dqrele(olddquot);
xfs_qm_dqrele(udqp);
xfs_qm_dqrele(gdqp);
return code;
error_return:
xfs_qm_dqrele(udqp);
xfs_qm_dqrele(gdqp);
xfs_trans_cancel(tp, 0);
if (lock_flags)
xfs_iunlock(ip, lock_flags);
return code;
}
int
xfs_symlink(
struct xfs_inode *dp,
struct xfs_name *link_name,
const char *target_path,
umode_t mode,
struct xfs_inode **ipp)
{
struct xfs_mount *mp = dp->i_mount;
struct xfs_trans *tp = NULL;
struct xfs_inode *ip = NULL;
int error = 0;
int pathlen;
struct xfs_bmap_free free_list;
xfs_fsblock_t first_block;
bool unlock_dp_on_error = false;
uint cancel_flags;
int committed;
xfs_fileoff_t first_fsb;
xfs_filblks_t fs_blocks;
int nmaps;
struct xfs_bmbt_irec mval[XFS_SYMLINK_MAPS];
xfs_daddr_t d;
const char *cur_chunk;
int byte_cnt;
int n;
xfs_buf_t *bp;
prid_t prid;
struct xfs_dquot *udqp = NULL;
struct xfs_dquot *gdqp = NULL;
struct xfs_dquot *pdqp = NULL;
uint resblks;
*ipp = NULL;
trace_xfs_symlink(dp, link_name);
if (XFS_FORCED_SHUTDOWN(mp))
return XFS_ERROR(EIO);
/*
* Check component lengths of the target path name.
*/
pathlen = strlen(target_path);
if (pathlen >= MAXPATHLEN) /* total string too long */
return XFS_ERROR(ENAMETOOLONG);
udqp = gdqp = NULL;
if (dp->i_d.di_flags & XFS_DIFLAG_PROJINHERIT)
prid = xfs_get_projid(dp);
else
prid = XFS_PROJID_DEFAULT;
/*
* Make sure that we have allocated dquot(s) on disk.
*/
error = xfs_qm_vop_dqalloc(dp,
xfs_kuid_to_uid(current_fsuid()),
xfs_kgid_to_gid(current_fsgid()), prid,
XFS_QMOPT_QUOTALL | XFS_QMOPT_INHERIT,
&udqp, &gdqp, &pdqp);
if (error)
goto std_return;
tp = xfs_trans_alloc(mp, XFS_TRANS_SYMLINK);
cancel_flags = XFS_TRANS_RELEASE_LOG_RES;
/*
* The symlink will fit into the inode data fork?
* There can't be any attributes so we get the whole variable part.
*/
if (pathlen <= XFS_LITINO(mp, dp->i_d.di_version))
fs_blocks = 0;
else
fs_blocks = xfs_symlink_blocks(mp, pathlen);
resblks = XFS_SYMLINK_SPACE_RES(mp, link_name->len, fs_blocks);
error = xfs_trans_reserve(tp, &M_RES(mp)->tr_symlink, resblks, 0);
if (error == ENOSPC && fs_blocks == 0) {
resblks = 0;
error = xfs_trans_reserve(tp, &M_RES(mp)->tr_symlink, 0, 0);
}
if (error) {
cancel_flags = 0;
goto error_return;
}
xfs_ilock(dp, XFS_ILOCK_EXCL | XFS_ILOCK_PARENT);
unlock_dp_on_error = true;
/*
* Check whether the directory allows new symlinks or not.
*/
if (dp->i_d.di_flags & XFS_DIFLAG_NOSYMLINKS) {
error = XFS_ERROR(EPERM);
goto error_return;
}
/*
* Reserve disk quota : blocks and inode.
*/
error = xfs_trans_reserve_quota(tp, mp, udqp, gdqp,
pdqp, resblks, 1, 0);
if (error)
goto error_return;
/*
* Check for ability to enter directory entry, if no space reserved.
*/
error = xfs_dir_canenter(tp, dp, link_name, resblks);
if (error)
goto error_return;
/*
* Initialize the bmap freelist prior to calling either
* bmapi or the directory create code.
*/
xfs_bmap_init(&free_list, &first_block);
/*
* Allocate an inode for the symlink.
*/
error = xfs_dir_ialloc(&tp, dp, S_IFLNK | (mode & ~S_IFMT), 1, 0,
prid, resblks > 0, &ip, NULL);
if (error) {
if (error == ENOSPC)
goto error_return;
goto error1;
}
/*
* An error after we've joined dp to the transaction will result in the
* transaction cancel unlocking dp so don't do it explicitly in the
* error path.
*/
xfs_trans_ijoin(tp, dp, XFS_ILOCK_EXCL);
unlock_dp_on_error = false;
/*
* Also attach the dquot(s) to it, if applicable.
*/
xfs_qm_vop_create_dqattach(tp, ip, udqp, gdqp, pdqp);
if (resblks)
resblks -= XFS_IALLOC_SPACE_RES(mp);
/*
* If the symlink will fit into the inode, write it inline.
*/
if (pathlen <= XFS_IFORK_DSIZE(ip)) {
xfs_idata_realloc(ip, pathlen, XFS_DATA_FORK);
memcpy(ip->i_df.if_u1.if_data, target_path, pathlen);
ip->i_d.di_size = pathlen;
/*
* The inode was initially created in extent format.
*/
ip->i_df.if_flags &= ~(XFS_IFEXTENTS | XFS_IFBROOT);
ip->i_df.if_flags |= XFS_IFINLINE;
ip->i_d.di_format = XFS_DINODE_FMT_LOCAL;
xfs_trans_log_inode(tp, ip, XFS_ILOG_DDATA | XFS_ILOG_CORE);
} else {
int offset;
first_fsb = 0;
nmaps = XFS_SYMLINK_MAPS;
error = xfs_bmapi_write(tp, ip, first_fsb, fs_blocks,
XFS_BMAPI_METADATA, &first_block, resblks,
mval, &nmaps, &free_list);
if (error)
goto error2;
if (resblks)
resblks -= fs_blocks;
ip->i_d.di_size = pathlen;
xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
cur_chunk = target_path;
offset = 0;
for (n = 0; n < nmaps; n++) {
char *buf;
d = XFS_FSB_TO_DADDR(mp, mval[n].br_startblock);
byte_cnt = XFS_FSB_TO_B(mp, mval[n].br_blockcount);
bp = xfs_trans_get_buf(tp, mp->m_ddev_targp, d,
BTOBB(byte_cnt), 0);
if (!bp) {
error = ENOMEM;
goto error2;
}
bp->b_ops = &xfs_symlink_buf_ops;
byte_cnt = XFS_SYMLINK_BUF_SPACE(mp, byte_cnt);
byte_cnt = min(byte_cnt, pathlen);
buf = bp->b_addr;
buf += xfs_symlink_hdr_set(mp, ip->i_ino, offset,
byte_cnt, bp);
memcpy(buf, cur_chunk, byte_cnt);
cur_chunk += byte_cnt;
pathlen -= byte_cnt;
offset += byte_cnt;
xfs_trans_buf_set_type(tp, bp, XFS_BLFT_SYMLINK_BUF);
xfs_trans_log_buf(tp, bp, 0, (buf + byte_cnt - 1) -
(char *)bp->b_addr);
}
ASSERT(pathlen == 0);
}
/*
* Create the directory entry for the symlink.
*/
error = xfs_dir_createname(tp, dp, link_name, ip->i_ino,
&first_block, &free_list, resblks);
if (error)
goto error2;
xfs_trans_ichgtime(tp, dp, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
xfs_trans_log_inode(tp, dp, XFS_ILOG_CORE);
/*
* If this is a synchronous mount, make sure that the
* symlink transaction goes to disk before returning to
* the user.
*/
if (mp->m_flags & (XFS_MOUNT_WSYNC|XFS_MOUNT_DIRSYNC)) {
xfs_trans_set_sync(tp);
}
error = xfs_bmap_finish(&tp, &free_list, &committed);
if (error) {
goto error2;
}
error = xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES);
xfs_qm_dqrele(udqp);
xfs_qm_dqrele(gdqp);
xfs_qm_dqrele(pdqp);
*ipp = ip;
return 0;
error2:
IRELE(ip);
error1:
xfs_bmap_cancel(&free_list);
cancel_flags |= XFS_TRANS_ABORT;
error_return:
xfs_trans_cancel(tp, cancel_flags);
xfs_qm_dqrele(udqp);
xfs_qm_dqrele(gdqp);
xfs_qm_dqrele(pdqp);
if (unlock_dp_on_error)
xfs_iunlock(dp, XFS_ILOCK_EXCL);
std_return:
return error;
}
/*
* Truncate file. Must have write permission and not be a directory.
*/
int
xfs_setattr_size(
struct xfs_inode *ip,
struct iattr *iattr)
{
struct xfs_mount *mp = ip->i_mount;
struct inode *inode = VFS_I(ip);
xfs_off_t oldsize, newsize;
struct xfs_trans *tp;
int error;
uint lock_flags = 0;
uint commit_flags = 0;
trace_xfs_setattr(ip);
if (mp->m_flags & XFS_MOUNT_RDONLY)
return XFS_ERROR(EROFS);
if (XFS_FORCED_SHUTDOWN(mp))
return XFS_ERROR(EIO);
error = -inode_change_ok(inode, iattr);
if (error)
return XFS_ERROR(error);
ASSERT(xfs_isilocked(ip, XFS_IOLOCK_EXCL));
ASSERT(S_ISREG(ip->i_d.di_mode));
ASSERT((iattr->ia_valid & (ATTR_UID|ATTR_GID|ATTR_ATIME|ATTR_ATIME_SET|
ATTR_MTIME_SET|ATTR_KILL_PRIV|ATTR_TIMES_SET)) == 0);
oldsize = inode->i_size;
newsize = iattr->ia_size;
/*
* Short circuit the truncate case for zero length files.
*/
if (newsize == 0 && oldsize == 0 && ip->i_d.di_nextents == 0) {
if (!(iattr->ia_valid & (ATTR_CTIME|ATTR_MTIME)))
return 0;
/*
* Use the regular setattr path to update the timestamps.
*/
iattr->ia_valid &= ~ATTR_SIZE;
return xfs_setattr_nonsize(ip, iattr, 0);
}
/*
* Make sure that the dquots are attached to the inode.
*/
error = xfs_qm_dqattach(ip, 0);
if (error)
return error;
/*
* Now we can make the changes. Before we join the inode to the
* transaction, take care of the part of the truncation that must be
* done without the inode lock. This needs to be done before joining
* the inode to the transaction, because the inode cannot be unlocked
* once it is a part of the transaction.
*/
if (newsize > oldsize) {
/*
* Do the first part of growing a file: zero any data in the
* last block that is beyond the old EOF. We need to do this
* before the inode is joined to the transaction to modify
* i_size.
*/
error = xfs_zero_eof(ip, newsize, oldsize);
if (error)
return error;
}
/*
* We are going to log the inode size change in this transaction so
* any previous writes that are beyond the on disk EOF and the new
* EOF that have not been written out need to be written here. If we
* do not write the data out, we expose ourselves to the null files
* problem.
*
* Only flush from the on disk size to the smaller of the in memory
* file size or the new size as that's the range we really care about
* here and prevents waiting for other data not within the range we
* care about here.
*/
if (oldsize != ip->i_d.di_size && newsize > ip->i_d.di_size) {
error = -filemap_write_and_wait_range(VFS_I(ip)->i_mapping,
ip->i_d.di_size, newsize);
if (error)
return error;
}
/*
* Wait for all direct I/O to complete.
*/
inode_dio_wait(inode);
error = -block_truncate_page(inode->i_mapping, newsize, xfs_get_blocks);
if (error)
return error;
tp = xfs_trans_alloc(mp, XFS_TRANS_SETATTR_SIZE);
error = xfs_trans_reserve(tp, &M_RES(mp)->tr_itruncate, 0, 0);
if (error)
goto out_trans_cancel;
truncate_setsize(inode, newsize);
commit_flags = XFS_TRANS_RELEASE_LOG_RES;
lock_flags |= XFS_ILOCK_EXCL;
xfs_ilock(ip, XFS_ILOCK_EXCL);
xfs_trans_ijoin(tp, ip, 0);
/*
* Only change the c/mtime if we are changing the size or we are
* explicitly asked to change it. This handles the semantic difference
* between truncate() and ftruncate() as implemented in the VFS.
*
* The regular truncate() case without ATTR_CTIME and ATTR_MTIME is a
* special case where we need to update the times despite not having
* these flags set. For all other operations the VFS set these flags
* explicitly if it wants a timestamp update.
*/
if (newsize != oldsize &&
!(iattr->ia_valid & (ATTR_CTIME | ATTR_MTIME))) {
iattr->ia_ctime = iattr->ia_mtime =
current_fs_time(inode->i_sb);
iattr->ia_valid |= ATTR_CTIME | ATTR_MTIME;
}
/*
* The first thing we do is set the size to new_size permanently on
* disk. This way we don't have to worry about anyone ever being able
* to look at the data being freed even in the face of a crash.
* What we're getting around here is the case where we free a block, it
* is allocated to another file, it is written to, and then we crash.
* If the new data gets written to the file but the log buffers
* containing the free and reallocation don't, then we'd end up with
* garbage in the blocks being freed. As long as we make the new size
* permanent before actually freeing any blocks it doesn't matter if
* they get written to.
*/
ip->i_d.di_size = newsize;
xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
if (newsize <= oldsize) {
error = xfs_itruncate_extents(&tp, ip, XFS_DATA_FORK, newsize);
if (error)
goto out_trans_abort;
/*
* Truncated "down", so we're removing references to old data
* here - if we delay flushing for a long time, we expose
* ourselves unduly to the notorious NULL files problem. So,
* we mark this inode and flush it when the file is closed,
* and do not wait the usual (long) time for writeout.
*/
xfs_iflags_set(ip, XFS_ITRUNCATED);
/* A truncate down always removes post-EOF blocks. */
xfs_inode_clear_eofblocks_tag(ip);
}
if (iattr->ia_valid & ATTR_MODE)
xfs_setattr_mode(ip, iattr);
if (iattr->ia_valid & (ATTR_ATIME|ATTR_CTIME|ATTR_MTIME))
xfs_setattr_time(ip, iattr);
xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
XFS_STATS_INC(xs_ig_attrchg);
if (mp->m_flags & XFS_MOUNT_WSYNC)
xfs_trans_set_sync(tp);
error = xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES);
out_unlock:
if (lock_flags)
xfs_iunlock(ip, lock_flags);
return error;
out_trans_abort:
commit_flags |= XFS_TRANS_ABORT;
out_trans_cancel:
xfs_trans_cancel(tp, commit_flags);
goto out_unlock;
}
/*
* Generic handler routine to remove a name from an attribute list.
* Transitions attribute list from Btree to shortform as necessary.
*/
int
xfs_attr_remove(
struct xfs_inode *dp,
const unsigned char *name,
int flags)
{
struct xfs_mount *mp = dp->i_mount;
struct xfs_da_args args;
int error;
XFS_STATS_INC(mp, xs_attr_remove);
if (XFS_FORCED_SHUTDOWN(dp->i_mount))
return -EIO;
error = xfs_attr_args_init(&args, dp, name, flags);
if (error)
return error;
/*
* we have no control over the attribute names that userspace passes us
* to remove, so we have to allow the name lookup prior to attribute
* removal to fail.
*/
args.op_flags = XFS_DA_OP_OKNOENT;
error = xfs_qm_dqattach(dp);
if (error)
return error;
/*
* Root fork attributes can use reserved data blocks for this
* operation if necessary
*/
error = xfs_trans_alloc(mp, &M_RES(mp)->tr_attrrm,
XFS_ATTRRM_SPACE_RES(mp), 0,
(flags & ATTR_ROOT) ? XFS_TRANS_RESERVE : 0,
&args.trans);
if (error)
return error;
xfs_ilock(dp, XFS_ILOCK_EXCL);
/*
* No need to make quota reservations here. We expect to release some
* blocks not allocate in the common case.
*/
xfs_trans_ijoin(args.trans, dp, 0);
if (!xfs_inode_hasattr(dp)) {
error = -ENOATTR;
} else if (dp->i_d.di_aformat == XFS_DINODE_FMT_LOCAL) {
ASSERT(dp->i_afp->if_flags & XFS_IFINLINE);
error = xfs_attr_shortform_remove(&args);
} else if (xfs_bmap_one_block(dp, XFS_ATTR_FORK)) {
error = xfs_attr_leaf_removename(&args);
} else {
error = xfs_attr_node_removename(&args);
}
if (error)
goto out;
/*
* If this is a synchronous mount, make sure that the
* transaction goes to disk before returning to the user.
*/
if (mp->m_flags & XFS_MOUNT_WSYNC)
xfs_trans_set_sync(args.trans);
if ((flags & ATTR_KERNOTIME) == 0)
xfs_trans_ichgtime(args.trans, dp, XFS_ICHGTIME_CHG);
/*
* Commit the last in the sequence of transactions.
*/
xfs_trans_log_inode(args.trans, dp, XFS_ILOG_CORE);
error = xfs_trans_commit(args.trans);
xfs_iunlock(dp, XFS_ILOCK_EXCL);
return error;
out:
if (args.trans)
xfs_trans_cancel(args.trans);
xfs_iunlock(dp, XFS_ILOCK_EXCL);
return error;
}
/*
* Allocate a block and fill it with dquots.
* This is called when the bmapi finds a hole.
*/
STATIC int
xfs_qm_dqalloc(
xfs_trans_t **tpp,
xfs_mount_t *mp,
xfs_dquot_t *dqp,
xfs_inode_t *quotip,
xfs_fileoff_t offset_fsb,
xfs_buf_t **O_bpp)
{
xfs_fsblock_t firstblock;
xfs_bmap_free_t flist;
xfs_bmbt_irec_t map;
int nmaps, error, committed;
xfs_buf_t *bp;
xfs_trans_t *tp = *tpp;
ASSERT(tp != NULL);
xfs_dqtrace_entry(dqp, "DQALLOC");
/*
* Initialize the bmap freelist prior to calling bmapi code.
*/
XFS_BMAP_INIT(&flist, &firstblock);
xfs_ilock(quotip, XFS_ILOCK_EXCL);
/*
* Return if this type of quotas is turned off while we didn't
* have an inode lock
*/
if (XFS_IS_THIS_QUOTA_OFF(dqp)) {
xfs_iunlock(quotip, XFS_ILOCK_EXCL);
return (ESRCH);
}
/*
* xfs_trans_commit normally decrements the vnode ref count
* when it unlocks the inode. Since we want to keep the quota
* inode around, we bump the vnode ref count now.
*/
VN_HOLD(XFS_ITOV(quotip));
xfs_trans_ijoin(tp, quotip, XFS_ILOCK_EXCL);
nmaps = 1;
if ((error = xfs_bmapi(tp, quotip,
offset_fsb, XFS_DQUOT_CLUSTER_SIZE_FSB,
XFS_BMAPI_METADATA | XFS_BMAPI_WRITE,
&firstblock,
XFS_QM_DQALLOC_SPACE_RES(mp),
&map, &nmaps, &flist))) {
goto error0;
}
ASSERT(map.br_blockcount == XFS_DQUOT_CLUSTER_SIZE_FSB);
ASSERT(nmaps == 1);
ASSERT((map.br_startblock != DELAYSTARTBLOCK) &&
(map.br_startblock != HOLESTARTBLOCK));
/*
* Keep track of the blkno to save a lookup later
*/
dqp->q_blkno = XFS_FSB_TO_DADDR(mp, map.br_startblock);
/* now we can just get the buffer (there's nothing to read yet) */
bp = xfs_trans_get_buf(tp, mp->m_ddev_targp,
dqp->q_blkno,
XFS_QI_DQCHUNKLEN(mp),
0);
if (!bp || (error = XFS_BUF_GETERROR(bp)))
goto error1;
/*
* Make a chunk of dquots out of this buffer and log
* the entire thing.
*/
xfs_qm_init_dquot_blk(tp, mp, be32_to_cpu(dqp->q_core.d_id),
dqp->dq_flags & XFS_DQ_ALLTYPES, bp);
/*
* xfs_bmap_finish() may commit the current transaction and
* start a second transaction if the freelist is not empty.
*
* Since we still want to modify this buffer, we need to
* ensure that the buffer is not released on commit of
* the first transaction and ensure the buffer is added to the
* second transaction.
*
* If there is only one transaction then don't stop the buffer
* from being released when it commits later on.
*/
xfs_trans_bhold(tp, bp);
if ((error = xfs_bmap_finish(tpp, &flist, firstblock, &committed))) {
goto error1;
}
if (committed) {
tp = *tpp;
xfs_trans_bjoin(tp, bp);
} else {
xfs_trans_bhold_release(tp, bp);
}
*O_bpp = bp;
return 0;
error1:
xfs_bmap_cancel(&flist);
error0:
xfs_iunlock(quotip, XFS_ILOCK_EXCL);
return (error);
}
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;
}
ssize_t /* bytes written, or (-) error */
xfs_write(
bhv_desc_t *bdp,
struct kiocb *iocb,
const struct iovec *iovp,
unsigned int nsegs,
loff_t *offset,
int ioflags,
cred_t *credp)
{
struct file *file = iocb->ki_filp;
struct address_space *mapping = file->f_mapping;
struct inode *inode = mapping->host;
unsigned long segs = nsegs;
xfs_inode_t *xip;
xfs_mount_t *mp;
ssize_t ret = 0, error = 0;
xfs_fsize_t isize, new_size;
xfs_iocore_t *io;
vnode_t *vp;
unsigned long seg;
int iolock;
int eventsent = 0;
vrwlock_t locktype;
size_t ocount = 0, count;
loff_t pos;
int need_isem = 1, need_flush = 0;
XFS_STATS_INC(xs_write_calls);
vp = BHV_TO_VNODE(bdp);
xip = XFS_BHVTOI(bdp);
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.
*/
ocount += iv->iov_len;
if (unlikely((ssize_t)(ocount|iv->iov_len) < 0))
return -EINVAL;
if (access_ok(VERIFY_READ, iv->iov_base, iv->iov_len))
continue;
if (seg == 0)
return -EFAULT;
segs = seg;
ocount -= iv->iov_len; /* This segment is no good */
break;
}
count = ocount;
pos = *offset;
if (count == 0)
return 0;
io = &xip->i_iocore;
mp = io->io_mount;
if (XFS_FORCED_SHUTDOWN(mp))
return -EIO;
if (ioflags & IO_ISDIRECT) {
xfs_buftarg_t *target =
(xip->i_d.di_flags & XFS_DIFLAG_REALTIME) ?
mp->m_rtdev_targp : mp->m_ddev_targp;
if ((pos & target->pbr_smask) || (count & target->pbr_smask))
return XFS_ERROR(-EINVAL);
if (!VN_CACHED(vp) && pos < i_size_read(inode))
need_isem = 0;
if (VN_CACHED(vp))
need_flush = 1;
}
relock:
if (need_isem) {
iolock = XFS_IOLOCK_EXCL;
locktype = VRWLOCK_WRITE;
down(&inode->i_sem);
} else {
iolock = XFS_IOLOCK_SHARED;
locktype = VRWLOCK_WRITE_DIRECT;
}
xfs_ilock(xip, XFS_ILOCK_EXCL|iolock);
isize = i_size_read(inode);
if (file->f_flags & O_APPEND)
*offset = isize;
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_isem;
}
new_size = pos + count;
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 = pos;
int dmflags = FILP_DELAY_FLAG(file);
if (need_isem)
dmflags |= DM_FLAGS_ISEM;
xfs_iunlock(xip, XFS_ILOCK_EXCL);
error = XFS_SEND_DATA(xip->i_mount, DM_EVENT_WRITE, vp,
pos, count,
dmflags, &locktype);
if (error) {
xfs_iunlock(xip, iolock);
goto out_unlock_isem;
}
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 != isize) {
pos = 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 (!(ioflags & IO_INVIS)) {
xfs_ichgtime(xip, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
inode_update_time(inode, 1);
}
/*
* 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 > isize) {
error = xfs_zero_eof(BHV_TO_VNODE(bdp), io, pos,
isize, pos + count);
if (error) {
xfs_iunlock(xip, XFS_ILOCK_EXCL|iolock);
goto out_unlock_isem;
}
}
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 = -remove_suid(file->f_dentry);
if (unlikely(error)) {
xfs_iunlock(xip, iolock);
goto out_unlock_isem;
}
}
retry:
/* We can write back this queue in page reclaim */
current->backing_dev_info = mapping->backing_dev_info;
if ((ioflags & IO_ISDIRECT)) {
if (need_flush) {
xfs_inval_cached_trace(io, pos, -1,
ctooff(offtoct(pos)), -1);
VOP_FLUSHINVAL_PAGES(vp, ctooff(offtoct(pos)),
-1, FI_REMAPF_LOCKED);
}
if (need_isem) {
/* demote the lock now the cached pages are gone */
XFS_ILOCK_DEMOTE(mp, io, XFS_IOLOCK_EXCL);
up(&inode->i_sem);
iolock = XFS_IOLOCK_SHARED;
locktype = VRWLOCK_WRITE_DIRECT;
need_isem = 0;
}
xfs_rw_enter_trace(XFS_DIOWR_ENTER, io, (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;
need_isem = 1;
ioflags &= ~IO_ISDIRECT;
xfs_iunlock(xip, iolock);
goto relock;
}
} else {
xfs_rw_enter_trace(XFS_WRITE_ENTER, io, (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)
ret = wait_on_sync_kiocb(iocb);
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)
goto out_unlock_isem;
xfs_rwlock(bdp, locktype);
pos = 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) {
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);
}
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)) {
/*
* 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)) {
xfs_inode_log_item_t *iip = xip->i_itemp;
/*
* 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.
*/
if (iip && iip->ili_last_lsn) {
xfs_log_force(mp, iip->ili_last_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, NULL);
xfs_iunlock(xip, XFS_ILOCK_EXCL);
if (error)
goto out_unlock_internal;
}
}
xfs_rwunlock(bdp, locktype);
if (need_isem)
up(&inode->i_sem);
error = sync_page_range(inode, mapping, pos, ret);
if (!error)
error = ret;
return error;
}
out_unlock_internal:
xfs_rwunlock(bdp, locktype);
out_unlock_isem:
if (need_isem)
up(&inode->i_sem);
return -error;
}
/*
* Free a symlink that has blocks associated with it.
*/
STATIC int
xfs_inactive_symlink_rmt(
struct xfs_inode *ip)
{
xfs_buf_t *bp;
int committed;
int done;
int error;
xfs_fsblock_t first_block;
xfs_bmap_free_t free_list;
int i;
xfs_mount_t *mp;
xfs_bmbt_irec_t mval[XFS_SYMLINK_MAPS];
int nmaps;
int size;
xfs_trans_t *tp;
mp = ip->i_mount;
ASSERT(ip->i_df.if_flags & XFS_IFEXTENTS);
/*
* We're freeing a symlink that has some
* blocks allocated to it. Free the
* blocks here. We know that we've got
* either 1 or 2 extents and that we can
* free them all in one bunmapi call.
*/
ASSERT(ip->i_d.di_nextents > 0 && ip->i_d.di_nextents <= 2);
tp = xfs_trans_alloc(mp, XFS_TRANS_INACTIVE);
error = xfs_trans_reserve(tp, &M_RES(mp)->tr_itruncate, 0, 0);
if (error) {
xfs_trans_cancel(tp, 0);
return error;
}
xfs_ilock(ip, XFS_ILOCK_EXCL);
xfs_trans_ijoin(tp, ip, 0);
/*
* Lock the inode, fix the size, and join it to the transaction.
* Hold it so in the normal path, we still have it locked for
* the second transaction. In the error paths we need it
* held so the cancel won't rele it, see below.
*/
size = (int)ip->i_d.di_size;
ip->i_d.di_size = 0;
xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
/*
* Find the block(s) so we can inval and unmap them.
*/
done = 0;
xfs_bmap_init(&free_list, &first_block);
nmaps = ARRAY_SIZE(mval);
error = xfs_bmapi_read(ip, 0, xfs_symlink_blocks(mp, size),
mval, &nmaps, 0);
if (error)
goto error_trans_cancel;
/*
* Invalidate the block(s). No validation is done.
*/
for (i = 0; i < nmaps; i++) {
bp = xfs_trans_get_buf(tp, mp->m_ddev_targp,
XFS_FSB_TO_DADDR(mp, mval[i].br_startblock),
XFS_FSB_TO_BB(mp, mval[i].br_blockcount), 0);
if (!bp) {
error = ENOMEM;
goto error_bmap_cancel;
}
xfs_trans_binval(tp, bp);
}
/*
* Unmap the dead block(s) to the free_list.
*/
error = xfs_bunmapi(tp, ip, 0, size, XFS_BMAPI_METADATA, nmaps,
&first_block, &free_list, &done);
if (error)
goto error_bmap_cancel;
ASSERT(done);
/*
* Commit the first transaction. This logs the EFI and the inode.
*/
error = xfs_bmap_finish(&tp, &free_list, &committed);
if (error)
goto error_bmap_cancel;
/*
* The transaction must have been committed, since there were
* actually extents freed by xfs_bunmapi. See xfs_bmap_finish.
* The new tp has the extent freeing and EFDs.
*/
ASSERT(committed);
/*
* The first xact was committed, so add the inode to the new one.
* Mark it dirty so it will be logged and moved forward in the log as
* part of every commit.
*/
xfs_trans_ijoin(tp, ip, 0);
xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
/*
* Commit the transaction containing extent freeing and EFDs.
*/
error = xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES);
if (error) {
ASSERT(XFS_FORCED_SHUTDOWN(mp));
goto error_unlock;
}
/*
* Remove the memory for extent descriptions (just bookkeeping).
*/
if (ip->i_df.if_bytes)
xfs_idata_realloc(ip, -ip->i_df.if_bytes, XFS_DATA_FORK);
ASSERT(ip->i_df.if_bytes == 0);
xfs_iunlock(ip, XFS_ILOCK_EXCL);
return 0;
error_bmap_cancel:
xfs_bmap_cancel(&free_list);
error_trans_cancel:
xfs_trans_cancel(tp, XFS_TRANS_RELEASE_LOG_RES | XFS_TRANS_ABORT);
error_unlock:
xfs_iunlock(ip, XFS_ILOCK_EXCL);
return error;
}
int
xfs_alloc_file_space(
struct xfs_inode *ip,
xfs_off_t offset,
xfs_off_t len,
int alloc_type)
{
xfs_mount_t *mp = ip->i_mount;
xfs_off_t count;
xfs_filblks_t allocated_fsb;
xfs_filblks_t allocatesize_fsb;
xfs_extlen_t extsz, temp;
xfs_fileoff_t startoffset_fsb;
xfs_fsblock_t firstfsb;
int nimaps;
int quota_flag;
int rt;
xfs_trans_t *tp;
xfs_bmbt_irec_t imaps[1], *imapp;
xfs_bmap_free_t free_list;
uint qblocks, resblks, resrtextents;
int committed;
int error;
trace_xfs_alloc_file_space(ip);
if (XFS_FORCED_SHUTDOWN(mp))
return XFS_ERROR(EIO);
error = xfs_qm_dqattach(ip, 0);
if (error)
return error;
if (len <= 0)
return XFS_ERROR(EINVAL);
rt = XFS_IS_REALTIME_INODE(ip);
extsz = xfs_get_extsz_hint(ip);
count = len;
imapp = &imaps[0];
nimaps = 1;
startoffset_fsb = XFS_B_TO_FSBT(mp, offset);
allocatesize_fsb = XFS_B_TO_FSB(mp, count);
/*
* Allocate file space until done or until there is an error
*/
while (allocatesize_fsb && !error) {
xfs_fileoff_t s, e;
/*
* Determine space reservations for data/realtime.
*/
if (unlikely(extsz)) {
s = startoffset_fsb;
do_div(s, extsz);
s *= extsz;
e = startoffset_fsb + allocatesize_fsb;
if ((temp = do_mod(startoffset_fsb, extsz)))
e += temp;
if ((temp = do_mod(e, extsz)))
e += extsz - temp;
} else {
s = 0;
e = allocatesize_fsb;
}
/*
* The transaction reservation is limited to a 32-bit block
* count, hence we need to limit the number of blocks we are
* trying to reserve to avoid an overflow. We can't allocate
* more than @nimaps extents, and an extent is limited on disk
* to MAXEXTLEN (21 bits), so use that to enforce the limit.
*/
resblks = min_t(xfs_fileoff_t, (e - s), (MAXEXTLEN * nimaps));
if (unlikely(rt)) {
resrtextents = qblocks = resblks;
resrtextents /= mp->m_sb.sb_rextsize;
resblks = XFS_DIOSTRAT_SPACE_RES(mp, 0);
quota_flag = XFS_QMOPT_RES_RTBLKS;
} else {
resrtextents = 0;
resblks = qblocks = XFS_DIOSTRAT_SPACE_RES(mp, resblks);
quota_flag = XFS_QMOPT_RES_REGBLKS;
}
/*
* Allocate and setup the transaction.
*/
tp = xfs_trans_alloc(mp, XFS_TRANS_DIOSTRAT);
error = xfs_trans_reserve(tp, &M_RES(mp)->tr_write,
resblks, resrtextents);
/*
* Check for running out of space
*/
if (error) {
/*
* Free the transaction structure.
*/
ASSERT(error == ENOSPC || XFS_FORCED_SHUTDOWN(mp));
xfs_trans_cancel(tp, 0);
break;
}
xfs_ilock(ip, XFS_ILOCK_EXCL);
error = xfs_trans_reserve_quota_nblks(tp, ip, qblocks,
0, quota_flag);
if (error)
goto error1;
xfs_trans_ijoin(tp, ip, 0);
xfs_bmap_init(&free_list, &firstfsb);
error = xfs_bmapi_write(tp, ip, startoffset_fsb,
allocatesize_fsb, alloc_type, &firstfsb,
0, imapp, &nimaps, &free_list);
if (error) {
goto error0;
}
/*
* Complete the transaction
*/
error = xfs_bmap_finish(&tp, &free_list, &committed);
if (error) {
goto error0;
}
error = xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES);
xfs_iunlock(ip, XFS_ILOCK_EXCL);
if (error) {
break;
}
allocated_fsb = imapp->br_blockcount;
if (nimaps == 0) {
error = XFS_ERROR(ENOSPC);
break;
}
startoffset_fsb += allocated_fsb;
allocatesize_fsb -= allocated_fsb;
}
return error;
error0: /* Cancel bmap, unlock inode, unreserve quota blocks, cancel trans */
xfs_bmap_cancel(&free_list);
xfs_trans_unreserve_quota_nblks(tp, ip, (long)qblocks, 0, quota_flag);
error1: /* Just cancel transaction */
xfs_trans_cancel(tp, XFS_TRANS_RELEASE_LOG_RES | XFS_TRANS_ABORT);
xfs_iunlock(ip, XFS_ILOCK_EXCL);
return error;
}
/*
* xfs_rename
*/
int
xfs_rename(
xfs_inode_t *src_dp,
struct xfs_name *src_name,
xfs_inode_t *src_ip,
xfs_inode_t *target_dp,
struct xfs_name *target_name,
xfs_inode_t *target_ip)
{
xfs_trans_t *tp = NULL;
xfs_mount_t *mp = src_dp->i_mount;
int new_parent; /* moving to a new dir */
int src_is_directory; /* src_name is a directory */
int error;
xfs_bmap_free_t free_list;
xfs_fsblock_t first_block;
int cancel_flags;
int committed;
xfs_inode_t *inodes[4];
int spaceres;
int num_inodes;
xfs_itrace_entry(src_dp);
xfs_itrace_entry(target_dp);
if (DM_EVENT_ENABLED(src_dp, DM_EVENT_RENAME) ||
DM_EVENT_ENABLED(target_dp, DM_EVENT_RENAME)) {
error = XFS_SEND_NAMESP(mp, DM_EVENT_RENAME,
src_dp, DM_RIGHT_NULL,
target_dp, DM_RIGHT_NULL,
src_name->name, target_name->name,
0, 0, 0);
if (error)
return error;
}
/* Return through std_return after this point. */
new_parent = (src_dp != target_dp);
src_is_directory = ((src_ip->i_d.di_mode & S_IFMT) == S_IFDIR);
if (src_is_directory) {
/*
* Check for link count overflow on target_dp
*/
if (target_ip == NULL && new_parent &&
target_dp->i_d.di_nlink >= XFS_MAXLINK) {
error = XFS_ERROR(EMLINK);
goto std_return;
}
}
xfs_sort_for_rename(src_dp, target_dp, src_ip, target_ip,
inodes, &num_inodes);
xfs_bmap_init(&free_list, &first_block);
tp = xfs_trans_alloc(mp, XFS_TRANS_RENAME);
cancel_flags = XFS_TRANS_RELEASE_LOG_RES;
spaceres = XFS_RENAME_SPACE_RES(mp, target_name->len);
error = xfs_trans_reserve(tp, spaceres, XFS_RENAME_LOG_RES(mp), 0,
XFS_TRANS_PERM_LOG_RES, XFS_RENAME_LOG_COUNT);
if (error == ENOSPC) {
spaceres = 0;
error = xfs_trans_reserve(tp, 0, XFS_RENAME_LOG_RES(mp), 0,
XFS_TRANS_PERM_LOG_RES, XFS_RENAME_LOG_COUNT);
}
if (error) {
xfs_trans_cancel(tp, 0);
goto std_return;
}
/*
* Attach the dquots to the inodes
*/
if ((error = XFS_QM_DQVOPRENAME(mp, inodes))) {
xfs_trans_cancel(tp, cancel_flags);
goto std_return;
}
/*
* Lock all the participating inodes. Depending upon whether
* the target_name exists in the target directory, and
* whether the target directory is the same as the source
* directory, we can lock from 2 to 4 inodes.
*/
xfs_lock_inodes(inodes, num_inodes, XFS_ILOCK_EXCL);
/*
* Join all the inodes to the transaction. From this point on,
* we can rely on either trans_commit or trans_cancel to unlock
* them. Note that we need to add a vnode reference to the
* directories since trans_commit & trans_cancel will decrement
* them when they unlock the inodes. Also, we need to be careful
* not to add an inode to the transaction more than once.
*/
IHOLD(src_dp);
xfs_trans_ijoin(tp, src_dp, XFS_ILOCK_EXCL);
if (new_parent) {
IHOLD(target_dp);
xfs_trans_ijoin(tp, target_dp, XFS_ILOCK_EXCL);
}
IHOLD(src_ip);
xfs_trans_ijoin(tp, src_ip, XFS_ILOCK_EXCL);
if (target_ip) {
IHOLD(target_ip);
xfs_trans_ijoin(tp, target_ip, XFS_ILOCK_EXCL);
}
/*
* If we are using project inheritance, we only allow renames
* into our tree when the project IDs are the same; else the
* tree quota mechanism would be circumvented.
*/
if (unlikely((target_dp->i_d.di_flags & XFS_DIFLAG_PROJINHERIT) &&
(target_dp->i_d.di_projid != src_ip->i_d.di_projid))) {
error = XFS_ERROR(EXDEV);
goto error_return;
}
/*
* Set up the target.
*/
if (target_ip == NULL) {
/*
* If there's no space reservation, check the entry will
* fit before actually inserting it.
*/
error = xfs_dir_canenter(tp, target_dp, target_name, spaceres);
if (error)
goto error_return;
/*
* If target does not exist and the rename crosses
* directories, adjust the target directory link count
* to account for the ".." reference from the new entry.
*/
error = xfs_dir_createname(tp, target_dp, target_name,
src_ip->i_ino, &first_block,
&free_list, spaceres);
if (error == ENOSPC)
goto error_return;
if (error)
goto abort_return;
xfs_ichgtime(target_dp, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
if (new_parent && src_is_directory) {
error = xfs_bumplink(tp, target_dp);
if (error)
goto abort_return;
}
} else { /* target_ip != NULL */
/*
* If target exists and it's a directory, check that both
* target and source are directories and that target can be
* destroyed, or that neither is a directory.
*/
if ((target_ip->i_d.di_mode & S_IFMT) == S_IFDIR) {
/*
* Make sure target dir is empty.
*/
if (!(xfs_dir_isempty(target_ip)) ||
(target_ip->i_d.di_nlink > 2)) {
error = XFS_ERROR(EEXIST);
goto error_return;
}
}
/*
* Link the source inode under the target name.
* If the source inode is a directory and we are moving
* it across directories, its ".." entry will be
* inconsistent until we replace that down below.
*
* In case there is already an entry with the same
* name at the destination directory, remove it first.
*/
error = xfs_dir_replace(tp, target_dp, target_name,
src_ip->i_ino,
&first_block, &free_list, spaceres);
if (error)
goto abort_return;
xfs_ichgtime(target_dp, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
/*
* Decrement the link count on the target since the target
* dir no longer points to it.
*/
error = xfs_droplink(tp, target_ip);
if (error)
goto abort_return;
if (src_is_directory) {
/*
* Drop the link from the old "." entry.
*/
error = xfs_droplink(tp, target_ip);
if (error)
goto abort_return;
}
} /* target_ip != NULL */
/*
* Remove the source.
*/
if (new_parent && src_is_directory) {
/*
* Rewrite the ".." entry to point to the new
* directory.
*/
error = xfs_dir_replace(tp, src_ip, &xfs_name_dotdot,
target_dp->i_ino,
&first_block, &free_list, spaceres);
ASSERT(error != EEXIST);
if (error)
goto abort_return;
}
/*
* We always want to hit the ctime on the source inode.
*
* This isn't strictly required by the standards since the source
* inode isn't really being changed, but old unix file systems did
* it and some incremental backup programs won't work without it.
*/
xfs_ichgtime(src_ip, XFS_ICHGTIME_CHG);
/*
* Adjust the link count on src_dp. This is necessary when
* renaming a directory, either within one parent when
* the target existed, or across two parent directories.
*/
if (src_is_directory && (new_parent || target_ip != NULL)) {
/*
* Decrement link count on src_directory since the
* entry that's moved no longer points to it.
*/
error = xfs_droplink(tp, src_dp);
if (error)
goto abort_return;
}
error = xfs_dir_removename(tp, src_dp, src_name, src_ip->i_ino,
&first_block, &free_list, spaceres);
if (error)
goto abort_return;
xfs_ichgtime(src_dp, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
xfs_trans_log_inode(tp, src_dp, XFS_ILOG_CORE);
if (new_parent)
xfs_trans_log_inode(tp, target_dp, XFS_ILOG_CORE);
/*
* If this is a synchronous mount, make sure that the
* rename transaction goes to disk before returning to
* the user.
*/
if (mp->m_flags & (XFS_MOUNT_WSYNC|XFS_MOUNT_DIRSYNC)) {
xfs_trans_set_sync(tp);
}
error = xfs_bmap_finish(&tp, &free_list, &committed);
if (error) {
xfs_bmap_cancel(&free_list);
xfs_trans_cancel(tp, (XFS_TRANS_RELEASE_LOG_RES |
XFS_TRANS_ABORT));
goto std_return;
}
/*
* trans_commit will unlock src_ip, target_ip & decrement
* the vnode references.
*/
error = xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES);
/* Fall through to std_return with error = 0 or errno from
* xfs_trans_commit */
std_return:
if (DM_EVENT_ENABLED(src_dp, DM_EVENT_POSTRENAME) ||
DM_EVENT_ENABLED(target_dp, DM_EVENT_POSTRENAME)) {
(void) XFS_SEND_NAMESP (mp, DM_EVENT_POSTRENAME,
src_dp, DM_RIGHT_NULL,
target_dp, DM_RIGHT_NULL,
src_name->name, target_name->name,
0, error, 0);
}
return error;
abort_return:
cancel_flags |= XFS_TRANS_ABORT;
/* FALLTHROUGH */
error_return:
xfs_bmap_cancel(&free_list);
xfs_trans_cancel(tp, cancel_flags);
goto std_return;
}
int
xfs_setattr_nonsize(
struct xfs_inode *ip,
struct iattr *iattr,
int flags)
{
xfs_mount_t *mp = ip->i_mount;
struct inode *inode = VFS_I(ip);
int mask = iattr->ia_valid;
xfs_trans_t *tp;
int error;
kuid_t uid = GLOBAL_ROOT_UID, iuid = GLOBAL_ROOT_UID;
kgid_t gid = GLOBAL_ROOT_GID, igid = GLOBAL_ROOT_GID;
struct xfs_dquot *udqp = NULL, *gdqp = NULL;
struct xfs_dquot *olddquot1 = NULL, *olddquot2 = NULL;
trace_xfs_setattr(ip);
/* If acls are being inherited, we already have this checked */
if (!(flags & XFS_ATTR_NOACL)) {
if (mp->m_flags & XFS_MOUNT_RDONLY)
return XFS_ERROR(EROFS);
if (XFS_FORCED_SHUTDOWN(mp))
return XFS_ERROR(EIO);
error = -inode_change_ok(inode, iattr);
if (error)
return XFS_ERROR(error);
}
ASSERT((mask & ATTR_SIZE) == 0);
/*
* If disk quotas is on, we make sure that the dquots do exist on disk,
* before we start any other transactions. Trying to do this later
* is messy. We don't care to take a readlock to look at the ids
* in inode here, because we can't hold it across the trans_reserve.
* If the IDs do change before we take the ilock, we're covered
* because the i_*dquot fields will get updated anyway.
*/
if (XFS_IS_QUOTA_ON(mp) && (mask & (ATTR_UID|ATTR_GID))) {
uint qflags = 0;
if ((mask & ATTR_UID) && XFS_IS_UQUOTA_ON(mp)) {
uid = iattr->ia_uid;
qflags |= XFS_QMOPT_UQUOTA;
} else {
uid = inode->i_uid;
}
if ((mask & ATTR_GID) && XFS_IS_GQUOTA_ON(mp)) {
gid = iattr->ia_gid;
qflags |= XFS_QMOPT_GQUOTA;
} else {
gid = inode->i_gid;
}
/*
* We take a reference when we initialize udqp and gdqp,
* so it is important that we never blindly double trip on
* the same variable. See xfs_create() for an example.
*/
ASSERT(udqp == NULL);
ASSERT(gdqp == NULL);
error = xfs_qm_vop_dqalloc(ip, xfs_kuid_to_uid(uid),
xfs_kgid_to_gid(gid),
xfs_get_projid(ip),
qflags, &udqp, &gdqp, NULL);
if (error)
return error;
}
tp = xfs_trans_alloc(mp, XFS_TRANS_SETATTR_NOT_SIZE);
error = xfs_trans_reserve(tp, &M_RES(mp)->tr_ichange, 0, 0);
if (error)
goto out_dqrele;
xfs_ilock(ip, XFS_ILOCK_EXCL);
/*
* Change file ownership. Must be the owner or privileged.
*/
if (mask & (ATTR_UID|ATTR_GID)) {
/*
* These IDs could have changed since we last looked at them.
* But, we're assured that if the ownership did change
* while we didn't have the inode locked, inode's dquot(s)
* would have changed also.
*/
iuid = inode->i_uid;
igid = inode->i_gid;
gid = (mask & ATTR_GID) ? iattr->ia_gid : igid;
uid = (mask & ATTR_UID) ? iattr->ia_uid : iuid;
/*
* Do a quota reservation only if uid/gid is actually
* going to change.
*/
if (XFS_IS_QUOTA_RUNNING(mp) &&
((XFS_IS_UQUOTA_ON(mp) && !uid_eq(iuid, uid)) ||
(XFS_IS_GQUOTA_ON(mp) && !gid_eq(igid, gid)))) {
ASSERT(tp);
error = xfs_qm_vop_chown_reserve(tp, ip, udqp, gdqp,
NULL, capable(CAP_FOWNER) ?
XFS_QMOPT_FORCE_RES : 0);
if (error) /* out of quota */
goto out_trans_cancel;
}
}
xfs_trans_ijoin(tp, ip, 0);
/*
* Change file ownership. Must be the owner or privileged.
*/
if (mask & (ATTR_UID|ATTR_GID)) {
/*
* CAP_FSETID overrides the following restrictions:
*
* The set-user-ID and set-group-ID bits of a file will be
* cleared upon successful return from chown()
*/
if ((ip->i_d.di_mode & (S_ISUID|S_ISGID)) &&
!capable(CAP_FSETID))
ip->i_d.di_mode &= ~(S_ISUID|S_ISGID);
/*
* Change the ownerships and register quota modifications
* in the transaction.
*/
if (!uid_eq(iuid, uid)) {
if (XFS_IS_QUOTA_RUNNING(mp) && XFS_IS_UQUOTA_ON(mp)) {
ASSERT(mask & ATTR_UID);
ASSERT(udqp);
olddquot1 = xfs_qm_vop_chown(tp, ip,
&ip->i_udquot, udqp);
}
ip->i_d.di_uid = xfs_kuid_to_uid(uid);
inode->i_uid = uid;
}
if (!gid_eq(igid, gid)) {
if (XFS_IS_QUOTA_RUNNING(mp) && XFS_IS_GQUOTA_ON(mp)) {
ASSERT(xfs_sb_version_has_pquotino(&mp->m_sb) ||
!XFS_IS_PQUOTA_ON(mp));
ASSERT(mask & ATTR_GID);
ASSERT(gdqp);
olddquot2 = xfs_qm_vop_chown(tp, ip,
&ip->i_gdquot, gdqp);
}
ip->i_d.di_gid = xfs_kgid_to_gid(gid);
inode->i_gid = gid;
}
}
if (mask & ATTR_MODE)
xfs_setattr_mode(ip, iattr);
if (mask & (ATTR_ATIME|ATTR_CTIME|ATTR_MTIME))
xfs_setattr_time(ip, iattr);
xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
XFS_STATS_INC(xs_ig_attrchg);
if (mp->m_flags & XFS_MOUNT_WSYNC)
xfs_trans_set_sync(tp);
error = xfs_trans_commit(tp, 0);
xfs_iunlock(ip, XFS_ILOCK_EXCL);
/*
* Release any dquot(s) the inode had kept before chown.
*/
xfs_qm_dqrele(olddquot1);
xfs_qm_dqrele(olddquot2);
xfs_qm_dqrele(udqp);
xfs_qm_dqrele(gdqp);
if (error)
return XFS_ERROR(error);
/*
* XXX(hch): Updating the ACL entries is not atomic vs the i_mode
* update. We could avoid this with linked transactions
* and passing down the transaction pointer all the way
* to attr_set. No previous user of the generic
* Posix ACL code seems to care about this issue either.
*/
if ((mask & ATTR_MODE) && !(flags & XFS_ATTR_NOACL)) {
error = -posix_acl_chmod(inode, inode->i_mode);
if (error)
return XFS_ERROR(error);
}
return 0;
out_trans_cancel:
xfs_trans_cancel(tp, 0);
xfs_iunlock(ip, XFS_ILOCK_EXCL);
out_dqrele:
xfs_qm_dqrele(udqp);
xfs_qm_dqrele(gdqp);
return error;
}
ssize_t /* bytes written, or (-) error */
xfs_write(
bhv_desc_t *bdp,
struct file *file,
const char *buf,
size_t size,
loff_t *offset,
int ioflags,
cred_t *credp)
{
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;
int iolock;
int eventsent = 0;
vrwlock_t locktype;
XFS_STATS_INC(xs_write_calls);
vp = BHV_TO_VNODE(bdp);
xip = XFS_BHVTOI(bdp);
if (size == 0)
return 0;
io = &xip->i_iocore;
mp = io->io_mount;
fs_check_frozen(vp->v_vfsp, SB_FREEZE_WRITE);
if (XFS_FORCED_SHUTDOWN(xip->i_mount)) {
return -EIO;
}
if (unlikely(ioflags & IO_ISDIRECT)) {
if (((__psint_t)buf & BBMASK) ||
(*offset & mp->m_blockmask) ||
(size & mp->m_blockmask)) {
return XFS_ERROR(-EINVAL);
}
iolock = XFS_IOLOCK_SHARED;
locktype = VRWLOCK_WRITE_DIRECT;
} else {
iolock = XFS_IOLOCK_EXCL;
locktype = VRWLOCK_WRITE;
}
if (ioflags & IO_ISLOCKED)
iolock = 0;
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;
int dmflags = FILP_DELAY_FLAG(file) | DM_SEM_FLAG_RD(ioflags);
xfs_iunlock(xip, XFS_ILOCK_EXCL);
error = XFS_SEND_DATA(xip->i_mount, DM_EVENT_WRITE, vp,
*offset, size,
dmflags, &locktype);
if (error) {
if (iolock) 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;
}
}
/*
* 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;
}
}
if ((ssize_t) size < 0) {
ret = -EINVAL;
goto error;
}
if (!access_ok(VERIFY_READ, buf, size)) {
ret = -EINVAL;
goto error;
}
retry:
if (unlikely(ioflags & IO_ISDIRECT)) {
xfs_inval_cached_pages(vp, io, *offset, 1, 1);
xfs_rw_enter_trace(XFS_DIOWR_ENTER,
io, buf, size, *offset, ioflags);
ret = do_generic_direct_write(file, buf, size, offset);
} else {
xfs_rw_enter_trace(XFS_WRITE_ENTER,
io, buf, size, *offset, ioflags);
ret = do_generic_file_write(file, buf, size, offset);
}
if (unlikely(ioflags & IO_INVIS)) {
/* generic_file_write updates the mtime/ctime but we need
* to undo that because this I/O was supposed to be
* invisible.
*/
struct inode *inode = LINVFS_GET_IP(vp);
inode->i_mtime = xip->i_d.di_mtime.t_sec;
inode->i_ctime = xip->i_d.di_ctime.t_sec;
} else {
xfs_ichgtime(xip, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
}
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;
}
error:
if (ret <= 0) {
if (iolock)
xfs_rwunlock(bdp, locktype);
return ret;
}
XFS_STATS_ADD(xs_write_bytes, ret);
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;
mark_inode_dirty_sync(inode);
}
xfs_iunlock(xip, XFS_ILOCK_EXCL);
}
/* 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, NULL);
xfs_iunlock(xip, XFS_ILOCK_EXCL);
}
}
} /* (ioflags & O_SYNC) */
/*
* If we are coming from an nfsd thread then insert into the
* reference cache.
*/
if (!strcmp(current->comm, "nfsd"))
xfs_refcache_insert(xip);
/* Drop lock this way - the old refcache release is in here */
if (iolock)
xfs_rwunlock(bdp, locktype);
return(ret);
}
/*
* xfs_rename
*/
int
xfs_rename(
bhv_desc_t *src_dir_bdp,
bhv_vname_t *src_vname,
bhv_vnode_t *target_dir_vp,
bhv_vname_t *target_vname,
cred_t *credp)
{
xfs_trans_t *tp;
xfs_inode_t *src_dp, *target_dp, *src_ip, *target_ip;
xfs_mount_t *mp;
int new_parent; /* moving to a new dir */
int src_is_directory; /* src_name is a directory */
int error;
xfs_bmap_free_t free_list;
xfs_fsblock_t first_block;
int cancel_flags;
int committed;
xfs_inode_t *inodes[4];
int target_ip_dropped = 0; /* dropped target_ip link? */
bhv_vnode_t *src_dir_vp;
int spaceres;
int target_link_zero = 0;
int num_inodes;
char *src_name = VNAME(src_vname);
char *target_name = VNAME(target_vname);
int src_namelen = VNAMELEN(src_vname);
int target_namelen = VNAMELEN(target_vname);
src_dir_vp = BHV_TO_VNODE(src_dir_bdp);
vn_trace_entry(src_dir_vp, "xfs_rename", (inst_t *)__return_address);
vn_trace_entry(target_dir_vp, "xfs_rename", (inst_t *)__return_address);
/*
* Find the XFS behavior descriptor for the target directory
* vnode since it was not handed to us.
*/
target_dp = xfs_vtoi(target_dir_vp);
if (target_dp == NULL) {
return XFS_ERROR(EXDEV);
}
src_dp = XFS_BHVTOI(src_dir_bdp);
mp = src_dp->i_mount;
if (DM_EVENT_ENABLED(src_dir_vp->v_vfsp, src_dp, DM_EVENT_RENAME) ||
DM_EVENT_ENABLED(target_dir_vp->v_vfsp,
target_dp, DM_EVENT_RENAME)) {
error = XFS_SEND_NAMESP(mp, DM_EVENT_RENAME,
src_dir_vp, DM_RIGHT_NULL,
target_dir_vp, DM_RIGHT_NULL,
src_name, target_name,
0, 0, 0);
if (error) {
return error;
}
}
/* Return through std_return after this point. */
/*
* Lock all the participating inodes. Depending upon whether
* the target_name exists in the target directory, and
* whether the target directory is the same as the source
* directory, we can lock from 2 to 4 inodes.
* xfs_lock_for_rename() will return ENOENT if src_name
* does not exist in the source directory.
*/
tp = NULL;
error = xfs_lock_for_rename(src_dp, target_dp, src_vname,
target_vname, &src_ip, &target_ip, inodes,
&num_inodes);
if (error) {
/*
* We have nothing locked, no inode references, and
* no transaction, so just get out.
*/
goto std_return;
}
ASSERT(src_ip != NULL);
if ((src_ip->i_d.di_mode & S_IFMT) == S_IFDIR) {
/*
* Check for link count overflow on target_dp
*/
if (target_ip == NULL && (src_dp != target_dp) &&
target_dp->i_d.di_nlink >= XFS_MAXLINK) {
error = XFS_ERROR(EMLINK);
xfs_rename_unlock4(inodes, XFS_ILOCK_SHARED);
goto rele_return;
}
}
/*
* If we are using project inheritance, we only allow renames
* into our tree when the project IDs are the same; else the
* tree quota mechanism would be circumvented.
*/
if (unlikely((target_dp->i_d.di_flags & XFS_DIFLAG_PROJINHERIT) &&
(target_dp->i_d.di_projid != src_ip->i_d.di_projid))) {
error = XFS_ERROR(EXDEV);
xfs_rename_unlock4(inodes, XFS_ILOCK_SHARED);
goto rele_return;
}
new_parent = (src_dp != target_dp);
src_is_directory = ((src_ip->i_d.di_mode & S_IFMT) == S_IFDIR);
/*
* Drop the locks on our inodes so that we can start the transaction.
*/
xfs_rename_unlock4(inodes, XFS_ILOCK_SHARED);
XFS_BMAP_INIT(&free_list, &first_block);
tp = xfs_trans_alloc(mp, XFS_TRANS_RENAME);
cancel_flags = XFS_TRANS_RELEASE_LOG_RES;
spaceres = XFS_RENAME_SPACE_RES(mp, target_namelen);
error = xfs_trans_reserve(tp, spaceres, XFS_RENAME_LOG_RES(mp), 0,
XFS_TRANS_PERM_LOG_RES, XFS_RENAME_LOG_COUNT);
if (error == ENOSPC) {
spaceres = 0;
error = xfs_trans_reserve(tp, 0, XFS_RENAME_LOG_RES(mp), 0,
XFS_TRANS_PERM_LOG_RES, XFS_RENAME_LOG_COUNT);
}
if (error) {
xfs_trans_cancel(tp, 0);
goto rele_return;
}
/*
* Attach the dquots to the inodes
*/
if ((error = XFS_QM_DQVOPRENAME(mp, inodes))) {
xfs_trans_cancel(tp, cancel_flags);
goto rele_return;
}
/*
* Reacquire the inode locks we dropped above.
*/
xfs_lock_inodes(inodes, num_inodes, 0, XFS_ILOCK_EXCL);
/*
* Join all the inodes to the transaction. From this point on,
* we can rely on either trans_commit or trans_cancel to unlock
* them. Note that we need to add a vnode reference to the
* directories since trans_commit & trans_cancel will decrement
* them when they unlock the inodes. Also, we need to be careful
* not to add an inode to the transaction more than once.
*/
VN_HOLD(src_dir_vp);
xfs_trans_ijoin(tp, src_dp, XFS_ILOCK_EXCL);
if (new_parent) {
VN_HOLD(target_dir_vp);
xfs_trans_ijoin(tp, target_dp, XFS_ILOCK_EXCL);
}
if ((src_ip != src_dp) && (src_ip != target_dp)) {
xfs_trans_ijoin(tp, src_ip, XFS_ILOCK_EXCL);
}
if ((target_ip != NULL) &&
(target_ip != src_ip) &&
(target_ip != src_dp) &&
(target_ip != target_dp)) {
xfs_trans_ijoin(tp, target_ip, XFS_ILOCK_EXCL);
}
/*
* Set up the target.
*/
if (target_ip == NULL) {
/*
* If there's no space reservation, check the entry will
* fit before actually inserting it.
*/
if (spaceres == 0 &&
(error = xfs_dir_canenter(tp, target_dp, target_name,
target_namelen)))
goto error_return;
/*
* If target does not exist and the rename crosses
* directories, adjust the target directory link count
* to account for the ".." reference from the new entry.
*/
error = xfs_dir_createname(tp, target_dp, target_name,
target_namelen, src_ip->i_ino,
&first_block, &free_list, spaceres);
if (error == ENOSPC)
goto error_return;
if (error)
goto abort_return;
xfs_ichgtime(target_dp, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
if (new_parent && src_is_directory) {
error = xfs_bumplink(tp, target_dp);
if (error)
goto abort_return;
}
} else { /* target_ip != NULL */
/*
* If target exists and it's a directory, check that both
* target and source are directories and that target can be
* destroyed, or that neither is a directory.
*/
if ((target_ip->i_d.di_mode & S_IFMT) == S_IFDIR) {
/*
* Make sure target dir is empty.
*/
if (!(xfs_dir_isempty(target_ip)) ||
(target_ip->i_d.di_nlink > 2)) {
error = XFS_ERROR(EEXIST);
goto error_return;
}
}
/*
* Link the source inode under the target name.
* If the source inode is a directory and we are moving
* it across directories, its ".." entry will be
* inconsistent until we replace that down below.
*
* In case there is already an entry with the same
* name at the destination directory, remove it first.
*/
error = xfs_dir_replace(tp, target_dp, target_name,
target_namelen, src_ip->i_ino,
&first_block, &free_list, spaceres);
if (error)
goto abort_return;
xfs_ichgtime(target_dp, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
/*
* Decrement the link count on the target since the target
* dir no longer points to it.
*/
error = xfs_droplink(tp, target_ip);
if (error)
goto abort_return;
target_ip_dropped = 1;
if (src_is_directory) {
/*
* Drop the link from the old "." entry.
*/
error = xfs_droplink(tp, target_ip);
if (error)
goto abort_return;
}
/* Do this test while we still hold the locks */
target_link_zero = (target_ip)->i_d.di_nlink==0;
} /* target_ip != NULL */
/*
* Remove the source.
*/
if (new_parent && src_is_directory) {
/*
* Rewrite the ".." entry to point to the new
* directory.
*/
error = xfs_dir_replace(tp, src_ip, "..", 2, target_dp->i_ino,
&first_block, &free_list, spaceres);
ASSERT(error != EEXIST);
if (error)
goto abort_return;
xfs_ichgtime(src_ip, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
} else {
/*
* We always want to hit the ctime on the source inode.
* We do it in the if clause above for the 'new_parent &&
* src_is_directory' case, and here we get all the other
* cases. This isn't strictly required by the standards
* since the source inode isn't really being changed,
* but old unix file systems did it and some incremental
* backup programs won't work without it.
*/
xfs_ichgtime(src_ip, XFS_ICHGTIME_CHG);
}
/*
* Adjust the link count on src_dp. This is necessary when
* renaming a directory, either within one parent when
* the target existed, or across two parent directories.
*/
if (src_is_directory && (new_parent || target_ip != NULL)) {
/*
* Decrement link count on src_directory since the
* entry that's moved no longer points to it.
*/
error = xfs_droplink(tp, src_dp);
if (error)
goto abort_return;
}
error = xfs_dir_removename(tp, src_dp, src_name, src_namelen,
src_ip->i_ino, &first_block, &free_list, spaceres);
if (error)
goto abort_return;
xfs_ichgtime(src_dp, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
/*
* Update the generation counts on all the directory inodes
* that we're modifying.
*/
src_dp->i_gen++;
xfs_trans_log_inode(tp, src_dp, XFS_ILOG_CORE);
if (new_parent) {
target_dp->i_gen++;
xfs_trans_log_inode(tp, target_dp, XFS_ILOG_CORE);
}
/*
* If there was a target inode, take an extra reference on
* it here so that it doesn't go to xfs_inactive() from
* within the commit.
*/
if (target_ip != NULL) {
IHOLD(target_ip);
}
/*
* If this is a synchronous mount, make sure that the
* rename transaction goes to disk before returning to
* the user.
*/
if (mp->m_flags & (XFS_MOUNT_WSYNC|XFS_MOUNT_DIRSYNC)) {
xfs_trans_set_sync(tp);
}
/*
* Take refs. for vop_link_removed calls below. No need to worry
* about directory refs. because the caller holds them.
*
* Do holds before the xfs_bmap_finish since it might rele them down
* to zero.
*/
if (target_ip_dropped)
IHOLD(target_ip);
IHOLD(src_ip);
error = xfs_bmap_finish(&tp, &free_list, &committed);
if (error) {
xfs_bmap_cancel(&free_list);
xfs_trans_cancel(tp, (XFS_TRANS_RELEASE_LOG_RES |
XFS_TRANS_ABORT));
if (target_ip != NULL) {
IRELE(target_ip);
}
if (target_ip_dropped) {
IRELE(target_ip);
}
IRELE(src_ip);
goto std_return;
}
/*
* trans_commit will unlock src_ip, target_ip & decrement
* the vnode references.
*/
error = xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES);
if (target_ip != NULL) {
xfs_refcache_purge_ip(target_ip);
IRELE(target_ip);
}
/*
* Let interposed file systems know about removed links.
*/
if (target_ip_dropped) {
bhv_vop_link_removed(XFS_ITOV(target_ip), target_dir_vp,
target_link_zero);
IRELE(target_ip);
}
IRELE(src_ip);
/* Fall through to std_return with error = 0 or errno from
* xfs_trans_commit */
std_return:
if (DM_EVENT_ENABLED(src_dir_vp->v_vfsp, src_dp, DM_EVENT_POSTRENAME) ||
DM_EVENT_ENABLED(target_dir_vp->v_vfsp,
target_dp, DM_EVENT_POSTRENAME)) {
(void) XFS_SEND_NAMESP (mp, DM_EVENT_POSTRENAME,
src_dir_vp, DM_RIGHT_NULL,
target_dir_vp, DM_RIGHT_NULL,
src_name, target_name,
0, error, 0);
}
return error;
abort_return:
cancel_flags |= XFS_TRANS_ABORT;
/* FALLTHROUGH */
error_return:
xfs_bmap_cancel(&free_list);
xfs_trans_cancel(tp, cancel_flags);
goto std_return;
rele_return:
IRELE(src_ip);
if (target_ip != NULL) {
IRELE(target_ip);
}
goto std_return;
}
/*
* Add a name to a Btree-format attribute list.
*
* This will involve walking down the Btree, and may involve splitting
* leaf nodes and even splitting intermediate nodes up to and including
* the root node (a special case of an intermediate node).
*
* "Remote" attribute values confuse the issue and atomic rename operations
* add a whole extra layer of confusion on top of that.
*/
STATIC int
xfs_attr_node_addname(xfs_da_args_t *args)
{
xfs_da_state_t *state;
xfs_da_state_blk_t *blk;
xfs_inode_t *dp;
xfs_mount_t *mp;
int committed, retval, error;
trace_xfs_attr_node_addname(args);
/*
* Fill in bucket of arguments/results/context to carry around.
*/
dp = args->dp;
mp = dp->i_mount;
restart:
state = xfs_da_state_alloc();
state->args = args;
state->mp = mp;
/*
* Search to see if name already exists, and get back a pointer
* to where it should go.
*/
error = xfs_da3_node_lookup_int(state, &retval);
if (error)
goto out;
blk = &state->path.blk[ state->path.active-1 ];
ASSERT(blk->magic == XFS_ATTR_LEAF_MAGIC);
if ((args->flags & ATTR_REPLACE) && (retval == -ENOATTR)) {
goto out;
} else if (retval == -EEXIST) {
if (args->flags & ATTR_CREATE)
goto out;
trace_xfs_attr_node_replace(args);
/* save the attribute state for later removal*/
args->op_flags |= XFS_DA_OP_RENAME; /* atomic rename op */
args->blkno2 = args->blkno; /* set 2nd entry info*/
args->index2 = args->index;
args->rmtblkno2 = args->rmtblkno;
args->rmtblkcnt2 = args->rmtblkcnt;
args->rmtvaluelen2 = args->rmtvaluelen;
/*
* clear the remote attr state now that it is saved so that the
* values reflect the state of the attribute we are about to
* add, not the attribute we just found and will remove later.
*/
args->rmtblkno = 0;
args->rmtblkcnt = 0;
args->rmtvaluelen = 0;
}
retval = xfs_attr3_leaf_add(blk->bp, state->args);
if (retval == -ENOSPC) {
if (state->path.active == 1) {
/*
* Its really a single leaf node, but it had
* out-of-line values so it looked like it *might*
* have been a b-tree.
*/
xfs_da_state_free(state);
state = NULL;
xfs_bmap_init(args->flist, args->firstblock);
error = xfs_attr3_leaf_to_node(args);
if (!error) {
error = xfs_bmap_finish(&args->trans,
args->flist,
&committed);
}
if (error) {
ASSERT(committed);
args->trans = NULL;
xfs_bmap_cancel(args->flist);
goto out;
}
/*
* bmap_finish() may have committed the last trans
* and started a new one. We need the inode to be
* in all transactions.
*/
if (committed)
xfs_trans_ijoin(args->trans, dp, 0);
/*
* Commit the node conversion and start the next
* trans in the chain.
*/
error = xfs_trans_roll(&args->trans, dp);
if (error)
goto out;
goto restart;
}
/*
* Split as many Btree elements as required.
* This code tracks the new and old attr's location
* in the index/blkno/rmtblkno/rmtblkcnt fields and
* in the index2/blkno2/rmtblkno2/rmtblkcnt2 fields.
*/
xfs_bmap_init(args->flist, args->firstblock);
error = xfs_da3_split(state);
if (!error) {
error = xfs_bmap_finish(&args->trans, args->flist,
&committed);
}
if (error) {
ASSERT(committed);
args->trans = NULL;
xfs_bmap_cancel(args->flist);
goto out;
}
/*
* bmap_finish() may have committed the last trans and started
* a new one. We need the inode to be in all transactions.
*/
if (committed)
xfs_trans_ijoin(args->trans, dp, 0);
} else {
/*
* Addition succeeded, update Btree hashvals.
*/
xfs_da3_fixhashpath(state, &state->path);
}
/*
* Kill the state structure, we're done with it and need to
* allow the buffers to come back later.
*/
xfs_da_state_free(state);
state = NULL;
/*
* Commit the leaf addition or btree split and start the next
* trans in the chain.
*/
error = xfs_trans_roll(&args->trans, dp);
if (error)
goto out;
/*
* If there was an out-of-line value, allocate the blocks we
* identified for its storage and copy the value. This is done
* after we create the attribute so that we don't overflow the
* maximum size of a transaction and/or hit a deadlock.
*/
if (args->rmtblkno > 0) {
error = xfs_attr_rmtval_set(args);
if (error)
return error;
}
/*
* If this is an atomic rename operation, we must "flip" the
* incomplete flags on the "new" and "old" attribute/value pairs
* so that one disappears and one appears atomically. Then we
* must remove the "old" attribute/value pair.
*/
if (args->op_flags & XFS_DA_OP_RENAME) {
/*
* In a separate transaction, set the incomplete flag on the
* "old" attr and clear the incomplete flag on the "new" attr.
*/
error = xfs_attr3_leaf_flipflags(args);
if (error)
goto out;
/*
* Dismantle the "old" attribute/value pair by removing
* a "remote" value (if it exists).
*/
args->index = args->index2;
args->blkno = args->blkno2;
args->rmtblkno = args->rmtblkno2;
args->rmtblkcnt = args->rmtblkcnt2;
args->rmtvaluelen = args->rmtvaluelen2;
if (args->rmtblkno) {
error = xfs_attr_rmtval_remove(args);
if (error)
return error;
}
/*
* Re-find the "old" attribute entry after any split ops.
* The INCOMPLETE flag means that we will find the "old"
* attr, not the "new" one.
*/
args->flags |= XFS_ATTR_INCOMPLETE;
state = xfs_da_state_alloc();
state->args = args;
state->mp = mp;
state->inleaf = 0;
error = xfs_da3_node_lookup_int(state, &retval);
if (error)
goto out;
/*
* Remove the name and update the hashvals in the tree.
*/
blk = &state->path.blk[ state->path.active-1 ];
ASSERT(blk->magic == XFS_ATTR_LEAF_MAGIC);
error = xfs_attr3_leaf_remove(blk->bp, args);
xfs_da3_fixhashpath(state, &state->path);
/*
* Check to see if the tree needs to be collapsed.
*/
if (retval && (state->path.active > 1)) {
xfs_bmap_init(args->flist, args->firstblock);
error = xfs_da3_join(state);
if (!error) {
error = xfs_bmap_finish(&args->trans,
args->flist,
&committed);
}
if (error) {
ASSERT(committed);
args->trans = NULL;
xfs_bmap_cancel(args->flist);
goto out;
}
/*
* bmap_finish() may have committed the last trans
* and started a new one. We need the inode to be
* in all transactions.
*/
if (committed)
xfs_trans_ijoin(args->trans, dp, 0);
}
/*
* Commit and start the next trans in the chain.
*/
error = xfs_trans_roll(&args->trans, dp);
if (error)
goto out;
} else if (args->rmtblkno > 0) {
/*
* Added a "remote" value, just clear the incomplete flag.
*/
error = xfs_attr3_leaf_clearflag(args);
if (error)
goto out;
}
retval = error = 0;
out:
if (state)
xfs_da_state_free(state);
if (error)
return error;
return retval;
}
/*
* Handle logging requirements of various synchronous types of write.
*/
int
xfs_write_sync_logforce(
xfs_mount_t *mp,
xfs_inode_t *ip)
{
int error = 0;
/*
* 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) &&
!(ip->i_update_size)) {
xfs_inode_log_item_t *iip = ip->i_itemp;
/*
* 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.
*/
if (iip && iip->ili_last_lsn) {
xfs_log_force(mp, iip->ili_last_lsn,
XFS_LOG_FORCE | XFS_LOG_SYNC);
} else if (xfs_ipincount(ip) > 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(ip, XFS_ILOCK_EXCL);
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, NULL);
xfs_iunlock(ip, XFS_ILOCK_EXCL);
}
}
return error;
}
int
xfs_attr_set(
struct xfs_inode *dp,
const unsigned char *name,
unsigned char *value,
int valuelen,
int flags)
{
struct xfs_mount *mp = dp->i_mount;
struct xfs_buf *leaf_bp = NULL;
struct xfs_da_args args;
struct xfs_trans_res tres;
int rsvd = (flags & ATTR_ROOT) != 0;
int error, err2, local;
XFS_STATS_INC(mp, xs_attr_set);
if (XFS_FORCED_SHUTDOWN(dp->i_mount))
return -EIO;
error = xfs_attr_args_init(&args, dp, name, flags);
if (error)
return error;
args.value = value;
args.valuelen = valuelen;
args.op_flags = XFS_DA_OP_ADDNAME | XFS_DA_OP_OKNOENT;
args.total = xfs_attr_calc_size(&args, &local);
error = xfs_qm_dqattach(dp);
if (error)
return error;
/*
* If the inode doesn't have an attribute fork, add one.
* (inode must not be locked when we call this routine)
*/
if (XFS_IFORK_Q(dp) == 0) {
int sf_size = sizeof(xfs_attr_sf_hdr_t) +
XFS_ATTR_SF_ENTSIZE_BYNAME(args.namelen, valuelen);
error = xfs_bmap_add_attrfork(dp, sf_size, rsvd);
if (error)
return error;
}
tres.tr_logres = M_RES(mp)->tr_attrsetm.tr_logres +
M_RES(mp)->tr_attrsetrt.tr_logres * args.total;
tres.tr_logcount = XFS_ATTRSET_LOG_COUNT;
tres.tr_logflags = XFS_TRANS_PERM_LOG_RES;
/*
* Root fork attributes can use reserved data blocks for this
* operation if necessary
*/
error = xfs_trans_alloc(mp, &tres, args.total, 0,
rsvd ? XFS_TRANS_RESERVE : 0, &args.trans);
if (error)
return error;
xfs_ilock(dp, XFS_ILOCK_EXCL);
error = xfs_trans_reserve_quota_nblks(args.trans, dp, args.total, 0,
rsvd ? XFS_QMOPT_RES_REGBLKS | XFS_QMOPT_FORCE_RES :
XFS_QMOPT_RES_REGBLKS);
if (error) {
xfs_iunlock(dp, XFS_ILOCK_EXCL);
xfs_trans_cancel(args.trans);
return error;
}
xfs_trans_ijoin(args.trans, dp, 0);
/*
* If the attribute list is non-existent or a shortform list,
* upgrade it to a single-leaf-block attribute list.
*/
if (dp->i_d.di_aformat == XFS_DINODE_FMT_LOCAL ||
(dp->i_d.di_aformat == XFS_DINODE_FMT_EXTENTS &&
dp->i_d.di_anextents == 0)) {
/*
* Build initial attribute list (if required).
*/
if (dp->i_d.di_aformat == XFS_DINODE_FMT_EXTENTS)
xfs_attr_shortform_create(&args);
/*
* Try to add the attr to the attribute list in
* the inode.
*/
error = xfs_attr_shortform_addname(&args);
if (error != -ENOSPC) {
/*
* Commit the shortform mods, and we're done.
* NOTE: this is also the error path (EEXIST, etc).
*/
ASSERT(args.trans != NULL);
/*
* If this is a synchronous mount, make sure that
* the transaction goes to disk before returning
* to the user.
*/
if (mp->m_flags & XFS_MOUNT_WSYNC)
xfs_trans_set_sync(args.trans);
if (!error && (flags & ATTR_KERNOTIME) == 0) {
xfs_trans_ichgtime(args.trans, dp,
XFS_ICHGTIME_CHG);
}
err2 = xfs_trans_commit(args.trans);
xfs_iunlock(dp, XFS_ILOCK_EXCL);
return error ? error : err2;
}
/*
* It won't fit in the shortform, transform to a leaf block.
* GROT: another possible req'mt for a double-split btree op.
*/
error = xfs_attr_shortform_to_leaf(&args, &leaf_bp);
if (error)
goto out;
/*
* Prevent the leaf buffer from being unlocked so that a
* concurrent AIL push cannot grab the half-baked leaf
* buffer and run into problems with the write verifier.
*/
xfs_trans_bhold(args.trans, leaf_bp);
error = xfs_defer_finish(&args.trans);
if (error)
goto out;
/*
* Commit the leaf transformation. We'll need another (linked)
* transaction to add the new attribute to the leaf, which
* means that we have to hold & join the leaf buffer here too.
*/
error = xfs_trans_roll_inode(&args.trans, dp);
if (error)
goto out;
xfs_trans_bjoin(args.trans, leaf_bp);
leaf_bp = NULL;
}
if (xfs_bmap_one_block(dp, XFS_ATTR_FORK))
error = xfs_attr_leaf_addname(&args);
else
error = xfs_attr_node_addname(&args);
if (error)
goto out;
/*
* If this is a synchronous mount, make sure that the
* transaction goes to disk before returning to the user.
*/
if (mp->m_flags & XFS_MOUNT_WSYNC)
xfs_trans_set_sync(args.trans);
if ((flags & ATTR_KERNOTIME) == 0)
xfs_trans_ichgtime(args.trans, dp, XFS_ICHGTIME_CHG);
/*
* Commit the last in the sequence of transactions.
*/
xfs_trans_log_inode(args.trans, dp, XFS_ILOG_CORE);
error = xfs_trans_commit(args.trans);
xfs_iunlock(dp, XFS_ILOCK_EXCL);
return error;
out:
if (leaf_bp)
xfs_trans_brelse(args.trans, leaf_bp);
if (args.trans)
xfs_trans_cancel(args.trans);
xfs_iunlock(dp, XFS_ILOCK_EXCL);
return error;
}