/*
* Ensure the reflink bit is set in both inodes.
*/
STATIC int
xfs_reflink_set_inode_flag(
struct xfs_inode *src,
struct xfs_inode *dest)
{
struct xfs_mount *mp = src->i_mount;
int error;
struct xfs_trans *tp;
if (xfs_is_reflink_inode(src) && xfs_is_reflink_inode(dest))
return 0;
error = xfs_trans_alloc(mp, &M_RES(mp)->tr_ichange, 0, 0, 0, &tp);
if (error)
goto out_error;
/* Lock both files against IO */
if (src->i_ino == dest->i_ino)
xfs_ilock(src, XFS_ILOCK_EXCL);
else
xfs_lock_two_inodes(src, dest, XFS_ILOCK_EXCL);
if (!xfs_is_reflink_inode(src)) {
trace_xfs_reflink_set_inode_flag(src);
xfs_trans_ijoin(tp, src, XFS_ILOCK_EXCL);
src->i_d.di_flags2 |= XFS_DIFLAG2_REFLINK;
xfs_trans_log_inode(tp, src, XFS_ILOG_CORE);
xfs_ifork_init_cow(src);
} else
xfs_iunlock(src, XFS_ILOCK_EXCL);
if (src->i_ino == dest->i_ino)
goto commit_flags;
if (!xfs_is_reflink_inode(dest)) {
trace_xfs_reflink_set_inode_flag(dest);
xfs_trans_ijoin(tp, dest, XFS_ILOCK_EXCL);
dest->i_d.di_flags2 |= XFS_DIFLAG2_REFLINK;
xfs_trans_log_inode(tp, dest, XFS_ILOG_CORE);
xfs_ifork_init_cow(dest);
} else
xfs_iunlock(dest, XFS_ILOCK_EXCL);
commit_flags:
error = xfs_trans_commit(tp);
if (error)
goto out_error;
return error;
out_error:
trace_xfs_reflink_set_inode_flag_error(dest, error, _RET_IP_);
return error;
}
int /* */
xfs_dir2_sf_create(
xfs_da_args_t *args, /* */
xfs_ino_t pino) /* */
{
xfs_inode_t *dp; /* */
int i8count; /* */
xfs_dir2_sf_hdr_t *sfp; /* */
int size; /* */
trace_xfs_dir2_sf_create(args);
dp = args->dp;
ASSERT(dp != NULL);
ASSERT(dp->i_d.di_size == 0);
/*
*/
if (dp->i_d.di_format == XFS_DINODE_FMT_EXTENTS) {
dp->i_df.if_flags &= ~XFS_IFEXTENTS; /* */
dp->i_d.di_format = XFS_DINODE_FMT_LOCAL;
xfs_trans_log_inode(args->trans, dp, XFS_ILOG_CORE);
dp->i_df.if_flags |= XFS_IFINLINE;
}
ASSERT(dp->i_df.if_flags & XFS_IFINLINE);
ASSERT(dp->i_df.if_bytes == 0);
i8count = pino > XFS_DIR2_MAX_SHORT_INUM;
size = xfs_dir2_sf_hdr_size(i8count);
/*
*/
xfs_idata_realloc(dp, size, XFS_DATA_FORK);
/*
*/
sfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data;
sfp->i8count = i8count;
/*
*/
xfs_dir2_sf_put_parent_ino(sfp, pino);
sfp->count = 0;
dp->i_d.di_size = size;
xfs_dir2_sf_check(args);
xfs_trans_log_inode(args->trans, dp, XFS_ILOG_CORE | XFS_ILOG_DDATA);
return 0;
}
/*
* Create a new (shortform) directory.
*/
int /* error, always 0 */
xfs_dir2_sf_create(
xfs_da_args_t *args, /* operation arguments */
xfs_ino_t pino) /* parent inode number */
{
xfs_inode_t *dp; /* incore directory inode */
int i8count; /* parent inode is an 8-byte number */
xfs_dir2_sf_hdr_t *sfp; /* shortform structure */
int size; /* directory size */
trace_xfs_dir2_sf_create(args);
dp = args->dp;
ASSERT(dp != NULL);
ASSERT(dp->i_d.di_size == 0);
/*
* If it's currently a zero-length extent file,
* convert it to local format.
*/
if (dp->i_d.di_format == XFS_DINODE_FMT_EXTENTS) {
dp->i_df.if_flags &= ~XFS_IFEXTENTS; /* just in case */
dp->i_d.di_format = XFS_DINODE_FMT_LOCAL;
xfs_trans_log_inode(args->trans, dp, XFS_ILOG_CORE);
dp->i_df.if_flags |= XFS_IFINLINE;
}
ASSERT(dp->i_df.if_flags & XFS_IFINLINE);
ASSERT(dp->i_df.if_bytes == 0);
i8count = pino > XFS_DIR2_MAX_SHORT_INUM;
size = xfs_dir2_sf_hdr_size(i8count);
/*
* Make a buffer for the data.
*/
xfs_idata_realloc(dp, size, XFS_DATA_FORK);
/*
* Fill in the header,
*/
sfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data;
sfp->i8count = i8count;
/*
* Now can put in the inode number, since i8count is set.
*/
xfs_dir2_sf_put_parent_ino(sfp, pino);
sfp->count = 0;
dp->i_d.di_size = size;
xfs_dir2_sf_check(args);
xfs_trans_log_inode(args->trans, dp, XFS_ILOG_CORE | XFS_ILOG_DDATA);
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;
/*
* 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, (flags & SYNC_WAIT) ? XFS_LOG_SYNC : 0);
return error;
}
/*
* Update on-disk file size now that data has been written to disk.
*/
STATIC int
xfs_setfilesize(
struct xfs_ioend *ioend)
{
struct xfs_inode *ip = XFS_I(ioend->io_inode);
struct xfs_trans *tp = ioend->io_append_trans;
xfs_fsize_t isize;
/*
* The transaction was allocated in the I/O submission thread,
* thus we need to mark ourselves as beeing in a transaction
* manually.
*/
current_set_flags_nested(&tp->t_pflags, PF_FSTRANS);
xfs_ilock(ip, XFS_ILOCK_EXCL);
isize = xfs_new_eof(ip, ioend->io_offset + ioend->io_size);
if (!isize) {
xfs_iunlock(ip, XFS_ILOCK_EXCL);
xfs_trans_cancel(tp, 0);
return 0;
}
trace_xfs_setfilesize(ip, ioend->io_offset, ioend->io_size);
ip->i_d.di_size = isize;
xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
return xfs_trans_commit(tp, 0);
}
int
xfs_log_dirty_inode(
struct xfs_inode *ip,
struct xfs_perag *pag,
int flags)
{
struct xfs_mount *mp = ip->i_mount;
struct xfs_trans *tp;
int error;
if (!ip->i_update_core)
return 0;
tp = xfs_trans_alloc(mp, XFS_TRANS_FSYNC_TS);
error = xfs_trans_reserve(tp, 0, XFS_FSYNC_TS_LOG_RES(mp), 0, 0, 0);
if (error) {
xfs_trans_cancel(tp, 0);
return error;
}
xfs_ilock(ip, XFS_ILOCK_EXCL);
xfs_trans_ijoin_ref(tp, ip, XFS_ILOCK_EXCL);
xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
return xfs_trans_commit(tp, 0);
}
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);
error = xfs_trans_alloc(mp, &M_RES(mp)->tr_fsyncts, 0, 0, 0, &tp);
if (error)
return error;
xfs_ilock(ip, XFS_ILOCK_EXCL);
if (flags & S_CTIME)
inode->i_ctime = *now;
if (flags & S_MTIME)
inode->i_mtime = *now;
if (flags & S_ATIME)
inode->i_atime = *now;
xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
xfs_trans_log_inode(tp, ip, XFS_ILOG_TIMESTAMP);
return xfs_trans_commit(tp);
}
/*
* Increment the link count on an inode & log the change.
*/
int
xfs_bumplink(
xfs_trans_t *tp,
xfs_inode_t *ip)
{
if (ip->i_d.di_nlink >= XFS_MAXLINK)
return XFS_ERROR(EMLINK);
xfs_trans_ichgtime(tp, ip, XFS_ICHGTIME_CHG);
ASSERT(ip->i_d.di_nlink > 0);
ip->i_d.di_nlink++;
inc_nlink(VFS_I(ip));
if ((ip->i_d.di_version == 1) &&
(ip->i_d.di_nlink > XFS_MAXLINK_1)) {
/*
* The inode has increased its number of links beyond
* what can fit in an old format inode. It now needs
* to be converted to a version 2 inode with a 32 bit
* link count. If this is the first inode in the file
* system to do this, then we need to bump the superblock
* version number as well.
*/
xfs_bump_ino_vers2(tp, ip);
}
xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
return 0;
}
/* Clear the inode reflink flag if there are no shared extents. */
int
xfs_reflink_clear_inode_flag(
struct xfs_inode *ip,
struct xfs_trans **tpp)
{
bool needs_flag;
int error = 0;
ASSERT(xfs_is_reflink_inode(ip));
error = xfs_reflink_inode_has_shared_extents(*tpp, ip, &needs_flag);
if (error || needs_flag)
return error;
/*
* We didn't find any shared blocks so turn off the reflink flag.
* First, get rid of any leftover CoW mappings.
*/
error = xfs_reflink_cancel_cow_blocks(ip, tpp, 0, NULLFILEOFF, true);
if (error)
return error;
/* Clear the inode flag. */
trace_xfs_reflink_unset_inode_flag(ip);
ip->i_d.di_flags2 &= ~XFS_DIFLAG2_REFLINK;
xfs_inode_clear_cowblocks_tag(ip);
xfs_trans_ijoin(*tpp, ip, 0);
xfs_trans_log_inode(*tpp, ip, XFS_ILOG_CORE);
return error;
}
/*
* Update on-disk file size now that data has been written to disk.
*/
STATIC int
xfs_setfilesize(
struct xfs_inode *ip,
struct xfs_trans *tp,
xfs_off_t offset,
size_t size)
{
xfs_fsize_t isize;
xfs_ilock(ip, XFS_ILOCK_EXCL);
isize = xfs_new_eof(ip, offset + size);
if (!isize) {
xfs_iunlock(ip, XFS_ILOCK_EXCL);
xfs_trans_cancel(tp);
return 0;
}
trace_xfs_setfilesize(ip, offset, size);
ip->i_d.di_size = isize;
xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
return xfs_trans_commit(tp);
}
/*
* Update on-disk file size now that data has been written to disk.
*/
STATIC int
xfs_setfilesize(
struct xfs_ioend *ioend)
{
struct xfs_inode *ip = XFS_I(ioend->io_inode);
struct xfs_trans *tp = ioend->io_append_trans;
xfs_fsize_t isize;
/*
* The transaction may have been allocated in the I/O submission thread,
* thus we need to mark ourselves as beeing in a transaction manually.
* Similarly for freeze protection.
*/
current_set_flags_nested(&tp->t_pflags, PF_FSTRANS);
rwsem_acquire_read(&VFS_I(ip)->i_sb->s_writers.lock_map[SB_FREEZE_FS-1],
0, 1, _THIS_IP_);
xfs_ilock(ip, XFS_ILOCK_EXCL);
isize = xfs_new_eof(ip, ioend->io_offset + ioend->io_size);
if (!isize) {
xfs_iunlock(ip, XFS_ILOCK_EXCL);
xfs_trans_cancel(tp, 0);
return 0;
}
trace_xfs_setfilesize(ip, ioend->io_offset, ioend->io_size);
ip->i_d.di_size = isize;
xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
return xfs_trans_commit(tp, 0);
}
STATIC int
xfs_commit_dummy_trans(
struct xfs_mount *mp,
uint log_flags)
{
struct xfs_inode *ip = mp->m_rootip;
struct xfs_trans *tp;
int error;
/*
* 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);
/* XXX(hch): ignoring the error here.. */
error = xfs_trans_commit(tp, 0);
xfs_iunlock(ip, XFS_ILOCK_EXCL);
xfs_log_force(mp, 0, log_flags);
return 0;
}
/*
* Update on-disk file size now that data has been written to disk.
*/
STATIC int
xfs_setfilesize(
struct xfs_ioend *ioend)
{
struct xfs_inode *ip = XFS_I(ioend->io_inode);
struct xfs_trans *tp = ioend->io_append_trans;
xfs_fsize_t isize;
current_set_flags_nested(&tp->t_pflags, PF_FSTRANS);
xfs_ilock(ip, XFS_ILOCK_EXCL);
isize = xfs_new_eof(ip, ioend->io_offset + ioend->io_size);
if (!isize) {
xfs_iunlock(ip, XFS_ILOCK_EXCL);
xfs_trans_cancel(tp, 0);
return 0;
}
trace_xfs_setfilesize(ip, ioend->io_offset, ioend->io_size);
ip->i_d.di_size = isize;
xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
return xfs_trans_commit(tp, 0);
}
int
xfs_update_prealloc_flags(
struct xfs_inode *ip,
enum xfs_prealloc_flags flags)
{
struct xfs_trans *tp;
int error;
error = xfs_trans_alloc(ip->i_mount, &M_RES(ip->i_mount)->tr_writeid,
0, 0, 0, &tp);
if (error)
return error;
xfs_ilock(ip, XFS_ILOCK_EXCL);
xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
if (!(flags & XFS_PREALLOC_INVISIBLE)) {
VFS_I(ip)->i_mode &= ~S_ISUID;
if (VFS_I(ip)->i_mode & S_IXGRP)
VFS_I(ip)->i_mode &= ~S_ISGID;
xfs_trans_ichgtime(tp, ip, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
}
if (flags & XFS_PREALLOC_SET)
ip->i_d.di_flags |= XFS_DIFLAG_PREALLOC;
if (flags & XFS_PREALLOC_CLEAR)
ip->i_d.di_flags &= ~XFS_DIFLAG_PREALLOC;
xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
if (flags & XFS_PREALLOC_SYNC)
xfs_trans_set_sync(tp);
return xfs_trans_commit(tp);
}
int
xfs_set_dmattrs(
xfs_inode_t *ip,
u_int evmask,
u_int16_t state)
{
xfs_mount_t *mp = ip->i_mount;
xfs_trans_t *tp;
int error;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
if (XFS_FORCED_SHUTDOWN(mp))
return -EIO;
tp = xfs_trans_alloc(mp, XFS_TRANS_SET_DMATTRS);
error = xfs_trans_reserve(tp, &M_RES(mp)->tr_ichange, 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);
ip->i_d.di_dmevmask = evmask;
ip->i_d.di_dmstate = state;
xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
error = xfs_trans_commit(tp, 0);
return error;
}
/*
* Decrement the link count on an inode & log the change.
* If this causes the link count to go to zero, initiate the
* logging activity required to truncate a file.
*/
int /* error */
xfs_droplink(
xfs_trans_t *tp,
xfs_inode_t *ip)
{
int error;
xfs_trans_ichgtime(tp, ip, XFS_ICHGTIME_CHG);
ASSERT (ip->i_d.di_nlink > 0);
ip->i_d.di_nlink--;
drop_nlink(VFS_I(ip));
xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
error = 0;
if (ip->i_d.di_nlink == 0) {
/*
* We're dropping the last link to this file.
* Move the on-disk inode to the AGI unlinked list.
* From xfs_inactive() we will pull the inode from
* the list and free it.
*/
error = xfs_iunlink(tp, ip);
}
return error;
}
/*
* Roll from one trans in the sequence of PERMANENT transactions to
* the next: permanent transactions are only flushed out when
* committed with XFS_TRANS_RELEASE_LOG_RES, but we still want as soon
* as possible to let chunks of it go to the log. So we commit the
* chunk we've been working on and get a new transaction to continue.
*/
int
libxfs_trans_roll(
struct xfs_trans **tpp,
struct xfs_inode *dp)
{
struct xfs_mount *mp;
struct xfs_trans *trans;
struct xfs_trans_res tres;
int error;
/*
* Ensure that the inode is always logged.
*/
trans = *tpp;
if (dp)
xfs_trans_log_inode(trans, dp, XFS_ILOG_CORE);
/*
* Copy the critical parameters from one trans to the next.
*/
mp = trans->t_mountp;
tres.tr_logres = trans->t_log_res;
tres.tr_logcount = trans->t_log_count;
/*
* Commit the current transaction.
* If this commit failed, then it'd just unlock those items that
* are marked to be released. That also means that a filesystem shutdown
* is in progress. The caller takes the responsibility to cancel
* the duplicate transaction that gets returned.
*/
error = xfs_trans_commit(trans);
if (error)
return error;
/*
* Reserve space in the log for th next transaction.
* This also pushes items in the "AIL", the list of logged items,
* out to disk if they are taking up space at the tail of the log
* that we want to use. This requires that either nothing be locked
* across this call, or that anything that is locked be logged in
* the prior and the next transactions.
*/
tres.tr_logflags = XFS_TRANS_PERM_LOG_RES;
error = libxfs_trans_alloc(mp, &tres, 0, 0, 0, tpp);
trans = *tpp;
/*
* Ensure that the inode is in the new transaction and locked.
*/
if (error)
return error;
if (dp)
xfs_trans_ijoin(trans, dp, 0);
return 0;
}
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, 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;
}
int
xfs_trans_roll_inode(
struct xfs_trans **tpp,
struct xfs_inode *ip)
{
int error;
xfs_trans_log_inode(*tpp, ip, XFS_ILOG_CORE);
error = xfs_trans_roll(tpp);
if (!error)
xfs_trans_ijoin(*tpp, ip, 0);
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;
}
static int
xfs_ioctl_setattr_xflags(
struct xfs_trans *tp,
struct xfs_inode *ip,
struct fsxattr *fa)
{
struct xfs_mount *mp = ip->i_mount;
/* 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 & FS_XFLAG_REALTIME))
return -EINVAL;
/* If realtime flag is set then must have realtime device */
if (fa->fsx_xflags & FS_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))
return -EINVAL;
}
/* Clear reflink if we are actually able to set the rt flag. */
if ((fa->fsx_xflags & FS_XFLAG_REALTIME) && xfs_is_reflink_inode(ip))
ip->i_d.di_flags2 &= ~XFS_DIFLAG2_REFLINK;
/* Don't allow us to set DAX mode for a reflinked file for now. */
if ((fa->fsx_xflags & FS_XFLAG_DAX) && xfs_is_reflink_inode(ip))
return -EINVAL;
/*
* 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 & (FS_XFLAG_IMMUTABLE | FS_XFLAG_APPEND))) &&
!capable(CAP_LINUX_IMMUTABLE))
return -EPERM;
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(mp, xs_ig_attrchg);
return 0;
}
/*
* Add a block to the directory.
*
* This routine is for data and free blocks, not leaf/node blocks which are
* handled by xfs_da_grow_inode.
*/
int
xfs_dir2_grow_inode(
struct xfs_da_args *args,
int space, /* v2 dir's space XFS_DIR2_xxx_SPACE */
xfs_dir2_db_t *dbp) /* out: block number added */
{
struct xfs_inode *dp = args->dp;
struct xfs_mount *mp = dp->i_mount;
xfs_fileoff_t bno; /* directory offset of new block */
int count; /* count of filesystem blocks */
int error;
trace_xfs_dir2_grow_inode(args, space);
/*
* Set lowest possible block in the space requested.
*/
bno = XFS_B_TO_FSBT(mp, space * XFS_DIR2_SPACE_SIZE);
count = args->geo->fsbcount;
error = xfs_da_grow_inode_int(args, &bno, count);
if (error)
return error;
*dbp = xfs_dir2_da_to_db(args->geo, (xfs_dablk_t)bno);
/*
* Update file's size if this is the data space and it grew.
*/
if (space == XFS_DIR2_DATA_SPACE) {
xfs_fsize_t size; /* directory file (data) size */
size = XFS_FSB_TO_B(mp, bno + count);
if (size > dp->i_d.di_size) {
dp->i_d.di_size = size;
xfs_trans_log_inode(args->trans, dp, XFS_ILOG_CORE);
}
}
return 0;
}
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;
}
/*
* 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;
}
/*
* 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;
}
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;
}
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;
}
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;
}
