/*
* xfs_file_dio_aio_write - handle direct IO writes
*
* Lock the inode appropriately to prepare for and issue a direct IO write.
* By separating it from the buffered write path we remove all the tricky to
* follow locking changes and looping.
*
* If there are cached pages or we're extending the file, we need IOLOCK_EXCL
* until we're sure the bytes at the new EOF have been zeroed and/or the cached
* pages are flushed out.
*
* In most cases the direct IO writes will be done holding IOLOCK_SHARED
* allowing them to be done in parallel with reads and other direct IO writes.
* However, if the IO is not aligned to filesystem blocks, the direct IO layer
* needs to do sub-block zeroing and that requires serialisation against other
* direct IOs to the same block. In this case we need to serialise the
* submission of the unaligned IOs so that we don't get racing block zeroing in
* the dio layer. To avoid the problem with aio, we also need to wait for
* outstanding IOs to complete so that unwritten extent conversion is completed
* before we try to map the overlapping block. This is currently implemented by
* hitting it with a big hammer (i.e. inode_dio_wait()).
*
* Returns with locks held indicated by @iolock and errors indicated by
* negative return values.
*/
STATIC ssize_t
xfs_file_dio_aio_write(
struct kiocb *iocb,
struct iov_iter *from)
{
struct file *file = iocb->ki_filp;
struct address_space *mapping = file->f_mapping;
struct inode *inode = mapping->host;
struct xfs_inode *ip = XFS_I(inode);
struct xfs_mount *mp = ip->i_mount;
ssize_t ret = 0;
int unaligned_io = 0;
int iolock;
size_t count = iov_iter_count(from);
loff_t end;
struct iov_iter data;
struct xfs_buftarg *target = XFS_IS_REALTIME_INODE(ip) ?
mp->m_rtdev_targp : mp->m_ddev_targp;
/* DIO must be aligned to device logical sector size */
if (!IS_DAX(inode) &&
((iocb->ki_pos | count) & target->bt_logical_sectormask))
return -EINVAL;
/* "unaligned" here means not aligned to a filesystem block */
if ((iocb->ki_pos & mp->m_blockmask) ||
((iocb->ki_pos + count) & mp->m_blockmask))
unaligned_io = 1;
/*
* We don't need to take an exclusive lock unless there page cache needs
* to be invalidated or unaligned IO is being executed. We don't need to
* consider the EOF extension case here because
* xfs_file_aio_write_checks() will relock the inode as necessary for
* EOF zeroing cases and fill out the new inode size as appropriate.
*/
if (unaligned_io || mapping->nrpages)
iolock = XFS_IOLOCK_EXCL;
else
iolock = XFS_IOLOCK_SHARED;
xfs_rw_ilock(ip, iolock);
/*
* Recheck if there are cached pages that need invalidate after we got
* the iolock to protect against other threads adding new pages while
* we were waiting for the iolock.
*/
if (mapping->nrpages && iolock == XFS_IOLOCK_SHARED) {
xfs_rw_iunlock(ip, iolock);
iolock = XFS_IOLOCK_EXCL;
xfs_rw_ilock(ip, iolock);
}
ret = xfs_file_aio_write_checks(iocb, from, &iolock);
if (ret)
goto out;
count = iov_iter_count(from);
end = iocb->ki_pos + count - 1;
/*
* See xfs_file_read_iter() for why we do a full-file flush here.
*/
if (mapping->nrpages) {
ret = filemap_write_and_wait(VFS_I(ip)->i_mapping);
if (ret)
goto out;
/*
* Invalidate whole pages. This can return an error if we fail
* to invalidate a page, but this should never happen on XFS.
* Warn if it does fail.
*/
ret = invalidate_inode_pages2(VFS_I(ip)->i_mapping);
WARN_ON_ONCE(ret);
ret = 0;
}
/*
* If we are doing unaligned IO, wait for all other IO to drain,
* otherwise demote the lock if we had to flush cached pages
*/
if (unaligned_io)
inode_dio_wait(inode);
else if (iolock == XFS_IOLOCK_EXCL) {
xfs_rw_ilock_demote(ip, XFS_IOLOCK_EXCL);
iolock = XFS_IOLOCK_SHARED;
}
trace_xfs_file_direct_write(ip, count, iocb->ki_pos, 0);
data = *from;
ret = mapping->a_ops->direct_IO(iocb, &data);
/* see generic_file_direct_write() for why this is necessary */
if (mapping->nrpages) {
invalidate_inode_pages2_range(mapping,
iocb->ki_pos >> PAGE_SHIFT,
end >> PAGE_SHIFT);
}
static int
xfs_iget_cache_miss(
struct xfs_mount *mp,
struct xfs_perag *pag,
xfs_trans_t *tp,
xfs_ino_t ino,
struct xfs_inode **ipp,
int flags,
int lock_flags)
{
struct xfs_inode *ip;
int error;
xfs_agino_t agino = XFS_INO_TO_AGINO(mp, ino);
int iflags;
ip = xfs_inode_alloc(mp, ino);
if (!ip)
return -ENOMEM;
error = xfs_iread(mp, tp, ip, flags);
if (error)
goto out_destroy;
trace_xfs_iget_miss(ip);
if ((VFS_I(ip)->i_mode == 0) && !(flags & XFS_IGET_CREATE)) {
error = -ENOENT;
goto out_destroy;
}
/*
* Preload the radix tree so we can insert safely under the
* write spinlock. Note that we cannot sleep inside the preload
* region. Since we can be called from transaction context, don't
* recurse into the file system.
*/
if (radix_tree_preload(GFP_NOFS)) {
error = -EAGAIN;
goto out_destroy;
}
/*
* Because the inode hasn't been added to the radix-tree yet it can't
* be found by another thread, so we can do the non-sleeping lock here.
*/
if (lock_flags) {
if (!xfs_ilock_nowait(ip, lock_flags))
BUG();
}
/*
* These values must be set before inserting the inode into the radix
* tree as the moment it is inserted a concurrent lookup (allowed by the
* RCU locking mechanism) can find it and that lookup must see that this
* is an inode currently under construction (i.e. that XFS_INEW is set).
* The ip->i_flags_lock that protects the XFS_INEW flag forms the
* memory barrier that ensures this detection works correctly at lookup
* time.
*/
iflags = XFS_INEW;
if (flags & XFS_IGET_DONTCACHE)
iflags |= XFS_IDONTCACHE;
ip->i_udquot = NULL;
ip->i_gdquot = NULL;
ip->i_pdquot = NULL;
xfs_iflags_set(ip, iflags);
/* insert the new inode */
spin_lock(&pag->pag_ici_lock);
error = radix_tree_insert(&pag->pag_ici_root, agino, ip);
if (unlikely(error)) {
WARN_ON(error != -EEXIST);
XFS_STATS_INC(mp, xs_ig_dup);
error = -EAGAIN;
goto out_preload_end;
}
spin_unlock(&pag->pag_ici_lock);
radix_tree_preload_end();
*ipp = ip;
return 0;
out_preload_end:
spin_unlock(&pag->pag_ici_lock);
radix_tree_preload_end();
if (lock_flags)
xfs_iunlock(ip, lock_flags);
out_destroy:
__destroy_inode(VFS_I(ip));
xfs_inode_free(ip);
return error;
}
STATIC ssize_t
xfs_file_aio_read(
struct kiocb *iocb,
const struct iovec *iovp,
unsigned long nr_segs,
loff_t pos)
{
struct file *file = iocb->ki_filp;
struct inode *inode = file->f_mapping->host;
struct xfs_inode *ip = XFS_I(inode);
struct xfs_mount *mp = ip->i_mount;
size_t size = 0;
ssize_t ret = 0;
int ioflags = 0;
xfs_fsize_t n;
XFS_STATS_INC(xs_read_calls);
BUG_ON(iocb->ki_pos != pos);
if (unlikely(file->f_flags & O_DIRECT))
ioflags |= IO_ISDIRECT;
if (file->f_mode & FMODE_NOCMTIME)
ioflags |= IO_INVIS;
ret = generic_segment_checks(iovp, &nr_segs, &size, VERIFY_WRITE);
if (ret < 0)
return ret;
if (unlikely(ioflags & IO_ISDIRECT)) {
xfs_buftarg_t *target =
XFS_IS_REALTIME_INODE(ip) ?
mp->m_rtdev_targp : mp->m_ddev_targp;
/* DIO must be aligned to device logical sector size */
if ((pos | size) & target->bt_logical_sectormask) {
if (pos == i_size_read(inode))
return 0;
return -XFS_ERROR(EINVAL);
}
}
n = mp->m_super->s_maxbytes - pos;
if (n <= 0 || size == 0)
return 0;
if (n < size)
size = n;
if (XFS_FORCED_SHUTDOWN(mp))
return -EIO;
/*
* Locking is a bit tricky here. If we take an exclusive lock
* for direct IO, we effectively serialise all new concurrent
* read IO to this file and block it behind IO that is currently in
* progress because IO in progress holds the IO lock shared. We only
* need to hold the lock exclusive to blow away the page cache, so
* only take lock exclusively if the page cache needs invalidation.
* This allows the normal direct IO case of no page cache pages to
* proceeed concurrently without serialisation.
*/
xfs_rw_ilock(ip, XFS_IOLOCK_SHARED);
if ((ioflags & IO_ISDIRECT) && inode->i_mapping->nrpages) {
xfs_rw_iunlock(ip, XFS_IOLOCK_SHARED);
xfs_rw_ilock(ip, XFS_IOLOCK_EXCL);
if (inode->i_mapping->nrpages) {
ret = filemap_write_and_wait_range(
VFS_I(ip)->i_mapping,
pos, pos + size - 1);
if (ret) {
xfs_rw_iunlock(ip, XFS_IOLOCK_EXCL);
return ret;
}
/*
* Invalidate whole pages. This can return an error if
* we fail to invalidate a page, but this should never
* happen on XFS. Warn if it does fail.
*/
ret = invalidate_inode_pages2_range(VFS_I(ip)->i_mapping,
pos >> PAGE_CACHE_SHIFT,
(pos + size - 1) >> PAGE_CACHE_SHIFT);
WARN_ON_ONCE(ret);
ret = 0;
}
int
xfs_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;
uid_t uid = 0, iuid = 0;
gid_t gid = 0, igid = 0;
struct xfs_dquot *udqp = NULL, *gdqp = NULL;
struct xfs_dquot *olddquot1 = NULL, *olddquot2 = NULL;
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((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 = ip->i_d.di_uid;
}
if ((mask & ATTR_GID) && XFS_IS_GQUOTA_ON(mp)) {
gid = iattr->ia_gid;
qflags |= XFS_QMOPT_GQUOTA;
} else {
gid = ip->i_d.di_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, uid, gid, xfs_get_projid(ip),
qflags, &udqp, &gdqp);
if (error)
return error;
}
tp = xfs_trans_alloc(mp, XFS_TRANS_SETATTR_NOT_SIZE);
error = xfs_trans_reserve(tp, 0, XFS_ICHANGE_LOG_RES(mp), 0, 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 = ip->i_d.di_uid;
igid = ip->i_d.di_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) && iuid != uid) ||
(XFS_IS_GQUOTA_ON(mp) && igid != gid))) {
ASSERT(tp);
error = xfs_qm_vop_chown_reserve(tp, ip, udqp, gdqp,
capable(CAP_FOWNER) ?
XFS_QMOPT_FORCE_RES : 0);
if (error) /* out of quota */
goto out_trans_cancel;
}
}
xfs_trans_ijoin(tp, ip);
/*
* 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 (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 = uid;
inode->i_uid = uid;
}
if (igid != gid) {
if (XFS_IS_QUOTA_RUNNING(mp) && XFS_IS_GQUOTA_ON(mp)) {
ASSERT(!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 = gid;
inode->i_gid = gid;
}
}
/*
* Change file access modes.
*/
if (mask & ATTR_MODE) {
umode_t mode = iattr->ia_mode;
if (!in_group_p(inode->i_gid) && !capable(CAP_FSETID))
mode &= ~S_ISGID;
ip->i_d.di_mode &= S_IFMT;
ip->i_d.di_mode |= mode & ~S_IFMT;
inode->i_mode &= S_IFMT;
inode->i_mode |= mode & ~S_IFMT;
}
/*
* Change file access or modified times.
*/
if (mask & ATTR_ATIME) {
inode->i_atime = iattr->ia_atime;
ip->i_d.di_atime.t_sec = iattr->ia_atime.tv_sec;
ip->i_d.di_atime.t_nsec = iattr->ia_atime.tv_nsec;
ip->i_update_core = 1;
}
if (mask & ATTR_CTIME) {
inode->i_ctime = iattr->ia_ctime;
ip->i_d.di_ctime.t_sec = iattr->ia_ctime.tv_sec;
ip->i_d.di_ctime.t_nsec = iattr->ia_ctime.tv_nsec;
ip->i_update_core = 1;
}
if (mask & ATTR_MTIME) {
inode->i_mtime = iattr->ia_mtime;
ip->i_d.di_mtime.t_sec = iattr->ia_mtime.tv_sec;
ip->i_d.di_mtime.t_nsec = iattr->ia_mtime.tv_nsec;
ip->i_update_core = 1;
}
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 = -xfs_acl_chmod(inode);
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;
}
/*
* Allocate an inode on disk and return a copy of its in-core version.
* Set mode, nlink, and rdev appropriately within the inode.
* The uid and gid for the inode are set according to the contents of
* the given cred structure.
*
* This was once shared with the kernel, but has diverged to the point
* where it's no longer worth the hassle of maintaining common code.
*/
int
libxfs_ialloc(
xfs_trans_t *tp,
xfs_inode_t *pip,
mode_t mode,
nlink_t nlink,
xfs_dev_t rdev,
struct cred *cr,
struct fsxattr *fsx,
int okalloc,
xfs_buf_t **ialloc_context,
xfs_inode_t **ipp)
{
xfs_ino_t ino;
xfs_inode_t *ip;
uint flags;
int error;
/*
* Call the space management code to pick
* the on-disk inode to be allocated.
*/
error = xfs_dialloc(tp, pip ? pip->i_ino : 0, mode, okalloc,
ialloc_context, &ino);
if (error != 0)
return error;
if (*ialloc_context || ino == NULLFSINO) {
*ipp = NULL;
return 0;
}
ASSERT(*ialloc_context == NULL);
error = xfs_trans_iget(tp->t_mountp, tp, ino, 0, 0, &ip);
if (error != 0)
return error;
ASSERT(ip != NULL);
VFS_I(ip)->i_mode = mode;
set_nlink(VFS_I(ip), nlink);
ip->i_d.di_uid = cr->cr_uid;
ip->i_d.di_gid = cr->cr_gid;
xfs_set_projid(&ip->i_d, pip ? 0 : fsx->fsx_projid);
xfs_trans_ichgtime(tp, ip, XFS_ICHGTIME_CHG | XFS_ICHGTIME_MOD);
/*
* We only support filesystems that understand v2 format inodes. So if
* this is currently an old format inode, then change the inode version
* number now. This way we only do the conversion here rather than here
* and in the flush/logging code.
*/
if (ip->i_d.di_version == 1) {
ip->i_d.di_version = 2;
/*
* old link count, projid_lo/hi field, pad field
* already zeroed
*/
}
if (pip && (VFS_I(pip)->i_mode & S_ISGID)) {
ip->i_d.di_gid = pip->i_d.di_gid;
if ((VFS_I(pip)->i_mode & S_ISGID) && (mode & S_IFMT) == S_IFDIR)
VFS_I(ip)->i_mode |= S_ISGID;
}
ip->i_d.di_size = 0;
ip->i_d.di_nextents = 0;
ASSERT(ip->i_d.di_nblocks == 0);
ip->i_d.di_extsize = pip ? 0 : fsx->fsx_extsize;
ip->i_d.di_dmevmask = 0;
ip->i_d.di_dmstate = 0;
ip->i_d.di_flags = pip ? 0 : fsx->fsx_xflags;
if (ip->i_d.di_version == 3) {
ASSERT(ip->i_d.di_ino == ino);
ASSERT(uuid_equal(&ip->i_d.di_uuid, &mp->m_sb.sb_meta_uuid));
VFS_I(ip)->i_version = 1;
ip->i_d.di_flags2 = 0;
ip->i_d.di_crtime.t_sec = (__int32_t)VFS_I(ip)->i_mtime.tv_sec;
ip->i_d.di_crtime.t_nsec = (__int32_t)VFS_I(ip)->i_mtime.tv_nsec;
}
flags = XFS_ILOG_CORE;
switch (mode & S_IFMT) {
case S_IFIFO:
case S_IFSOCK:
/* doesn't make sense to set an rdev for these */
rdev = 0;
/* FALLTHROUGH */
case S_IFCHR:
case S_IFBLK:
ip->i_d.di_format = XFS_DINODE_FMT_DEV;
ip->i_df.if_u2.if_rdev = rdev;
flags |= XFS_ILOG_DEV;
break;
case S_IFREG:
case S_IFDIR:
if (pip && (pip->i_d.di_flags & XFS_DIFLAG_ANY)) {
uint di_flags = 0;
if ((mode & S_IFMT) == S_IFDIR) {
if (pip->i_d.di_flags & XFS_DIFLAG_RTINHERIT)
di_flags |= XFS_DIFLAG_RTINHERIT;
if (pip->i_d.di_flags & XFS_DIFLAG_EXTSZINHERIT) {
di_flags |= XFS_DIFLAG_EXTSZINHERIT;
ip->i_d.di_extsize = pip->i_d.di_extsize;
}
} else {
if (pip->i_d.di_flags & XFS_DIFLAG_RTINHERIT) {
di_flags |= XFS_DIFLAG_REALTIME;
}
if (pip->i_d.di_flags & XFS_DIFLAG_EXTSZINHERIT) {
di_flags |= XFS_DIFLAG_EXTSIZE;
ip->i_d.di_extsize = pip->i_d.di_extsize;
}
}
if (pip->i_d.di_flags & XFS_DIFLAG_PROJINHERIT)
di_flags |= XFS_DIFLAG_PROJINHERIT;
ip->i_d.di_flags |= di_flags;
}
/* FALLTHROUGH */
case S_IFLNK:
ip->i_d.di_format = XFS_DINODE_FMT_EXTENTS;
ip->i_df.if_flags = XFS_IFEXTENTS;
ip->i_df.if_bytes = ip->i_df.if_real_bytes = 0;
ip->i_df.if_u1.if_extents = NULL;
break;
default:
ASSERT(0);
}
/* Attribute fork settings for new inode. */
ip->i_d.di_aformat = XFS_DINODE_FMT_EXTENTS;
ip->i_d.di_anextents = 0;
/*
* set up the inode ops structure that the libxfs code relies on
*/
if (XFS_ISDIR(ip))
ip->d_ops = ip->i_mount->m_dir_inode_ops;
else
ip->d_ops = ip->i_mount->m_nondir_inode_ops;
/*
* Log the new values stuffed into the inode.
*/
xfs_trans_log_inode(tp, ip, flags);
*ipp = ip;
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)
{
struct xfs_mount *mp = ip->i_mount;
xfs_fileoff_t fbno;
xfs_filblks_t end;
xfs_agnumber_t agno;
xfs_agblock_t agbno;
xfs_extlen_t aglen;
xfs_agblock_t rbno;
xfs_extlen_t rlen;
struct xfs_bmbt_irec map;
int nmaps;
int error = 0;
ASSERT(xfs_is_reflink_inode(ip));
fbno = 0;
end = XFS_B_TO_FSB(mp, i_size_read(VFS_I(ip)));
while (end - fbno > 0) {
nmaps = 1;
/*
* Look for extents in the file. Skip holes, delalloc, or
* unwritten extents; they can't be reflinked.
*/
error = xfs_bmapi_read(ip, fbno, end - fbno, &map, &nmaps, 0);
if (error)
return error;
if (nmaps == 0)
break;
if (!xfs_bmap_is_real_extent(&map))
goto next;
agno = XFS_FSB_TO_AGNO(mp, map.br_startblock);
agbno = XFS_FSB_TO_AGBNO(mp, map.br_startblock);
aglen = map.br_blockcount;
error = xfs_reflink_find_shared(mp, agno, agbno, aglen,
&rbno, &rlen, false);
if (error)
return error;
/* Is there still a shared block here? */
if (rbno != NULLAGBLOCK)
return 0;
next:
fbno = map.br_startoff + map.br_blockcount;
}
/*
* 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;
}
/*
* Sync all the inodes in the given AG according to the
* direction given by the flags.
*/
STATIC int
xfs_sync_inodes_ag(
xfs_mount_t *mp,
int ag,
int flags)
{
xfs_perag_t *pag = &mp->m_perag[ag];
int nr_found;
uint32_t first_index = 0;
int error = 0;
int last_error = 0;
int fflag = XFS_B_ASYNC;
if (flags & SYNC_DELWRI)
fflag = XFS_B_DELWRI;
if (flags & SYNC_WAIT)
fflag = 0; /* synchronous overrides all */
do {
struct inode *inode;
xfs_inode_t *ip = NULL;
int lock_flags = XFS_ILOCK_SHARED;
/*
* use a gang lookup to find the next inode in the tree
* as the tree is sparse and a gang lookup walks to find
* the number of objects requested.
*/
read_lock(&pag->pag_ici_lock);
nr_found = radix_tree_gang_lookup(&pag->pag_ici_root,
(void**)&ip, first_index, 1);
if (!nr_found) {
read_unlock(&pag->pag_ici_lock);
break;
}
/*
* Update the index for the next lookup. Catch overflows
* into the next AG range which can occur if we have inodes
* in the last block of the AG and we are currently
* pointing to the last inode.
*/
first_index = XFS_INO_TO_AGINO(mp, ip->i_ino + 1);
if (first_index < XFS_INO_TO_AGINO(mp, ip->i_ino)) {
read_unlock(&pag->pag_ici_lock);
break;
}
/* nothing to sync during shutdown */
if (XFS_FORCED_SHUTDOWN(mp)) {
read_unlock(&pag->pag_ici_lock);
return 0;
}
/*
* If we can't get a reference on the inode, it must be
* in reclaim. Leave it for the reclaim code to flush.
*/
inode = VFS_I(ip);
if (!igrab(inode)) {
read_unlock(&pag->pag_ici_lock);
continue;
}
read_unlock(&pag->pag_ici_lock);
/* avoid new or bad inodes */
if (is_bad_inode(inode) ||
xfs_iflags_test(ip, XFS_INEW)) {
IRELE(ip);
continue;
}
/*
* If we have to flush data or wait for I/O completion
* we need to hold the iolock.
*/
if ((flags & SYNC_DELWRI) && VN_DIRTY(inode)) {
xfs_ilock(ip, XFS_IOLOCK_SHARED);
lock_flags |= XFS_IOLOCK_SHARED;
error = xfs_flush_pages(ip, 0, -1, fflag, FI_NONE);
if (flags & SYNC_IOWAIT)
xfs_ioend_wait(ip);
}
xfs_ilock(ip, XFS_ILOCK_SHARED);
if ((flags & SYNC_ATTR) && !xfs_inode_clean(ip)) {
if (flags & SYNC_WAIT) {
xfs_iflock(ip);
if (!xfs_inode_clean(ip))
error = xfs_iflush(ip, XFS_IFLUSH_SYNC);
else
xfs_ifunlock(ip);
} else if (xfs_iflock_nowait(ip)) {
if (!xfs_inode_clean(ip))
error = xfs_iflush(ip, XFS_IFLUSH_DELWRI);
else
xfs_ifunlock(ip);
}
}
xfs_iput(ip, lock_flags);
if (error)
last_error = error;
/*
* bail out if the filesystem is corrupted.
*/
if (error == EFSCORRUPTED)
return XFS_ERROR(error);
} while (nr_found);
return last_error;
}
STATIC int
xfs_vn_mknod(
struct inode *dir,
struct dentry *dentry,
int mode,
dev_t rdev)
{
struct inode *inode;
struct xfs_inode *ip = NULL;
xfs_acl_t *default_acl = NULL;
struct xfs_name name;
int (*test_default_acl)(struct inode *) = _ACL_DEFAULT_EXISTS;
int error;
/*
* Irix uses Missed'em'V split, but doesn't want to see
* the upper 5 bits of (14bit) major.
*/
if (unlikely(!sysv_valid_dev(rdev) || MAJOR(rdev) & ~0x1ff))
return -EINVAL;
if (test_default_acl && test_default_acl(dir)) {
if (!_ACL_ALLOC(default_acl)) {
return -ENOMEM;
}
if (!_ACL_GET_DEFAULT(dir, default_acl)) {
_ACL_FREE(default_acl);
default_acl = NULL;
}
}
xfs_dentry_to_name(&name, dentry);
if (IS_POSIXACL(dir) && !default_acl)
mode &= ~current->fs->umask;
switch (mode & S_IFMT) {
case S_IFCHR:
case S_IFBLK:
case S_IFIFO:
case S_IFSOCK:
rdev = sysv_encode_dev(rdev);
case S_IFREG:
error = xfs_create(XFS_I(dir), &name, mode, rdev, &ip, NULL);
break;
case S_IFDIR:
error = xfs_mkdir(XFS_I(dir), &name, mode, &ip, NULL);
break;
default:
error = EINVAL;
break;
}
if (unlikely(error))
goto out_free_acl;
inode = VFS_I(ip);
error = xfs_init_security(inode, dir);
if (unlikely(error))
goto out_cleanup_inode;
if (default_acl) {
error = _ACL_INHERIT(inode, mode, default_acl);
if (unlikely(error))
goto out_cleanup_inode;
_ACL_FREE(default_acl);
}
d_instantiate(dentry, inode);
return -error;
out_cleanup_inode:
xfs_cleanup_inode(dir, inode, dentry);
out_free_acl:
if (default_acl)
_ACL_FREE(default_acl);
return -error;
}
STATIC int
xfs_generic_create(
struct inode *dir,
struct dentry *dentry,
umode_t mode,
dev_t rdev,
bool tmpfile) /* unnamed file */
{
struct inode *inode;
struct xfs_inode *ip = NULL;
struct posix_acl *default_acl, *acl;
struct xfs_name name;
int error;
/*
* Irix uses Missed'em'V split, but doesn't want to see
* the upper 5 bits of (14bit) major.
*/
if (S_ISCHR(mode) || S_ISBLK(mode)) {
if (unlikely(!sysv_valid_dev(rdev) || MAJOR(rdev) & ~0x1ff))
return -EINVAL;
rdev = sysv_encode_dev(rdev);
} else {
rdev = 0;
}
error = posix_acl_create(dir, &mode, &default_acl, &acl);
if (error)
return error;
if (!tmpfile) {
xfs_dentry_to_name(&name, dentry, mode);
error = xfs_create(XFS_I(dir), &name, mode, rdev, &ip);
} else {
error = xfs_create_tmpfile(XFS_I(dir), dentry, mode, &ip);
}
if (unlikely(error))
goto out_free_acl;
inode = VFS_I(ip);
error = xfs_init_security(inode, dir, &dentry->d_name);
if (unlikely(error))
goto out_cleanup_inode;
#ifdef CONFIG_XFS_POSIX_ACL
if (default_acl) {
error = xfs_set_acl(inode, default_acl, ACL_TYPE_DEFAULT);
if (error)
goto out_cleanup_inode;
}
if (acl) {
error = xfs_set_acl(inode, acl, ACL_TYPE_ACCESS);
if (error)
goto out_cleanup_inode;
}
#endif
if (tmpfile)
d_tmpfile(dentry, inode);
else
d_instantiate(dentry, inode);
xfs_finish_inode_setup(ip);
out_free_acl:
if (default_acl)
posix_acl_release(default_acl);
if (acl)
posix_acl_release(acl);
return error;
out_cleanup_inode:
xfs_finish_inode_setup(ip);
if (!tmpfile)
xfs_cleanup_inode(dir, inode, dentry);
iput(inode);
goto out_free_acl;
}
static int
xfs_iget_cache_miss(
struct xfs_mount *mp,
struct xfs_perag *pag,
xfs_trans_t *tp,
xfs_ino_t ino,
struct xfs_inode **ipp,
int flags,
int lock_flags)
{
struct xfs_inode *ip;
int error;
xfs_agino_t agino = XFS_INO_TO_AGINO(mp, ino);
ip = xfs_inode_alloc(mp, ino);
if (!ip)
return ENOMEM;
error = xfs_iread(mp, tp, ip, flags);
if (error)
goto out_destroy;
trace_xfs_iget_miss(ip);
if ((ip->i_d.di_mode == 0) && !(flags & XFS_IGET_CREATE)) {
error = ENOENT;
goto out_destroy;
}
/*
* Preload the radix tree so we can insert safely under the
* write spinlock. Note that we cannot sleep inside the preload
* region.
*/
if (radix_tree_preload(GFP_KERNEL)) {
error = EAGAIN;
goto out_destroy;
}
/*
* Because the inode hasn't been added to the radix-tree yet it can't
* be found by another thread, so we can do the non-sleeping lock here.
*/
if (lock_flags) {
if (!xfs_ilock_nowait(ip, lock_flags))
BUG();
}
spin_lock(&pag->pag_ici_lock);
/* insert the new inode */
error = radix_tree_insert(&pag->pag_ici_root, agino, ip);
if (unlikely(error)) {
WARN_ON(error != -EEXIST);
XFS_STATS_INC(xs_ig_dup);
error = EAGAIN;
goto out_preload_end;
}
/* These values _must_ be set before releasing the radix tree lock! */
ip->i_udquot = ip->i_gdquot = NULL;
xfs_iflags_set(ip, XFS_INEW);
spin_unlock(&pag->pag_ici_lock);
radix_tree_preload_end();
*ipp = ip;
return 0;
out_preload_end:
spin_unlock(&pag->pag_ici_lock);
radix_tree_preload_end();
if (lock_flags)
xfs_iunlock(ip, lock_flags);
out_destroy:
__destroy_inode(VFS_I(ip));
xfs_inode_free(ip);
return error;
}
/*
* Process a bmap update intent item that was recovered from the log.
* We need to update some inode's bmbt.
*/
int
xfs_bui_recover(
struct xfs_mount *mp,
struct xfs_bui_log_item *buip)
{
int error = 0;
unsigned int bui_type;
struct xfs_map_extent *bmap;
xfs_fsblock_t startblock_fsb;
xfs_fsblock_t inode_fsb;
xfs_filblks_t count;
bool op_ok;
struct xfs_bud_log_item *budp;
enum xfs_bmap_intent_type type;
int whichfork;
xfs_exntst_t state;
struct xfs_trans *tp;
struct xfs_inode *ip = NULL;
struct xfs_defer_ops dfops;
struct xfs_bmbt_irec irec;
xfs_fsblock_t firstfsb;
ASSERT(!test_bit(XFS_BUI_RECOVERED, &buip->bui_flags));
/* Only one mapping operation per BUI... */
if (buip->bui_format.bui_nextents != XFS_BUI_MAX_FAST_EXTENTS) {
set_bit(XFS_BUI_RECOVERED, &buip->bui_flags);
xfs_bui_release(buip);
return -EIO;
}
/*
* First check the validity of the extent described by the
* BUI. If anything is bad, then toss the BUI.
*/
bmap = &buip->bui_format.bui_extents[0];
startblock_fsb = XFS_BB_TO_FSB(mp,
XFS_FSB_TO_DADDR(mp, bmap->me_startblock));
inode_fsb = XFS_BB_TO_FSB(mp, XFS_FSB_TO_DADDR(mp,
XFS_INO_TO_FSB(mp, bmap->me_owner)));
switch (bmap->me_flags & XFS_BMAP_EXTENT_TYPE_MASK) {
case XFS_BMAP_MAP:
case XFS_BMAP_UNMAP:
op_ok = true;
break;
default:
op_ok = false;
break;
}
if (!op_ok || startblock_fsb == 0 ||
bmap->me_len == 0 ||
inode_fsb == 0 ||
startblock_fsb >= mp->m_sb.sb_dblocks ||
bmap->me_len >= mp->m_sb.sb_agblocks ||
inode_fsb >= mp->m_sb.sb_dblocks ||
(bmap->me_flags & ~XFS_BMAP_EXTENT_FLAGS)) {
/*
* This will pull the BUI from the AIL and
* free the memory associated with it.
*/
set_bit(XFS_BUI_RECOVERED, &buip->bui_flags);
xfs_bui_release(buip);
return -EIO;
}
error = xfs_trans_alloc(mp, &M_RES(mp)->tr_itruncate,
XFS_EXTENTADD_SPACE_RES(mp, XFS_DATA_FORK), 0, 0, &tp);
if (error)
return error;
budp = xfs_trans_get_bud(tp, buip);
/* Grab the inode. */
error = xfs_iget(mp, tp, bmap->me_owner, 0, XFS_ILOCK_EXCL, &ip);
if (error)
goto err_inode;
if (VFS_I(ip)->i_nlink == 0)
xfs_iflags_set(ip, XFS_IRECOVERY);
xfs_defer_init(&dfops, &firstfsb);
/* Process deferred bmap item. */
state = (bmap->me_flags & XFS_BMAP_EXTENT_UNWRITTEN) ?
XFS_EXT_UNWRITTEN : XFS_EXT_NORM;
whichfork = (bmap->me_flags & XFS_BMAP_EXTENT_ATTR_FORK) ?
XFS_ATTR_FORK : XFS_DATA_FORK;
bui_type = bmap->me_flags & XFS_BMAP_EXTENT_TYPE_MASK;
switch (bui_type) {
case XFS_BMAP_MAP:
case XFS_BMAP_UNMAP:
type = bui_type;
break;
default:
error = -EFSCORRUPTED;
goto err_dfops;
}
xfs_trans_ijoin(tp, ip, 0);
count = bmap->me_len;
error = xfs_trans_log_finish_bmap_update(tp, budp, &dfops, type,
ip, whichfork, bmap->me_startoff,
bmap->me_startblock, &count, state);
if (error)
goto err_dfops;
if (count > 0) {
ASSERT(type == XFS_BMAP_UNMAP);
irec.br_startblock = bmap->me_startblock;
irec.br_blockcount = count;
irec.br_startoff = bmap->me_startoff;
irec.br_state = state;
error = xfs_bmap_unmap_extent(tp->t_mountp, &dfops, ip, &irec);
if (error)
goto err_dfops;
}
/* Finish transaction, free inodes. */
error = xfs_defer_finish(&tp, &dfops);
if (error)
goto err_dfops;
set_bit(XFS_BUI_RECOVERED, &buip->bui_flags);
error = xfs_trans_commit(tp);
xfs_iunlock(ip, XFS_ILOCK_EXCL);
IRELE(ip);
return error;
err_dfops:
xfs_defer_cancel(&dfops);
err_inode:
xfs_trans_cancel(tp);
if (ip) {
xfs_iunlock(ip, XFS_ILOCK_EXCL);
IRELE(ip);
}
return error;
}
/*
* Convert userspace handle data into inode.
*
* We use the fact that all the fsop_handlereq ioctl calls have a data
* structure argument whose first component is always a xfs_fsop_handlereq_t,
* so we can pass that sub structure into this handy, shared routine.
*
* If no error, caller must always iput the returned inode.
*/
STATIC int
xfs_vget_fsop_handlereq(
xfs_mount_t *mp,
struct inode *parinode, /* parent inode pointer */
xfs_fsop_handlereq_t *hreq,
struct inode **inode)
{
void __user *hanp;
size_t hlen;
xfs_fid_t *xfid;
xfs_handle_t *handlep;
xfs_handle_t handle;
xfs_inode_t *ip;
xfs_ino_t ino;
__u32 igen;
int error;
/*
* Only allow handle opens under a directory.
*/
if (!S_ISDIR(parinode->i_mode))
return XFS_ERROR(ENOTDIR);
hanp = hreq->ihandle;
hlen = hreq->ihandlen;
handlep = &handle;
if (hlen < sizeof(handlep->ha_fsid) || hlen > sizeof(*handlep))
return XFS_ERROR(EINVAL);
if (copy_from_user(handlep, hanp, hlen))
return XFS_ERROR(EFAULT);
if (hlen < sizeof(*handlep))
memset(((char *)handlep) + hlen, 0, sizeof(*handlep) - hlen);
if (hlen > sizeof(handlep->ha_fsid)) {
if (handlep->ha_fid.fid_len !=
(hlen - sizeof(handlep->ha_fsid) -
sizeof(handlep->ha_fid.fid_len)) ||
handlep->ha_fid.fid_pad)
return XFS_ERROR(EINVAL);
}
/*
* Crack the handle, obtain the inode # & generation #
*/
xfid = (struct xfs_fid *)&handlep->ha_fid;
if (xfid->fid_len == sizeof(*xfid) - sizeof(xfid->fid_len)) {
ino = xfid->fid_ino;
igen = xfid->fid_gen;
} else {
return XFS_ERROR(EINVAL);
}
/*
* Get the XFS inode, building a Linux inode to go with it.
*/
error = xfs_iget(mp, NULL, ino, 0, XFS_ILOCK_SHARED, &ip, 0);
if (error)
return error;
if (ip == NULL)
return XFS_ERROR(EIO);
if (ip->i_d.di_gen != igen) {
xfs_iput_new(ip, XFS_ILOCK_SHARED);
return XFS_ERROR(ENOENT);
}
xfs_iunlock(ip, XFS_ILOCK_SHARED);
*inode = VFS_I(ip);
return 0;
}
/*
* 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;
}
ASSERT(completion_done(&ip->i_flush));
kmem_zone_free(xfs_inode_zone, ip);
}
/*
* Check the validity of the inode we just found it the cache
*/
static int
xfs_iget_cache_hit(
struct xfs_perag *pag,
struct xfs_inode *ip,
int flags,
int lock_flags) __releases(pag->pag_ici_lock)
{
struct inode *inode = VFS_I(ip);
struct xfs_mount *mp = ip->i_mount;
int error;
spin_lock(&ip->i_flags_lock);
/*
* If we are racing with another cache hit that is currently
* instantiating this inode or currently recycling it out of
* reclaimabe state, wait for the initialisation to complete
* before continuing.
*
* XXX(hch): eventually we should do something equivalent to
* wait_on_inode to wait for these flags to be cleared
* instead of polling for it.
*/
/*
* Unmap a range of blocks from a file, then map other blocks into the hole.
* The range to unmap is (destoff : destoff + srcioff + irec->br_blockcount).
* The extent irec is mapped into dest at irec->br_startoff.
*/
STATIC int
xfs_reflink_remap_extent(
struct xfs_inode *ip,
struct xfs_bmbt_irec *irec,
xfs_fileoff_t destoff,
xfs_off_t new_isize)
{
struct xfs_mount *mp = ip->i_mount;
bool real_extent = xfs_bmap_is_real_extent(irec);
struct xfs_trans *tp;
xfs_fsblock_t firstfsb;
unsigned int resblks;
struct xfs_defer_ops dfops;
struct xfs_bmbt_irec uirec;
xfs_filblks_t rlen;
xfs_filblks_t unmap_len;
xfs_off_t newlen;
int error;
unmap_len = irec->br_startoff + irec->br_blockcount - destoff;
trace_xfs_reflink_punch_range(ip, destoff, unmap_len);
/* No reflinking if we're low on space */
if (real_extent) {
error = xfs_reflink_ag_has_free_space(mp,
XFS_FSB_TO_AGNO(mp, irec->br_startblock));
if (error)
goto out;
}
/* Start a rolling transaction to switch the mappings */
resblks = XFS_EXTENTADD_SPACE_RES(ip->i_mount, XFS_DATA_FORK);
error = xfs_trans_alloc(mp, &M_RES(mp)->tr_write, resblks, 0, 0, &tp);
if (error)
goto out;
xfs_ilock(ip, XFS_ILOCK_EXCL);
xfs_trans_ijoin(tp, ip, 0);
/* If we're not just clearing space, then do we have enough quota? */
if (real_extent) {
error = xfs_trans_reserve_quota_nblks(tp, ip,
irec->br_blockcount, 0, XFS_QMOPT_RES_REGBLKS);
if (error)
goto out_cancel;
}
trace_xfs_reflink_remap(ip, irec->br_startoff,
irec->br_blockcount, irec->br_startblock);
/* Unmap the old blocks in the data fork. */
rlen = unmap_len;
while (rlen) {
xfs_defer_init(&dfops, &firstfsb);
error = __xfs_bunmapi(tp, ip, destoff, &rlen, 0, 1,
&firstfsb, &dfops);
if (error)
goto out_defer;
/*
* Trim the extent to whatever got unmapped.
* Remember, bunmapi works backwards.
*/
uirec.br_startblock = irec->br_startblock + rlen;
uirec.br_startoff = irec->br_startoff + rlen;
uirec.br_blockcount = unmap_len - rlen;
unmap_len = rlen;
/* If this isn't a real mapping, we're done. */
if (!real_extent || uirec.br_blockcount == 0)
goto next_extent;
trace_xfs_reflink_remap(ip, uirec.br_startoff,
uirec.br_blockcount, uirec.br_startblock);
/* Update the refcount tree */
error = xfs_refcount_increase_extent(mp, &dfops, &uirec);
if (error)
goto out_defer;
/* Map the new blocks into the data fork. */
error = xfs_bmap_map_extent(mp, &dfops, ip, &uirec);
if (error)
goto out_defer;
/* Update quota accounting. */
xfs_trans_mod_dquot_byino(tp, ip, XFS_TRANS_DQ_BCOUNT,
uirec.br_blockcount);
/* Update dest isize if needed. */
newlen = XFS_FSB_TO_B(mp,
uirec.br_startoff + uirec.br_blockcount);
newlen = min_t(xfs_off_t, newlen, new_isize);
if (newlen > i_size_read(VFS_I(ip))) {
trace_xfs_reflink_update_inode_size(ip, newlen);
i_size_write(VFS_I(ip), newlen);
ip->i_d.di_size = newlen;
xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
}
next_extent:
/* Process all the deferred stuff. */
error = xfs_defer_finish(&tp, &dfops, ip);
if (error)
goto out_defer;
}
error = xfs_trans_commit(tp);
xfs_iunlock(ip, XFS_ILOCK_EXCL);
if (error)
goto out;
return 0;
out_defer:
xfs_defer_cancel(&dfops);
out_cancel:
xfs_trans_cancel(tp);
xfs_iunlock(ip, XFS_ILOCK_EXCL);
out:
trace_xfs_reflink_remap_extent_error(ip, error, _RET_IP_);
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;
bool did_zeroing = false;
trace_xfs_setattr(ip);
if (mp->m_flags & XFS_MOUNT_RDONLY)
return -EROFS;
if (XFS_FORCED_SHUTDOWN(mp))
return -EIO;
error = inode_change_ok(inode, iattr);
if (error)
return error;
ASSERT(xfs_isilocked(ip, XFS_IOLOCK_EXCL));
ASSERT(xfs_isilocked(ip, XFS_MMAPLOCK_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;
/*
* File data changes must be complete before we start the transaction to
* modify the inode. 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.
*
* Start with zeroing any data block beyond EOF that we may expose on
* file extension.
*/
if (newsize > oldsize) {
error = xfs_zero_eof(ip, newsize, oldsize, &did_zeroing);
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. Note that this includes any block zeroing we did above;
* otherwise those blocks may not be zeroed after a crash.
*/
if (newsize > ip->i_d.di_size &&
(oldsize != ip->i_d.di_size || did_zeroing)) {
error = filemap_write_and_wait_range(VFS_I(ip)->i_mapping,
ip->i_d.di_size, newsize);
if (error)
return error;
}
/* Now wait for all direct I/O to complete. */
inode_dio_wait(inode);
/*
* We've already locked out new page faults, so now we can safely remove
* pages from the page cache knowing they won't get refaulted until we
* drop the XFS_MMAP_EXCL lock after the extent manipulations are
* complete. The truncate_setsize() call also cleans partial EOF page
* PTEs on extending truncates and hence ensures sub-page block size
* filesystems are correctly handled, too.
*
* We have to do all the page cache truncate work outside the
* transaction context as the "lock" order is page lock->log space
* reservation as defined by extent allocation in the writeback path.
* Hence a truncate can fail with ENOMEM from xfs_trans_reserve(), but
* having already truncated the in-memory version of the file (i.e. made
* user visible changes). There's not much we can do about this, except
* to hope that the caller sees ENOMEM and retries the truncate
* operation.
*/
if (IS_DAX(inode))
error = dax_truncate_page(inode, newsize, xfs_get_blocks_direct);
else
error = block_truncate_page(inode->i_mapping, newsize,
xfs_get_blocks);
if (error)
return error;
truncate_setsize(inode, newsize);
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;
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_cancel;
/*
* 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(mp, xs_ig_attrchg);
if (mp->m_flags & XFS_MOUNT_WSYNC)
xfs_trans_set_sync(tp);
error = xfs_trans_commit(tp);
out_unlock:
if (lock_flags)
xfs_iunlock(ip, lock_flags);
return error;
out_trans_cancel:
xfs_trans_cancel(tp);
goto out_unlock;
}
/*
* The user wants to preemptively CoW all shared blocks in this file,
* which enables us to turn off the reflink flag. Iterate all
* extents which are not prealloc/delalloc to see which ranges are
* mentioned in the refcount tree, then read those blocks into the
* pagecache, dirty them, fsync them back out, and then we can update
* the inode flag. What happens if we run out of memory? :)
*/
STATIC int
xfs_reflink_dirty_extents(
struct xfs_inode *ip,
xfs_fileoff_t fbno,
xfs_filblks_t end,
xfs_off_t isize)
{
struct xfs_mount *mp = ip->i_mount;
xfs_agnumber_t agno;
xfs_agblock_t agbno;
xfs_extlen_t aglen;
xfs_agblock_t rbno;
xfs_extlen_t rlen;
xfs_off_t fpos;
xfs_off_t flen;
struct xfs_bmbt_irec map[2];
int nmaps;
int error = 0;
while (end - fbno > 0) {
nmaps = 1;
/*
* Look for extents in the file. Skip holes, delalloc, or
* unwritten extents; they can't be reflinked.
*/
error = xfs_bmapi_read(ip, fbno, end - fbno, map, &nmaps, 0);
if (error)
goto out;
if (nmaps == 0)
break;
if (!xfs_bmap_is_real_extent(&map[0]))
goto next;
map[1] = map[0];
while (map[1].br_blockcount) {
agno = XFS_FSB_TO_AGNO(mp, map[1].br_startblock);
agbno = XFS_FSB_TO_AGBNO(mp, map[1].br_startblock);
aglen = map[1].br_blockcount;
error = xfs_reflink_find_shared(mp, agno, agbno, aglen,
&rbno, &rlen, true);
if (error)
goto out;
if (rbno == NULLAGBLOCK)
break;
/* Dirty the pages */
xfs_iunlock(ip, XFS_ILOCK_EXCL);
fpos = XFS_FSB_TO_B(mp, map[1].br_startoff +
(rbno - agbno));
flen = XFS_FSB_TO_B(mp, rlen);
if (fpos + flen > isize)
flen = isize - fpos;
error = iomap_file_dirty(VFS_I(ip), fpos, flen,
&xfs_iomap_ops);
xfs_ilock(ip, XFS_ILOCK_EXCL);
if (error)
goto out;
map[1].br_blockcount -= (rbno - agbno + rlen);
map[1].br_startoff += (rbno - agbno + rlen);
map[1].br_startblock += (rbno - agbno + rlen);
}
next:
fbno = map[0].br_startoff + map[0].br_blockcount;
}
out:
return error;
}
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;
uid_t uid = 0, iuid = 0;
gid_t gid = 0, igid = 0;
struct xfs_dquot *udqp = NULL, *gdqp = NULL;
struct xfs_dquot *olddquot1 = NULL, *olddquot2 = NULL;
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((mask & ATTR_SIZE) == 0);
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 = ip->i_d.di_uid;
}
if ((mask & ATTR_GID) && XFS_IS_GQUOTA_ON(mp)) {
gid = iattr->ia_gid;
qflags |= XFS_QMOPT_GQUOTA;
} else {
gid = ip->i_d.di_gid;
}
ASSERT(udqp == NULL);
ASSERT(gdqp == NULL);
error = xfs_qm_vop_dqalloc(ip, uid, gid, xfs_get_projid(ip),
qflags, &udqp, &gdqp);
if (error)
return error;
}
tp = xfs_trans_alloc(mp, XFS_TRANS_SETATTR_NOT_SIZE);
error = xfs_trans_reserve(tp, 0, XFS_ICHANGE_LOG_RES(mp), 0, 0, 0);
if (error)
goto out_dqrele;
xfs_ilock(ip, XFS_ILOCK_EXCL);
if (mask & (ATTR_UID|ATTR_GID)) {
iuid = ip->i_d.di_uid;
igid = ip->i_d.di_gid;
gid = (mask & ATTR_GID) ? iattr->ia_gid : igid;
uid = (mask & ATTR_UID) ? iattr->ia_uid : iuid;
if (XFS_IS_QUOTA_RUNNING(mp) &&
((XFS_IS_UQUOTA_ON(mp) && iuid != uid) ||
(XFS_IS_GQUOTA_ON(mp) && igid != gid))) {
ASSERT(tp);
error = xfs_qm_vop_chown_reserve(tp, ip, udqp, gdqp,
capable(CAP_FOWNER) ?
XFS_QMOPT_FORCE_RES : 0);
if (error)
goto out_trans_cancel;
}
}
xfs_trans_ijoin(tp, ip, 0);
if (mask & (ATTR_UID|ATTR_GID)) {
if ((ip->i_d.di_mode & (S_ISUID|S_ISGID)) &&
!capable(CAP_FSETID))
ip->i_d.di_mode &= ~(S_ISUID|S_ISGID);
if (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 = uid;
inode->i_uid = uid;
}
if (igid != gid) {
if (XFS_IS_QUOTA_RUNNING(mp) && XFS_IS_GQUOTA_ON(mp)) {
ASSERT(!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 = gid;
inode->i_gid = gid;
}
}
if (mask & ATTR_MODE) {
umode_t mode = iattr->ia_mode;
if (!in_group_p(inode->i_gid) && !capable(CAP_FSETID))
mode &= ~S_ISGID;
ip->i_d.di_mode &= S_IFMT;
ip->i_d.di_mode |= mode & ~S_IFMT;
inode->i_mode &= S_IFMT;
inode->i_mode |= mode & ~S_IFMT;
}
if (mask & ATTR_ATIME) {
inode->i_atime = iattr->ia_atime;
ip->i_d.di_atime.t_sec = iattr->ia_atime.tv_sec;
ip->i_d.di_atime.t_nsec = iattr->ia_atime.tv_nsec;
}
if (mask & ATTR_CTIME) {
inode->i_ctime = iattr->ia_ctime;
ip->i_d.di_ctime.t_sec = iattr->ia_ctime.tv_sec;
ip->i_d.di_ctime.t_nsec = iattr->ia_ctime.tv_nsec;
}
if (mask & ATTR_MTIME) {
inode->i_mtime = iattr->ia_mtime;
ip->i_d.di_mtime.t_sec = iattr->ia_mtime.tv_sec;
ip->i_d.di_mtime.t_nsec = iattr->ia_mtime.tv_nsec;
}
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);
xfs_qm_dqrele(olddquot1);
xfs_qm_dqrele(olddquot2);
xfs_qm_dqrele(udqp);
xfs_qm_dqrele(gdqp);
if (error)
return XFS_ERROR(error);
if ((mask & ATTR_MODE) && !(flags & XFS_ATTR_NOACL)) {
error = -xfs_acl_chmod(inode);
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;
}
STATIC int
xfs_ioctl_setattr(
xfs_inode_t *ip,
struct fsxattr *fa)
{
struct xfs_mount *mp = ip->i_mount;
struct xfs_trans *tp;
struct xfs_dquot *udqp = NULL;
struct xfs_dquot *pdqp = NULL;
struct xfs_dquot *olddquot = NULL;
int code;
int join_flags = 0;
trace_xfs_ioctl_setattr(ip);
code = xfs_ioctl_setattr_check_projid(ip, fa);
if (code)
return code;
/*
* 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)) {
code = xfs_qm_vop_dqalloc(ip, ip->i_d.di_uid,
ip->i_d.di_gid, fa->fsx_projid,
XFS_QMOPT_PQUOTA, &udqp, NULL, &pdqp);
if (code)
return code;
}
/*
* Changing DAX config may require inode locking for mapping
* invalidation. These need to be held all the way to transaction commit
* or cancel time, so need to be passed through to
* xfs_ioctl_setattr_get_trans() so it can apply them to the join call
* appropriately.
*/
code = xfs_ioctl_setattr_dax_invalidate(ip, fa, &join_flags);
if (code)
goto error_free_dquots;
tp = xfs_ioctl_setattr_get_trans(ip, join_flags);
if (IS_ERR(tp)) {
code = PTR_ERR(tp);
goto error_free_dquots;
}
if (XFS_IS_QUOTA_RUNNING(mp) && XFS_IS_PQUOTA_ON(mp) &&
xfs_get_projid(ip) != fa->fsx_projid) {
code = xfs_qm_vop_chown_reserve(tp, ip, udqp, NULL, pdqp,
capable(CAP_FOWNER) ? XFS_QMOPT_FORCE_RES : 0);
if (code) /* out of quota */
goto error_trans_cancel;
}
code = xfs_ioctl_setattr_check_extsize(ip, fa);
if (code)
goto error_trans_cancel;
code = xfs_ioctl_setattr_check_cowextsize(ip, fa);
if (code)
goto error_trans_cancel;
code = xfs_ioctl_setattr_xflags(tp, ip, fa);
if (code)
goto error_trans_cancel;
/*
* Change file ownership. Must be the owner or privileged. 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 ((VFS_I(ip)->i_mode & (S_ISUID|S_ISGID)) &&
!capable_wrt_inode_uidgid(VFS_I(ip), CAP_FSETID))
VFS_I(ip)->i_mode &= ~(S_ISUID|S_ISGID);
/* Change the ownerships and register project quota modifications */
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_pdquot, pdqp);
}
ASSERT(ip->i_d.di_version > 1);
xfs_set_projid(ip, fa->fsx_projid);
}
/*
* Only set the extent size hint if we've already determined that the
* extent size hint should be set on the inode. If no extent size flags
* are set on the inode then unconditionally clear the extent size hint.
*/
if (ip->i_d.di_flags & (XFS_DIFLAG_EXTSIZE | XFS_DIFLAG_EXTSZINHERIT))
ip->i_d.di_extsize = fa->fsx_extsize >> mp->m_sb.sb_blocklog;
else
int
xfs_setattr_size(
struct xfs_inode *ip,
struct iattr *iattr,
int flags)
{
struct xfs_mount *mp = ip->i_mount;
struct inode *inode = VFS_I(ip);
int mask = iattr->ia_valid;
xfs_off_t oldsize, newsize;
struct xfs_trans *tp;
int error;
uint lock_flags;
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(S_ISREG(ip->i_d.di_mode));
ASSERT((mask & (ATTR_MODE|ATTR_UID|ATTR_GID|ATTR_ATIME|ATTR_ATIME_SET|
ATTR_MTIME_SET|ATTR_KILL_SUID|ATTR_KILL_SGID|
ATTR_KILL_PRIV|ATTR_TIMES_SET)) == 0);
lock_flags = XFS_ILOCK_EXCL;
if (!(flags & XFS_ATTR_NOLOCK))
lock_flags |= XFS_IOLOCK_EXCL;
xfs_ilock(ip, lock_flags);
oldsize = inode->i_size;
newsize = iattr->ia_size;
if (newsize == 0 && oldsize == 0 && ip->i_d.di_nextents == 0) {
if (!(mask & (ATTR_CTIME|ATTR_MTIME)))
goto out_unlock;
xfs_iunlock(ip, lock_flags);
iattr->ia_valid &= ~ATTR_SIZE;
return xfs_setattr_nonsize(ip, iattr, 0);
}
error = xfs_qm_dqattach_locked(ip, 0);
if (error)
goto out_unlock;
if (newsize > oldsize) {
error = xfs_zero_eof(ip, newsize, oldsize);
if (error)
goto out_unlock;
}
xfs_iunlock(ip, XFS_ILOCK_EXCL);
lock_flags &= ~XFS_ILOCK_EXCL;
/*
* 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 = xfs_flush_pages(ip, ip->i_d.di_size, newsize, 0,
FI_NONE);
if (error)
goto out_unlock;
}
inode_dio_wait(inode);
error = -block_truncate_page(inode->i_mapping, newsize, xfs_get_blocks);
if (error)
goto out_unlock;
tp = xfs_trans_alloc(mp, XFS_TRANS_SETATTR_SIZE);
error = xfs_trans_reserve(tp, 0, XFS_ITRUNCATE_LOG_RES(mp), 0,
XFS_TRANS_PERM_LOG_RES,
XFS_ITRUNCATE_LOG_COUNT);
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);
if (newsize != oldsize && (!(mask & (ATTR_CTIME | ATTR_MTIME)))) {
iattr->ia_ctime = iattr->ia_mtime =
current_fs_time(inode->i_sb);
mask |= 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;
xfs_iflags_set(ip, XFS_ITRUNCATED);
}
if (mask & ATTR_CTIME) {
inode->i_ctime = iattr->ia_ctime;
ip->i_d.di_ctime.t_sec = iattr->ia_ctime.tv_sec;
ip->i_d.di_ctime.t_nsec = iattr->ia_ctime.tv_nsec;
}
if (mask & ATTR_MTIME) {
inode->i_mtime = iattr->ia_mtime;
ip->i_d.di_mtime.t_sec = iattr->ia_mtime.tv_sec;
ip->i_d.di_mtime.t_nsec = iattr->ia_mtime.tv_nsec;
}
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;
}
STATIC int
xfs_vn_mknod(
struct inode *dir,
struct dentry *dentry,
int mode,
dev_t rdev)
{
struct inode *inode;
struct xfs_inode *ip = NULL;
struct posix_acl *default_acl = NULL;
struct xfs_name name;
int error;
/*
* Irix uses Missed'em'V split, but doesn't want to see
* the upper 5 bits of (14bit) major.
*/
if (S_ISCHR(mode) || S_ISBLK(mode)) {
if (unlikely(!sysv_valid_dev(rdev) || MAJOR(rdev) & ~0x1ff))
return -EINVAL;
rdev = sysv_encode_dev(rdev);
} else {
rdev = 0;
}
if (IS_POSIXACL(dir)) {
default_acl = xfs_get_acl(dir, ACL_TYPE_DEFAULT);
if (IS_ERR(default_acl))
return PTR_ERR(default_acl);
if (!default_acl)
mode &= ~current_umask();
}
xfs_dentry_to_name(&name, dentry);
error = xfs_create(XFS_I(dir), &name, mode, rdev, &ip);
if (unlikely(error))
goto out_free_acl;
inode = VFS_I(ip);
error = xfs_init_security(inode, dir, &dentry->d_name);
if (unlikely(error))
goto out_cleanup_inode;
if (default_acl) {
error = -xfs_inherit_acl(inode, default_acl);
default_acl = NULL;
if (unlikely(error))
goto out_cleanup_inode;
}
d_instantiate(dentry, inode);
return -error;
out_cleanup_inode:
xfs_cleanup_inode(dir, inode, dentry);
out_free_acl:
posix_acl_release(default_acl);
return -error;
}
/*
* Inodes in different states need to be treated differently, and the return
* value of xfs_iflush is not sufficient to get this right. The following table
* lists the inode states and the reclaim actions necessary for non-blocking
* reclaim:
*
*
* inode state iflush ret required action
* --------------- ---------- ---------------
* bad - reclaim
* shutdown EIO unpin and reclaim
* clean, unpinned 0 reclaim
* stale, unpinned 0 reclaim
* clean, pinned(*) 0 requeue
* stale, pinned EAGAIN requeue
* dirty, delwri ok 0 requeue
* dirty, delwri blocked EAGAIN requeue
* dirty, sync flush 0 reclaim
*
* (*) dgc: I don't think the clean, pinned state is possible but it gets
* handled anyway given the order of checks implemented.
*
* As can be seen from the table, the return value of xfs_iflush() is not
* sufficient to correctly decide the reclaim action here. The checks in
* xfs_iflush() might look like duplicates, but they are not.
*
* Also, because we get the flush lock first, we know that any inode that has
* been flushed delwri has had the flush completed by the time we check that
* the inode is clean. The clean inode check needs to be done before flushing
* the inode delwri otherwise we would loop forever requeuing clean inodes as
* we cannot tell apart a successful delwri flush and a clean inode from the
* return value of xfs_iflush().
*
* Note that because the inode is flushed delayed write by background
* writeback, the flush lock may already be held here and waiting on it can
* result in very long latencies. Hence for sync reclaims, where we wait on the
* flush lock, the caller should push out delayed write inodes first before
* trying to reclaim them to minimise the amount of time spent waiting. For
* background relaim, we just requeue the inode for the next pass.
*
* Hence the order of actions after gaining the locks should be:
* bad => reclaim
* shutdown => unpin and reclaim
* pinned, delwri => requeue
* pinned, sync => unpin
* stale => reclaim
* clean => reclaim
* dirty, delwri => flush and requeue
* dirty, sync => flush, wait and reclaim
*/
STATIC int
xfs_reclaim_inode(
struct xfs_inode *ip,
struct xfs_perag *pag,
int sync_mode)
{
int error;
restart:
error = 0;
xfs_ilock(ip, XFS_ILOCK_EXCL);
if (!xfs_iflock_nowait(ip)) {
if (!(sync_mode & SYNC_WAIT))
goto out;
xfs_iflock(ip);
}
if (is_bad_inode(VFS_I(ip)))
goto reclaim;
if (XFS_FORCED_SHUTDOWN(ip->i_mount)) {
xfs_iunpin_wait(ip);
goto reclaim;
}
if (xfs_ipincount(ip)) {
if (!(sync_mode & SYNC_WAIT)) {
xfs_ifunlock(ip);
goto out;
}
xfs_iunpin_wait(ip);
}
if (xfs_iflags_test(ip, XFS_ISTALE))
goto reclaim;
if (xfs_inode_clean(ip))
goto reclaim;
/*
* Now we have an inode that needs flushing.
*
* We do a nonblocking flush here even if we are doing a SYNC_WAIT
* reclaim as we can deadlock with inode cluster removal.
* xfs_ifree_cluster() can lock the inode buffer before it locks the
* ip->i_lock, and we are doing the exact opposite here. As a result,
* doing a blocking xfs_itobp() to get the cluster buffer will result
* in an ABBA deadlock with xfs_ifree_cluster().
*
* As xfs_ifree_cluser() must gather all inodes that are active in the
* cache to mark them stale, if we hit this case we don't actually want
* to do IO here - we want the inode marked stale so we can simply
* reclaim it. Hence if we get an EAGAIN error on a SYNC_WAIT flush,
* just unlock the inode, back off and try again. Hopefully the next
* pass through will see the stale flag set on the inode.
*/
error = xfs_iflush(ip, SYNC_TRYLOCK | sync_mode);
if (sync_mode & SYNC_WAIT) {
if (error == EAGAIN) {
xfs_iunlock(ip, XFS_ILOCK_EXCL);
/* backoff longer than in xfs_ifree_cluster */
delay(2);
goto restart;
}
xfs_iflock(ip);
goto reclaim;
}
/*
* When we have to flush an inode but don't have SYNC_WAIT set, we
* flush the inode out using a delwri buffer and wait for the next
* call into reclaim to find it in a clean state instead of waiting for
* it now. We also don't return errors here - if the error is transient
* then the next reclaim pass will flush the inode, and if the error
* is permanent then the next sync reclaim will reclaim the inode and
* pass on the error.
*/
if (error && error != EAGAIN && !XFS_FORCED_SHUTDOWN(ip->i_mount)) {
xfs_warn(ip->i_mount,
"inode 0x%llx background reclaim flush failed with %d",
(long long)ip->i_ino, error);
}
out:
xfs_iflags_clear(ip, XFS_IRECLAIM);
xfs_iunlock(ip, XFS_ILOCK_EXCL);
/*
* We could return EAGAIN here to make reclaim rescan the inode tree in
* a short while. However, this just burns CPU time scanning the tree
* waiting for IO to complete and xfssyncd never goes back to the idle
* state. Instead, return 0 to let the next scheduled background reclaim
* attempt to reclaim the inode again.
*/
return 0;
reclaim:
xfs_ifunlock(ip);
xfs_iunlock(ip, XFS_ILOCK_EXCL);
XFS_STATS_INC(xs_ig_reclaims);
/*
* Remove the inode from the per-AG radix tree.
*
* Because radix_tree_delete won't complain even if the item was never
* added to the tree assert that it's been there before to catch
* problems with the inode life time early on.
*/
spin_lock(&pag->pag_ici_lock);
if (!radix_tree_delete(&pag->pag_ici_root,
XFS_INO_TO_AGINO(ip->i_mount, ip->i_ino)))
ASSERT(0);
__xfs_inode_clear_reclaim(pag, ip);
spin_unlock(&pag->pag_ici_lock);
/*
* Here we do an (almost) spurious inode lock in order to coordinate
* with inode cache radix tree lookups. This is because the lookup
* can reference the inodes in the cache without taking references.
*
* We make that OK here by ensuring that we wait until the inode is
* unlocked after the lookup before we go ahead and free it. We get
* both the ilock and the iolock because the code may need to drop the
* ilock one but will still hold the iolock.
*/
xfs_ilock(ip, XFS_ILOCK_EXCL | XFS_IOLOCK_EXCL);
xfs_qm_dqdetach(ip);
xfs_iunlock(ip, XFS_ILOCK_EXCL | XFS_IOLOCK_EXCL);
xfs_inode_free(ip);
return error;
}
/*
* Truncate file. Must have write permission and not be a directory.
*/
int
xfs_setattr_size(
struct xfs_inode *ip,
struct iattr *iattr,
int flags)
{
struct xfs_mount *mp = ip->i_mount;
struct inode *inode = VFS_I(ip);
int mask = iattr->ia_valid;
struct xfs_trans *tp;
int error;
uint lock_flags;
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(S_ISREG(ip->i_d.di_mode));
ASSERT((mask & (ATTR_MODE|ATTR_UID|ATTR_GID|ATTR_ATIME|ATTR_ATIME_SET|
ATTR_MTIME_SET|ATTR_KILL_SUID|ATTR_KILL_SGID|
ATTR_KILL_PRIV|ATTR_TIMES_SET)) == 0);
lock_flags = XFS_ILOCK_EXCL;
if (!(flags & XFS_ATTR_NOLOCK))
lock_flags |= XFS_IOLOCK_EXCL;
xfs_ilock(ip, lock_flags);
/*
* Short circuit the truncate case for zero length files.
*/
if (iattr->ia_size == 0 &&
ip->i_size == 0 && ip->i_d.di_nextents == 0) {
if (!(mask & (ATTR_CTIME|ATTR_MTIME)))
goto out_unlock;
/*
* Use the regular setattr path to update the timestamps.
*/
xfs_iunlock(ip, lock_flags);
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_locked(ip, 0);
if (error)
goto out_unlock;
/*
* 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 (iattr->ia_size > ip->i_size) {
/*
* 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, iattr->ia_size, ip->i_size);
if (error)
goto out_unlock;
}
xfs_iunlock(ip, XFS_ILOCK_EXCL);
lock_flags &= ~XFS_ILOCK_EXCL;
/*
* 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 (ip->i_size != ip->i_d.di_size && iattr->ia_size > ip->i_d.di_size) {
error = xfs_flush_pages(ip, ip->i_d.di_size, iattr->ia_size,
XBF_ASYNC, FI_NONE);
if (error)
goto out_unlock;
}
/*
* Wait for all I/O to complete.
*/
xfs_ioend_wait(ip);
error = -block_truncate_page(inode->i_mapping, iattr->ia_size,
xfs_get_blocks);
if (error)
goto out_unlock;
tp = xfs_trans_alloc(mp, XFS_TRANS_SETATTR_SIZE);
error = xfs_trans_reserve(tp, 0, XFS_ITRUNCATE_LOG_RES(mp), 0,
XFS_TRANS_PERM_LOG_RES,
XFS_ITRUNCATE_LOG_COUNT);
if (error)
goto out_trans_cancel;
truncate_setsize(inode, iattr->ia_size);
commit_flags = XFS_TRANS_RELEASE_LOG_RES;
lock_flags |= XFS_ILOCK_EXCL;
xfs_ilock(ip, XFS_ILOCK_EXCL);
xfs_trans_ijoin(tp, ip);
/*
* 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 (iattr->ia_size != ip->i_size &&
(!(mask & (ATTR_CTIME | ATTR_MTIME)))) {
iattr->ia_ctime = iattr->ia_mtime =
current_fs_time(inode->i_sb);
mask |= ATTR_CTIME | ATTR_MTIME;
}
if (iattr->ia_size > ip->i_size) {
ip->i_d.di_size = iattr->ia_size;
ip->i_size = iattr->ia_size;
} else if (iattr->ia_size <= ip->i_size ||
(iattr->ia_size == 0 && ip->i_d.di_nextents)) {
error = xfs_itruncate_data(&tp, ip, iattr->ia_size);
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);
}
if (mask & ATTR_CTIME) {
inode->i_ctime = iattr->ia_ctime;
ip->i_d.di_ctime.t_sec = iattr->ia_ctime.tv_sec;
ip->i_d.di_ctime.t_nsec = iattr->ia_ctime.tv_nsec;
ip->i_update_core = 1;
}
if (mask & ATTR_MTIME) {
inode->i_mtime = iattr->ia_mtime;
ip->i_d.di_mtime.t_sec = iattr->ia_mtime.tv_sec;
ip->i_d.di_mtime.t_nsec = iattr->ia_mtime.tv_nsec;
ip->i_update_core = 1;
}
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;
}
/*
* xfs_file_dio_aio_write - handle direct IO writes
*
* Lock the inode appropriately to prepare for and issue a direct IO write.
* By separating it from the buffered write path we remove all the tricky to
* follow locking changes and looping.
*
* If there are cached pages or we're extending the file, we need IOLOCK_EXCL
* until we're sure the bytes at the new EOF have been zeroed and/or the cached
* pages are flushed out.
*
* In most cases the direct IO writes will be done holding IOLOCK_SHARED
* allowing them to be done in parallel with reads and other direct IO writes.
* However, if the IO is not aligned to filesystem blocks, the direct IO layer
* needs to do sub-block zeroing and that requires serialisation against other
* direct IOs to the same block. In this case we need to serialise the
* submission of the unaligned IOs so that we don't get racing block zeroing in
* the dio layer. To avoid the problem with aio, we also need to wait for
* outstanding IOs to complete so that unwritten extent conversion is completed
* before we try to map the overlapping block. This is currently implemented by
* hitting it with a big hammer (i.e. inode_dio_wait()).
*
* Returns with locks held indicated by @iolock and errors indicated by
* negative return values.
*/
STATIC ssize_t
xfs_file_dio_aio_write(
struct kiocb *iocb,
const struct iovec *iovp,
unsigned long nr_segs,
loff_t pos,
size_t ocount)
{
struct file *file = iocb->ki_filp;
struct address_space *mapping = file->f_mapping;
struct inode *inode = mapping->host;
struct xfs_inode *ip = XFS_I(inode);
struct xfs_mount *mp = ip->i_mount;
ssize_t ret = 0;
size_t count = ocount;
int unaligned_io = 0;
int iolock;
struct xfs_buftarg *target = XFS_IS_REALTIME_INODE(ip) ?
mp->m_rtdev_targp : mp->m_ddev_targp;
/* DIO must be aligned to device logical sector size */
if ((pos | count) & target->bt_logical_sectormask)
return -XFS_ERROR(EINVAL);
/* "unaligned" here means not aligned to a filesystem block */
if ((pos & mp->m_blockmask) || ((pos + count) & mp->m_blockmask))
unaligned_io = 1;
/*
* We don't need to take an exclusive lock unless there page cache needs
* to be invalidated or unaligned IO is being executed. We don't need to
* consider the EOF extension case here because
* xfs_file_aio_write_checks() will relock the inode as necessary for
* EOF zeroing cases and fill out the new inode size as appropriate.
*/
if (unaligned_io || mapping->nrpages)
iolock = XFS_IOLOCK_EXCL;
else
iolock = XFS_IOLOCK_SHARED;
xfs_rw_ilock(ip, iolock);
/*
* Recheck if there are cached pages that need invalidate after we got
* the iolock to protect against other threads adding new pages while
* we were waiting for the iolock.
*/
if (mapping->nrpages && iolock == XFS_IOLOCK_SHARED) {
xfs_rw_iunlock(ip, iolock);
iolock = XFS_IOLOCK_EXCL;
xfs_rw_ilock(ip, iolock);
}
ret = xfs_file_aio_write_checks(file, &pos, &count, &iolock);
if (ret)
goto out;
if (mapping->nrpages) {
ret = -filemap_write_and_wait_range(VFS_I(ip)->i_mapping,
pos, -1);
if (ret)
goto out;
truncate_pagecache_range(VFS_I(ip), pos, -1);
}
/*
* If we are doing unaligned IO, wait for all other IO to drain,
* otherwise demote the lock if we had to flush cached pages
*/
if (unaligned_io)
inode_dio_wait(inode);
else if (iolock == XFS_IOLOCK_EXCL) {
xfs_rw_ilock_demote(ip, XFS_IOLOCK_EXCL);
iolock = XFS_IOLOCK_SHARED;
}
trace_xfs_file_direct_write(ip, count, iocb->ki_pos, 0);
ret = generic_file_direct_write(iocb, iovp,
&nr_segs, pos, &iocb->ki_pos, count, ocount);
out:
xfs_rw_iunlock(ip, iolock);
/* No fallback to buffered IO on errors for XFS. */
ASSERT(ret < 0 || ret == count);
return ret;
}
void
libxfs_iprint(
xfs_inode_t *ip)
{
struct xfs_icdinode *dip;
xfs_bmbt_rec_host_t *ep;
xfs_extnum_t i;
xfs_extnum_t nextents;
printf("Inode %lx\n", (unsigned long)ip);
printf(" i_ino %llx\n", (unsigned long long)ip->i_ino);
if (ip->i_df.if_flags & XFS_IFEXTENTS)
printf("EXTENTS ");
printf("\n");
printf(" i_df.if_bytes %d\n", ip->i_df.if_bytes);
printf(" i_df.if_u1.if_extents/if_data %lx\n",
(unsigned long)ip->i_df.if_u1.if_extents);
if (ip->i_df.if_flags & XFS_IFEXTENTS) {
nextents = ip->i_df.if_bytes / (uint)sizeof(*ep);
for (ep = ip->i_df.if_u1.if_extents, i = 0; i < nextents;
i++, ep++) {
xfs_bmbt_irec_t rec;
xfs_bmbt_get_all(ep, &rec);
printf("\t%d: startoff %llu, startblock 0x%llx,"
" blockcount %llu, state %d\n",
i, (unsigned long long)rec.br_startoff,
(unsigned long long)rec.br_startblock,
(unsigned long long)rec.br_blockcount,
(int)rec.br_state);
}
}
printf(" i_df.if_broot %lx\n", (unsigned long)ip->i_df.if_broot);
printf(" i_df.if_broot_bytes %x\n", ip->i_df.if_broot_bytes);
dip = &ip->i_d;
printf("\nOn disk portion\n");
printf(" di_mode %o\n", VFS_I(ip)->i_mode);
printf(" di_version %x\n", (uint)dip->di_version);
switch (ip->i_d.di_format) {
case XFS_DINODE_FMT_LOCAL:
printf(" Inline inode\n");
break;
case XFS_DINODE_FMT_EXTENTS:
printf(" Extents inode\n");
break;
case XFS_DINODE_FMT_BTREE:
printf(" B-tree inode\n");
break;
default:
printf(" Other inode\n");
break;
}
printf(" di_nlink %x\n", VFS_I(ip)->i_nlink);
printf(" di_uid %d\n", dip->di_uid);
printf(" di_gid %d\n", dip->di_gid);
printf(" di_nextents %d\n", dip->di_nextents);
printf(" di_size %llu\n", (unsigned long long)dip->di_size);
printf(" di_gen %x\n", VFS_I(ip)->i_generation);
printf(" di_extsize %d\n", dip->di_extsize);
printf(" di_flags %x\n", dip->di_flags);
printf(" di_nblocks %llu\n", (unsigned long long)dip->di_nblocks);
}
/*
* Inodes in different states need to be treated differently. The following
* table lists the inode states and the reclaim actions necessary:
*
* inode state iflush ret required action
* --------------- ---------- ---------------
* bad - reclaim
* shutdown EIO unpin and reclaim
* clean, unpinned 0 reclaim
* stale, unpinned 0 reclaim
* clean, pinned(*) 0 requeue
* stale, pinned EAGAIN requeue
* dirty, async - requeue
* dirty, sync 0 reclaim
*
* (*) dgc: I don't think the clean, pinned state is possible but it gets
* handled anyway given the order of checks implemented.
*
* Also, because we get the flush lock first, we know that any inode that has
* been flushed delwri has had the flush completed by the time we check that
* the inode is clean.
*
* Note that because the inode is flushed delayed write by AIL pushing, the
* flush lock may already be held here and waiting on it can result in very
* long latencies. Hence for sync reclaims, where we wait on the flush lock,
* the caller should push the AIL first before trying to reclaim inodes to
* minimise the amount of time spent waiting. For background relaim, we only
* bother to reclaim clean inodes anyway.
*
* Hence the order of actions after gaining the locks should be:
* bad => reclaim
* shutdown => unpin and reclaim
* pinned, async => requeue
* pinned, sync => unpin
* stale => reclaim
* clean => reclaim
* dirty, async => requeue
* dirty, sync => flush, wait and reclaim
*/
STATIC int
xfs_reclaim_inode(
struct xfs_inode *ip,
struct xfs_perag *pag,
int sync_mode)
{
struct xfs_buf *bp = NULL;
int error;
restart:
error = 0;
xfs_ilock(ip, XFS_ILOCK_EXCL);
if (!xfs_iflock_nowait(ip)) {
if (!(sync_mode & SYNC_WAIT))
goto out;
xfs_iflock(ip);
}
if (is_bad_inode(VFS_I(ip)))
goto reclaim;
if (XFS_FORCED_SHUTDOWN(ip->i_mount)) {
xfs_iunpin_wait(ip);
xfs_iflush_abort(ip, false);
goto reclaim;
}
if (xfs_ipincount(ip)) {
if (!(sync_mode & SYNC_WAIT))
goto out_ifunlock;
xfs_iunpin_wait(ip);
}
if (xfs_iflags_test(ip, XFS_ISTALE))
goto reclaim;
if (xfs_inode_clean(ip))
goto reclaim;
/*
* Never flush out dirty data during non-blocking reclaim, as it would
* just contend with AIL pushing trying to do the same job.
*/
if (!(sync_mode & SYNC_WAIT))
goto out_ifunlock;
/*
* Now we have an inode that needs flushing.
*
* Note that xfs_iflush will never block on the inode buffer lock, as
* xfs_ifree_cluster() can lock the inode buffer before it locks the
* ip->i_lock, and we are doing the exact opposite here. As a result,
* doing a blocking xfs_imap_to_bp() to get the cluster buffer would
* result in an ABBA deadlock with xfs_ifree_cluster().
*
* As xfs_ifree_cluser() must gather all inodes that are active in the
* cache to mark them stale, if we hit this case we don't actually want
* to do IO here - we want the inode marked stale so we can simply
* reclaim it. Hence if we get an EAGAIN error here, just unlock the
* inode, back off and try again. Hopefully the next pass through will
* see the stale flag set on the inode.
*/
error = xfs_iflush(ip, &bp);
if (error == EAGAIN) {
xfs_iunlock(ip, XFS_ILOCK_EXCL);
/* backoff longer than in xfs_ifree_cluster */
delay(2);
goto restart;
}
if (!error) {
error = xfs_bwrite(bp);
xfs_buf_relse(bp);
}
xfs_iflock(ip);
reclaim:
xfs_ifunlock(ip);
xfs_iunlock(ip, XFS_ILOCK_EXCL);
XFS_STATS_INC(xs_ig_reclaims);
/*
* Remove the inode from the per-AG radix tree.
*
* Because radix_tree_delete won't complain even if the item was never
* added to the tree assert that it's been there before to catch
* problems with the inode life time early on.
*/
spin_lock(&pag->pag_ici_lock);
if (!radix_tree_delete(&pag->pag_ici_root,
XFS_INO_TO_AGINO(ip->i_mount, ip->i_ino)))
ASSERT(0);
__xfs_inode_clear_reclaim(pag, ip);
spin_unlock(&pag->pag_ici_lock);
/*
* Here we do an (almost) spurious inode lock in order to coordinate
* with inode cache radix tree lookups. This is because the lookup
* can reference the inodes in the cache without taking references.
*
* We make that OK here by ensuring that we wait until the inode is
* unlocked after the lookup before we go ahead and free it.
*/
xfs_ilock(ip, XFS_ILOCK_EXCL);
xfs_qm_dqdetach(ip);
xfs_iunlock(ip, XFS_ILOCK_EXCL);
xfs_inode_free(ip);
return error;
out_ifunlock:
xfs_ifunlock(ip);
out:
xfs_iflags_clear(ip, XFS_IRECLAIM);
xfs_iunlock(ip, XFS_ILOCK_EXCL);
/*
* We could return EAGAIN here to make reclaim rescan the inode tree in
* a short while. However, this just burns CPU time scanning the tree
* waiting for IO to complete and the reclaim work never goes back to
* the idle state. Instead, return 0 to let the next scheduled
* background reclaim attempt to reclaim the inode again.
*/
return 0;
}
/*
* Look up an inode by number in the given file system.
* The inode is looked up in the cache held in each AG.
* If the inode is found in the cache, initialise the vfs inode
* if necessary.
*
* If it is not in core, read it in from the file system's device,
* add it to the cache and initialise the vfs inode.
*
* The inode is locked according to the value of the lock_flags parameter.
* This flag parameter indicates how and if the inode's IO lock and inode lock
* should be taken.
*
* mp -- the mount point structure for the current file system. It points
* to the inode hash table.
* tp -- a pointer to the current transaction if there is one. This is
* simply passed through to the xfs_iread() call.
* ino -- the number of the inode desired. This is the unique identifier
* within the file system for the inode being requested.
* lock_flags -- flags indicating how to lock the inode. See the comment
* for xfs_ilock() for a list of valid values.
*/
int
xfs_iget(
xfs_mount_t *mp,
xfs_trans_t *tp,
xfs_ino_t ino,
uint flags,
uint lock_flags,
xfs_inode_t **ipp)
{
xfs_inode_t *ip;
int error;
xfs_perag_t *pag;
xfs_agino_t agino;
/*
* xfs_reclaim_inode() uses the ILOCK to ensure an inode
* doesn't get freed while it's being referenced during a
* radix tree traversal here. It assumes this function
* aqcuires only the ILOCK (and therefore it has no need to
* involve the IOLOCK in this synchronization).
*/
ASSERT((lock_flags & (XFS_IOLOCK_EXCL | XFS_IOLOCK_SHARED)) == 0);
/* reject inode numbers outside existing AGs */
if (!ino || XFS_INO_TO_AGNO(mp, ino) >= mp->m_sb.sb_agcount)
return -EINVAL;
XFS_STATS_INC(mp, xs_ig_attempts);
/* get the perag structure and ensure that it's inode capable */
pag = xfs_perag_get(mp, XFS_INO_TO_AGNO(mp, ino));
agino = XFS_INO_TO_AGINO(mp, ino);
again:
error = 0;
rcu_read_lock();
ip = radix_tree_lookup(&pag->pag_ici_root, agino);
if (ip) {
error = xfs_iget_cache_hit(pag, ip, ino, flags, lock_flags);
if (error)
goto out_error_or_again;
} else {
rcu_read_unlock();
if (flags & XFS_IGET_INCORE) {
error = -ENOENT;
goto out_error_or_again;
}
XFS_STATS_INC(mp, xs_ig_missed);
error = xfs_iget_cache_miss(mp, pag, tp, ino, &ip,
flags, lock_flags);
if (error)
goto out_error_or_again;
}
xfs_perag_put(pag);
*ipp = ip;
/*
* If we have a real type for an on-disk inode, we can setup the inode
* now. If it's a new inode being created, xfs_ialloc will handle it.
*/
if (xfs_iflags_test(ip, XFS_INEW) && VFS_I(ip)->i_mode != 0)
xfs_setup_existing_inode(ip);
return 0;
out_error_or_again:
if (!(flags & XFS_IGET_INCORE) && error == -EAGAIN) {
delay(1);
goto again;
}
xfs_perag_put(pag);
return error;
}
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 *pdqp = 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, NULL, &pdqp);
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, &M_RES(mp)->tr_ichange, 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 (!inode_owner_or_capable(VFS_I(ip))) {
code = XFS_ERROR(EPERM);
goto error_return;
}
/*
* Do a quota reservation only if projid is actually going to change.
* Only allow changing of projid from init_user_ns since it is a
* non user namespace aware identifier.
*/
if (mask & FSX_PROJID) {
if (current_user_ns() != &init_user_ns) {
code = XFS_ERROR(EINVAL);
goto error_return;
}
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, NULL,
pdqp, 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)) &&
!inode_capable(VFS_I(ip), 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_pdquot, pdqp);
}
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(pdqp);
return code;
error_return:
xfs_qm_dqrele(udqp);
xfs_qm_dqrele(pdqp);
xfs_trans_cancel(tp, 0);
if (lock_flags)
xfs_iunlock(ip, lock_flags);
return code;
}
static 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;
}
if (VN_CACHED(VFS_I(tip)) != 0) {
error = xfs_flushinval_pages(tip, 0, -1,
FI_REMAPF_LOCKED);
if (error)
goto out_unlock;
}
/* 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.
*/
xfs_tosspages(ip, 0, -1, FI_REMAPF);
tp = xfs_trans_alloc(mp, XFS_TRANS_SWAPEXT);
if ((error = xfs_trans_reserve(tp, 0,
XFS_ICHANGE_LOG_RES(mp), 0,
0, 0))) {
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;
}
/*
* 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;
src_log_flags = XFS_ILOG_CORE;
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:
src_log_flags |= XFS_ILOG_DBROOT;
break;
}
target_log_flags = XFS_ILOG_CORE;
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;
break;
}
xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL | XFS_IOLOCK_EXCL);
xfs_trans_ijoin(tp, tip, XFS_ILOCK_EXCL | XFS_IOLOCK_EXCL);
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;
}
STATIC ssize_t
xfs_file_read_iter(
struct kiocb *iocb,
struct iov_iter *to)
{
struct file *file = iocb->ki_filp;
struct inode *inode = file->f_mapping->host;
struct xfs_inode *ip = XFS_I(inode);
struct xfs_mount *mp = ip->i_mount;
size_t size = iov_iter_count(to);
ssize_t ret = 0;
int ioflags = 0;
xfs_fsize_t n;
loff_t pos = iocb->ki_pos;
XFS_STATS_INC(mp, xs_read_calls);
if (unlikely(iocb->ki_flags & IOCB_DIRECT))
ioflags |= XFS_IO_ISDIRECT;
if (file->f_mode & FMODE_NOCMTIME)
ioflags |= XFS_IO_INVIS;
if ((ioflags & XFS_IO_ISDIRECT) && !IS_DAX(inode)) {
xfs_buftarg_t *target =
XFS_IS_REALTIME_INODE(ip) ?
mp->m_rtdev_targp : mp->m_ddev_targp;
/* DIO must be aligned to device logical sector size */
if ((pos | size) & target->bt_logical_sectormask) {
if (pos == i_size_read(inode))
return 0;
return -EINVAL;
}
}
n = mp->m_super->s_maxbytes - pos;
if (n <= 0 || size == 0)
return 0;
if (n < size)
size = n;
if (XFS_FORCED_SHUTDOWN(mp))
return -EIO;
/*
* Locking is a bit tricky here. If we take an exclusive lock for direct
* IO, we effectively serialise all new concurrent read IO to this file
* and block it behind IO that is currently in progress because IO in
* progress holds the IO lock shared. We only need to hold the lock
* exclusive to blow away the page cache, so only take lock exclusively
* if the page cache needs invalidation. This allows the normal direct
* IO case of no page cache pages to proceeed concurrently without
* serialisation.
*/
xfs_rw_ilock(ip, XFS_IOLOCK_SHARED);
if ((ioflags & XFS_IO_ISDIRECT) && inode->i_mapping->nrpages) {
xfs_rw_iunlock(ip, XFS_IOLOCK_SHARED);
xfs_rw_ilock(ip, XFS_IOLOCK_EXCL);
/*
* The generic dio code only flushes the range of the particular
* I/O. Because we take an exclusive lock here, this whole
* sequence is considerably more expensive for us. This has a
* noticeable performance impact for any file with cached pages,
* even when outside of the range of the particular I/O.
*
* Hence, amortize the cost of the lock against a full file
* flush and reduce the chances of repeated iolock cycles going
* forward.
*/
if (inode->i_mapping->nrpages) {
ret = filemap_write_and_wait(VFS_I(ip)->i_mapping);
if (ret) {
xfs_rw_iunlock(ip, XFS_IOLOCK_EXCL);
return ret;
}
/*
* Invalidate whole pages. This can return an error if
* we fail to invalidate a page, but this should never
* happen on XFS. Warn if it does fail.
*/
ret = invalidate_inode_pages2(VFS_I(ip)->i_mapping);
WARN_ON_ONCE(ret);
ret = 0;
}
xfs_rw_ilock_demote(ip, XFS_IOLOCK_EXCL);
}
trace_xfs_file_read(ip, size, pos, ioflags);
ret = generic_file_read_iter(iocb, to);
if (ret > 0)
XFS_STATS_ADD(mp, xs_read_bytes, ret);
xfs_rw_iunlock(ip, XFS_IOLOCK_SHARED);
return ret;
}
