STATIC int
xfs_file_fsync(
struct file *file,
loff_t start,
loff_t end,
int datasync)
{
struct inode *inode = file->f_mapping->host;
struct xfs_inode *ip = XFS_I(inode);
struct xfs_mount *mp = ip->i_mount;
int error = 0;
int log_flushed = 0;
xfs_lsn_t lsn = 0;
trace_xfs_file_fsync(ip);
error = filemap_write_and_wait_range(inode->i_mapping, start, end);
if (error)
return error;
if (XFS_FORCED_SHUTDOWN(mp))
return -XFS_ERROR(EIO);
xfs_iflags_clear(ip, XFS_ITRUNCATED);
if (mp->m_flags & XFS_MOUNT_BARRIER) {
/*
* If we have an RT and/or log subvolume we need to make sure
* to flush the write cache the device used for file data
* first. This is to ensure newly written file data make
* it to disk before logging the new inode size in case of
* an extending write.
*/
if (XFS_IS_REALTIME_INODE(ip))
xfs_blkdev_issue_flush(mp->m_rtdev_targp);
else if (mp->m_logdev_targp != mp->m_ddev_targp)
xfs_blkdev_issue_flush(mp->m_ddev_targp);
}
xfs_ilock(ip, XFS_ILOCK_SHARED);
if (xfs_ipincount(ip)) {
if (!datasync ||
(ip->i_itemp->ili_fields & ~XFS_ILOG_TIMESTAMP))
lsn = ip->i_itemp->ili_last_lsn;
}
xfs_iunlock(ip, XFS_ILOCK_SHARED);
if (lsn)
error = _xfs_log_force_lsn(mp, lsn, XFS_LOG_SYNC, &log_flushed);
if ((mp->m_flags & XFS_MOUNT_BARRIER) &&
mp->m_logdev_targp == mp->m_ddev_targp &&
!XFS_IS_REALTIME_INODE(ip) &&
!log_flushed)
xfs_blkdev_issue_flush(mp->m_ddev_targp);
return -error;
}
static xfs_daddr_t
xfs_fsb_to_db(struct xfs_inode *ip, xfs_fsblock_t fsb)
{
if (XFS_IS_REALTIME_INODE(ip))
return XFS_FSB_TO_BB(ip->i_mount, fsb);
return XFS_FSB_TO_DADDR(ip->i_mount, (fsb));
}
/*
* Convert the given file system block to a disk block. We have to treat it
* differently based on whether the file is a real time file or not, because the
* bmap code does.
*/
xfs_daddr_t
xfs_fsb_to_db(struct xfs_inode *ip, xfs_fsblock_t fsb)
{
return (XFS_IS_REALTIME_INODE(ip) ? \
(xfs_daddr_t)XFS_FSB_TO_BB((ip)->i_mount, (fsb)) : \
XFS_FSB_TO_DADDR((ip)->i_mount, (fsb)));
}
/*
* Actually transfer ownership, and do dquot modifications.
* These were already reserved.
*/
xfs_dquot_t *
xfs_qm_vop_chown(
xfs_trans_t *tp,
xfs_inode_t *ip,
xfs_dquot_t **IO_olddq,
xfs_dquot_t *newdq)
{
xfs_dquot_t *prevdq;
uint bfield = XFS_IS_REALTIME_INODE(ip) ?
XFS_TRANS_DQ_RTBCOUNT : XFS_TRANS_DQ_BCOUNT;
ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
ASSERT(XFS_IS_QUOTA_RUNNING(ip->i_mount));
/* old dquot */
prevdq = *IO_olddq;
ASSERT(prevdq);
ASSERT(prevdq != newdq);
xfs_trans_mod_dquot(tp, prevdq, bfield, -(ip->i_d.di_nblocks));
xfs_trans_mod_dquot(tp, prevdq, XFS_TRANS_DQ_ICOUNT, -1);
/* the sparkling new dquot */
xfs_trans_mod_dquot(tp, newdq, bfield, ip->i_d.di_nblocks);
xfs_trans_mod_dquot(tp, newdq, XFS_TRANS_DQ_ICOUNT, 1);
/*
* Take an extra reference, because the inode is going to keep
* this dquot pointer even after the trans_commit.
*/
*IO_olddq = xfs_qm_dqhold(newdq);
return prevdq;
}
STATIC int
xfs_vn_getattr(
struct vfsmount *mnt,
struct dentry *dentry,
struct kstat *stat)
{
struct inode *inode = dentry->d_inode;
struct xfs_inode *ip = XFS_I(inode);
struct xfs_mount *mp = ip->i_mount;
xfs_itrace_entry(ip);
if (XFS_FORCED_SHUTDOWN(mp))
return XFS_ERROR(EIO);
stat->size = XFS_ISIZE(ip);
stat->dev = inode->i_sb->s_dev;
stat->mode = ip->i_d.di_mode;
stat->nlink = ip->i_d.di_nlink;
stat->uid = ip->i_d.di_uid;
stat->gid = ip->i_d.di_gid;
stat->ino = ip->i_ino;
#if XFS_BIG_INUMS
stat->ino += mp->m_inoadd;
#endif
stat->atime = inode->i_atime;
stat->mtime.tv_sec = ip->i_d.di_mtime.t_sec;
stat->mtime.tv_nsec = ip->i_d.di_mtime.t_nsec;
stat->ctime.tv_sec = ip->i_d.di_ctime.t_sec;
stat->ctime.tv_nsec = ip->i_d.di_ctime.t_nsec;
stat->blocks =
XFS_FSB_TO_BB(mp, ip->i_d.di_nblocks + ip->i_delayed_blks);
switch (inode->i_mode & S_IFMT) {
case S_IFBLK:
case S_IFCHR:
stat->blksize = BLKDEV_IOSIZE;
stat->rdev = MKDEV(sysv_major(ip->i_df.if_u2.if_rdev) & 0x1ff,
sysv_minor(ip->i_df.if_u2.if_rdev));
break;
default:
if (XFS_IS_REALTIME_INODE(ip)) {
/*
* If the file blocks are being allocated from a
* realtime volume, then return the inode's realtime
* extent size or the realtime volume's extent size.
*/
stat->blksize =
xfs_get_extsz_hint(ip) << mp->m_sb.sb_blocklog;
} else
stat->blksize = xfs_preferred_iosize(mp);
stat->rdev = 0;
break;
}
return 0;
}
static struct xfs_buftarg *
xfs_find_bdev_for_inode(
struct xfs_inode *ip)
{
struct xfs_mount *mp = ip->i_mount;
if (XFS_IS_REALTIME_INODE(ip))
return mp->m_rtdev_targp;
return mp->m_ddev_targp;
}
/*
* helper function to extract extent size hint from inode
*/
xfs_extlen_t
xfs_get_extsz_hint(
struct xfs_inode *ip)
{
if ((ip->i_d.di_flags & XFS_DIFLAG_EXTSIZE) && ip->i_d.di_extsize)
return ip->i_d.di_extsize;
if (XFS_IS_REALTIME_INODE(ip))
return ip->i_mount->m_sb.sb_rextsize;
return 0;
}
STATIC struct block_device *
xfs_find_bdev_for_inode(
struct inode *inode)
{
struct xfs_inode *ip = XFS_I(inode);
struct xfs_mount *mp = ip->i_mount;
if (XFS_IS_REALTIME_INODE(ip))
return mp->m_rtdev_targp->bt_bdev;
else
return mp->m_ddev_targp->bt_bdev;
}
STATIC int
xfs_iomap_eof_align_last_fsb(
xfs_mount_t *mp,
xfs_inode_t *ip,
xfs_extlen_t extsize,
xfs_fileoff_t *last_fsb)
{
xfs_fileoff_t new_last_fsb = 0;
xfs_extlen_t align;
int eof, error;
if (XFS_IS_REALTIME_INODE(ip))
;
/*
* If mounted with the "-o swalloc" option, roundup the allocation
* request to a stripe width boundary if the file size is >=
* stripe width and we are allocating past the allocation eof.
*/
else if (mp->m_swidth && (mp->m_flags & XFS_MOUNT_SWALLOC) &&
(ip->i_size >= XFS_FSB_TO_B(mp, mp->m_swidth)))
new_last_fsb = roundup_64(*last_fsb, mp->m_swidth);
/*
* Roundup the allocation request to a stripe unit (m_dalign) boundary
* if the file size is >= stripe unit size, and we are allocating past
* the allocation eof.
*/
else if (mp->m_dalign && (ip->i_size >= XFS_FSB_TO_B(mp, mp->m_dalign)))
new_last_fsb = roundup_64(*last_fsb, mp->m_dalign);
/*
* Always round up the allocation request to an extent boundary
* (when file on a real-time subvolume or has di_extsize hint).
*/
if (extsize) {
if (new_last_fsb)
align = roundup_64(new_last_fsb, extsize);
else
align = extsize;
new_last_fsb = roundup_64(*last_fsb, align);
}
if (new_last_fsb) {
error = xfs_bmap_eof(ip, new_last_fsb, XFS_DATA_FORK, &eof);
if (error)
return error;
if (eof)
*last_fsb = new_last_fsb;
}
return 0;
}
STATIC int
xfs_vn_getattr(
struct vfsmount *mnt,
struct dentry *dentry,
struct kstat *stat)
{
struct inode *inode = dentry->d_inode;
struct xfs_inode *ip = XFS_I(inode);
struct xfs_mount *mp = ip->i_mount;
trace_xfs_getattr(ip);
if (XFS_FORCED_SHUTDOWN(mp))
return -XFS_ERROR(EIO);
stat->size = XFS_ISIZE(ip);
stat->dev = inode->i_sb->s_dev;
stat->mode = ip->i_d.di_mode;
stat->nlink = ip->i_d.di_nlink;
stat->uid = ip->i_d.di_uid;
stat->gid = ip->i_d.di_gid;
stat->ino = ip->i_ino;
stat->atime = inode->i_atime;
stat->mtime = inode->i_mtime;
stat->ctime = inode->i_ctime;
stat->blocks =
XFS_FSB_TO_BB(mp, ip->i_d.di_nblocks + ip->i_delayed_blks);
switch (inode->i_mode & S_IFMT) {
case S_IFBLK:
case S_IFCHR:
stat->blksize = BLKDEV_IOSIZE;
stat->rdev = MKDEV(sysv_major(ip->i_df.if_u2.if_rdev) & 0x1ff,
sysv_minor(ip->i_df.if_u2.if_rdev));
break;
default:
if (XFS_IS_REALTIME_INODE(ip)) {
stat->blksize =
xfs_get_extsz_hint(ip) << mp->m_sb.sb_blocklog;
} else
stat->blksize = xfs_preferred_iosize(mp);
stat->rdev = 0;
break;
}
return 0;
}
/*
* helper function to extract extent size hint from inode
*/
xfs_extlen_t
xfs_get_extsz_hint(
struct xfs_inode *ip)
{
xfs_extlen_t extsz;
if (unlikely(XFS_IS_REALTIME_INODE(ip))) {
extsz = (ip->i_d.di_flags & XFS_DIFLAG_EXTSIZE)
? ip->i_d.di_extsize
: ip->i_mount->m_sb.sb_rextsize;
ASSERT(extsz);
} else {
extsz = (ip->i_d.di_flags & XFS_DIFLAG_EXTSIZE)
? ip->i_d.di_extsize : 0;
}
return extsz;
}
STATIC int
xfs_imap_to_bmap(
xfs_inode_t *ip,
xfs_off_t offset,
xfs_bmbt_irec_t *imap,
xfs_iomap_t *iomapp,
int imaps, /* Number of imap entries */
int iomaps, /* Number of iomap entries */
int flags)
{
xfs_mount_t *mp = ip->i_mount;
int pbm;
xfs_fsblock_t start_block;
for (pbm = 0; imaps && pbm < iomaps; imaps--, iomapp++, imap++, pbm++) {
iomapp->iomap_offset = XFS_FSB_TO_B(mp, imap->br_startoff);
iomapp->iomap_delta = offset - iomapp->iomap_offset;
iomapp->iomap_bsize = XFS_FSB_TO_B(mp, imap->br_blockcount);
iomapp->iomap_flags = flags;
if (XFS_IS_REALTIME_INODE(ip)) {
iomapp->iomap_flags |= IOMAP_REALTIME;
iomapp->iomap_target = mp->m_rtdev_targp;
} else {
iomapp->iomap_target = mp->m_ddev_targp;
}
start_block = imap->br_startblock;
if (start_block == HOLESTARTBLOCK) {
iomapp->iomap_bn = IOMAP_DADDR_NULL;
iomapp->iomap_flags |= IOMAP_HOLE;
} else if (start_block == DELAYSTARTBLOCK) {
iomapp->iomap_bn = IOMAP_DADDR_NULL;
iomapp->iomap_flags |= IOMAP_DELAY;
} else {
iomapp->iomap_bn = xfs_fsb_to_db(ip, start_block);
if (ISUNWRITTEN(imap))
iomapp->iomap_flags |= IOMAP_UNWRITTEN;
}
offset += iomapp->iomap_bsize - iomapp->iomap_delta;
}
return pbm; /* Return the number filled */
}
static int
xfs_ioctl_setattr_xflags(
struct xfs_trans *tp,
struct xfs_inode *ip,
struct fsxattr *fa)
{
struct xfs_mount *mp = ip->i_mount;
/* Can't change realtime flag if any extents are allocated. */
if ((ip->i_d.di_nextents || ip->i_delayed_blks) &&
XFS_IS_REALTIME_INODE(ip) != (fa->fsx_xflags & FS_XFLAG_REALTIME))
return -EINVAL;
/* If realtime flag is set then must have realtime device */
if (fa->fsx_xflags & FS_XFLAG_REALTIME) {
if (mp->m_sb.sb_rblocks == 0 || mp->m_sb.sb_rextsize == 0 ||
(ip->i_d.di_extsize % mp->m_sb.sb_rextsize))
return -EINVAL;
}
/* Clear reflink if we are actually able to set the rt flag. */
if ((fa->fsx_xflags & FS_XFLAG_REALTIME) && xfs_is_reflink_inode(ip))
ip->i_d.di_flags2 &= ~XFS_DIFLAG2_REFLINK;
/* Don't allow us to set DAX mode for a reflinked file for now. */
if ((fa->fsx_xflags & FS_XFLAG_DAX) && xfs_is_reflink_inode(ip))
return -EINVAL;
/*
* Can't modify an immutable/append-only file unless
* we have appropriate permission.
*/
if (((ip->i_d.di_flags & (XFS_DIFLAG_IMMUTABLE | XFS_DIFLAG_APPEND)) ||
(fa->fsx_xflags & (FS_XFLAG_IMMUTABLE | FS_XFLAG_APPEND))) &&
!capable(CAP_LINUX_IMMUTABLE))
return -EPERM;
xfs_set_diflags(ip, fa->fsx_xflags);
xfs_diflags_to_linux(ip);
xfs_trans_ichgtime(tp, ip, XFS_ICHGTIME_CHG);
xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
XFS_STATS_INC(mp, xs_ig_attrchg);
return 0;
}
/*
* extent size hint validation is somewhat cumbersome. Rules are:
*
* 1. extent size hint is only valid for directories and regular files
* 2. XFS_XFLAG_EXTSIZE is only valid for regular files
* 3. XFS_XFLAG_EXTSZINHERIT is only valid for directories.
* 4. can only be changed on regular files if no extents are allocated
* 5. can be changed on directories at any time
* 6. extsize hint of 0 turns off hints, clears inode flags.
* 7. Extent size must be a multiple of the appropriate block size.
* 8. for non-realtime files, the extent size hint must be limited
* to half the AG size to avoid alignment extending the extent beyond the
* limits of the AG.
*/
static int
xfs_ioctl_setattr_check_extsize(
struct xfs_inode *ip,
struct fsxattr *fa)
{
struct xfs_mount *mp = ip->i_mount;
if ((fa->fsx_xflags & XFS_XFLAG_EXTSIZE) && !S_ISREG(ip->i_d.di_mode))
return -EINVAL;
if ((fa->fsx_xflags & XFS_XFLAG_EXTSZINHERIT) &&
!S_ISDIR(ip->i_d.di_mode))
return -EINVAL;
if (S_ISREG(ip->i_d.di_mode) && ip->i_d.di_nextents &&
((ip->i_d.di_extsize << mp->m_sb.sb_blocklog) != fa->fsx_extsize))
return -EINVAL;
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)
return -EINVAL;
if (XFS_IS_REALTIME_INODE(ip) ||
(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)
return -EINVAL;
}
if (fa->fsx_extsize % size)
return -EINVAL;
} else
fa->fsx_xflags &= ~(XFS_XFLAG_EXTSIZE | XFS_XFLAG_EXTSZINHERIT);
return 0;
}
STATIC int
xfs_qm_get_rtblks(
xfs_inode_t *ip,
xfs_qcnt_t *O_rtblks)
{
xfs_filblks_t rtblks; /* total rt blks */
xfs_extnum_t idx; /* extent record index */
xfs_ifork_t *ifp; /* inode fork pointer */
xfs_extnum_t nextents; /* number of extent entries */
int error;
ASSERT(XFS_IS_REALTIME_INODE(ip));
ifp = XFS_IFORK_PTR(ip, XFS_DATA_FORK);
if (!(ifp->if_flags & XFS_IFEXTENTS)) {
if ((error = xfs_iread_extents(NULL, ip, XFS_DATA_FORK)))
return error;
}
rtblks = 0;
nextents = ifp->if_bytes / (uint)sizeof(xfs_bmbt_rec_t);
for (idx = 0; idx < nextents; idx++)
rtblks += xfs_bmbt_get_blockcount(xfs_iext_get_ext(ifp, idx));
*O_rtblks = (xfs_qcnt_t)rtblks;
return 0;
}
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(xs_read_calls);
if (unlikely(file->f_flags & O_DIRECT))
ioflags |= XFS_IO_ISDIRECT;
if (file->f_mode & FMODE_NOCMTIME)
ioflags |= XFS_IO_INVIS;
if (unlikely(ioflags & XFS_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 -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);
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;
}
/*
* 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);
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 ((iocb->ki_pos | count) & target->bt_logical_sectormask)
return -EINVAL;
/*
* Don't take the exclusive iolock here unless the I/O is unaligned to
* the file system block size. 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 ((iocb->ki_pos & mp->m_blockmask) ||
((iocb->ki_pos + count) & mp->m_blockmask)) {
unaligned_io = 1;
/*
* We can't properly handle unaligned direct I/O to reflink
* files yet, as we can't unshare a partial block.
*/
if (xfs_is_reflink_inode(ip)) {
trace_xfs_reflink_bounce_dio_write(ip, iocb->ki_pos, count);
return -EREMCHG;
}
iolock = XFS_IOLOCK_EXCL;
} else {
iolock = XFS_IOLOCK_SHARED;
}
if (iocb->ki_flags & IOCB_NOWAIT) {
if (!xfs_ilock_nowait(ip, iolock))
return -EAGAIN;
} else {
xfs_ilock(ip, iolock);
}
ret = xfs_file_aio_write_checks(iocb, from, &iolock);
if (ret)
goto out;
count = iov_iter_count(from);
/*
* If we are doing unaligned IO, wait for all other IO to drain,
* otherwise demote the lock if we had to take the exclusive lock
* for other reasons in xfs_file_aio_write_checks.
*/
if (unaligned_io) {
/* If we are going to wait for other DIO to finish, bail */
if (iocb->ki_flags & IOCB_NOWAIT) {
if (atomic_read(&inode->i_dio_count))
return -EAGAIN;
} else {
inode_dio_wait(inode);
}
} else if (iolock == XFS_IOLOCK_EXCL) {
xfs_ilock_demote(ip, XFS_IOLOCK_EXCL);
iolock = XFS_IOLOCK_SHARED;
}
trace_xfs_file_direct_write(ip, count, iocb->ki_pos);
ret = iomap_dio_rw(iocb, from, &xfs_iomap_ops, xfs_dio_write_end_io);
out:
xfs_iunlock(ip, iolock);
/*
* No fallback to buffered IO on errors for XFS, direct IO will either
* complete fully or fail.
*/
ASSERT(ret < 0 || ret == count);
return ret;
}
STATIC int
xfs_file_fsync(
struct file *file,
loff_t start,
loff_t end,
int datasync)
{
struct inode *inode = file->f_mapping->host;
struct xfs_inode *ip = XFS_I(inode);
struct xfs_mount *mp = ip->i_mount;
int error = 0;
int log_flushed = 0;
xfs_lsn_t lsn = 0;
trace_xfs_file_fsync(ip);
error = file_write_and_wait_range(file, start, end);
if (error)
return error;
if (XFS_FORCED_SHUTDOWN(mp))
return -EIO;
xfs_iflags_clear(ip, XFS_ITRUNCATED);
/*
* If we have an RT and/or log subvolume we need to make sure to flush
* the write cache the device used for file data first. This is to
* ensure newly written file data make it to disk before logging the new
* inode size in case of an extending write.
*/
if (XFS_IS_REALTIME_INODE(ip))
xfs_blkdev_issue_flush(mp->m_rtdev_targp);
else if (mp->m_logdev_targp != mp->m_ddev_targp)
xfs_blkdev_issue_flush(mp->m_ddev_targp);
/*
* All metadata updates are logged, which means that we just have to
* flush the log up to the latest LSN that touched the inode. If we have
* concurrent fsync/fdatasync() calls, we need them to all block on the
* log force before we clear the ili_fsync_fields field. This ensures
* that we don't get a racing sync operation that does not wait for the
* metadata to hit the journal before returning. If we race with
* clearing the ili_fsync_fields, then all that will happen is the log
* force will do nothing as the lsn will already be on disk. We can't
* race with setting ili_fsync_fields because that is done under
* XFS_ILOCK_EXCL, and that can't happen because we hold the lock shared
* until after the ili_fsync_fields is cleared.
*/
xfs_ilock(ip, XFS_ILOCK_SHARED);
if (xfs_ipincount(ip)) {
if (!datasync ||
(ip->i_itemp->ili_fsync_fields & ~XFS_ILOG_TIMESTAMP))
lsn = ip->i_itemp->ili_last_lsn;
}
if (lsn) {
error = _xfs_log_force_lsn(mp, lsn, XFS_LOG_SYNC, &log_flushed);
ip->i_itemp->ili_fsync_fields = 0;
}
xfs_iunlock(ip, XFS_ILOCK_SHARED);
/*
* If we only have a single device, and the log force about was
* a no-op we might have to flush the data device cache here.
* This can only happen for fdatasync/O_DSYNC if we were overwriting
* an already allocated file and thus do not have any metadata to
* commit.
*/
if (!log_flushed && !XFS_IS_REALTIME_INODE(ip) &&
mp->m_logdev_targp == mp->m_ddev_targp)
xfs_blkdev_issue_flush(mp->m_ddev_targp);
return error;
}
STATIC int
xfs_file_fsync(
struct file *file,
struct dentry *dentry,
int datasync)
{
struct xfs_inode *ip = XFS_I(dentry->d_inode);
struct xfs_trans *tp;
int error = 0;
int log_flushed = 0;
xfs_itrace_entry(ip);
if (XFS_FORCED_SHUTDOWN(ip->i_mount))
return -XFS_ERROR(EIO);
xfs_iflags_clear(ip, XFS_ITRUNCATED);
/*
* We always need to make sure that the required inode state is safe on
* disk. The inode might be clean but we still might need to force the
* log because of committed transactions that haven't hit the disk yet.
* Likewise, there could be unflushed non-transactional changes to the
* inode core that have to go to disk and this requires us to issue
* a synchronous transaction to capture these changes correctly.
*
* This code relies on the assumption that if the i_update_core field
* of the inode is clear and the inode is unpinned then it is clean
* and no action is required.
*/
xfs_ilock(ip, XFS_ILOCK_SHARED);
/*
* First check if the VFS inode is marked dirty. All the dirtying
* of non-transactional updates no goes through mark_inode_dirty*,
* which allows us to distinguish beteeen pure timestamp updates
* and i_size updates which need to be caught for fdatasync.
* After that also theck for the dirty state in the XFS inode, which
* might gets cleared when the inode gets written out via the AIL
* or xfs_iflush_cluster.
*/
if (((dentry->d_inode->i_state & I_DIRTY_DATASYNC) ||
((dentry->d_inode->i_state & I_DIRTY_SYNC) && !datasync)) &&
ip->i_update_core) {
/*
* Kick off a transaction to log the inode core to get the
* updates. The sync transaction will also force the log.
*/
xfs_iunlock(ip, XFS_ILOCK_SHARED);
tp = xfs_trans_alloc(ip->i_mount, XFS_TRANS_FSYNC_TS);
error = xfs_trans_reserve(tp, 0,
XFS_FSYNC_TS_LOG_RES(ip->i_mount), 0, 0, 0);
if (error) {
xfs_trans_cancel(tp, 0);
return -error;
}
xfs_ilock(ip, XFS_ILOCK_EXCL);
/*
* Note - it's possible that we might have pushed ourselves out
* of the way during trans_reserve which would flush the inode.
* But there's no guarantee that the inode buffer has actually
* gone out yet (it's delwri). Plus the buffer could be pinned
* anyway if it's part of an inode in another recent
* transaction. So we play it safe and fire off the
* transaction anyway.
*/
xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
xfs_trans_ihold(tp, ip);
xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
xfs_trans_set_sync(tp);
error = _xfs_trans_commit(tp, 0, &log_flushed);
xfs_iunlock(ip, XFS_ILOCK_EXCL);
} else {
/*
* Timestamps/size haven't changed since last inode flush or
* inode transaction commit. That means either nothing got
* written or a transaction committed which caught the updates.
* If the latter happened and the transaction hasn't hit the
* disk yet, the inode will be still be pinned. If it is,
* force the log.
*/
if (xfs_ipincount(ip)) {
error = _xfs_log_force_lsn(ip->i_mount,
ip->i_itemp->ili_last_lsn,
XFS_LOG_SYNC, &log_flushed);
}
xfs_iunlock(ip, XFS_ILOCK_SHARED);
}
if (ip->i_mount->m_flags & XFS_MOUNT_BARRIER) {
/*
* If the log write didn't issue an ordered tag we need
* to flush the disk cache for the data device now.
*/
if (!log_flushed)
xfs_blkdev_issue_flush(ip->i_mount->m_ddev_targp);
/*
* If this inode is on the RT dev we need to flush that
* cache as well.
*/
if (XFS_IS_REALTIME_INODE(ip))
xfs_blkdev_issue_flush(ip->i_mount->m_rtdev_targp);
}
return -error;
}
int
xfs_alloc_file_space(
struct xfs_inode *ip,
xfs_off_t offset,
xfs_off_t len,
int alloc_type)
{
xfs_mount_t *mp = ip->i_mount;
xfs_off_t count;
xfs_filblks_t allocated_fsb;
xfs_filblks_t allocatesize_fsb;
xfs_extlen_t extsz, temp;
xfs_fileoff_t startoffset_fsb;
xfs_fsblock_t firstfsb;
int nimaps;
int quota_flag;
int rt;
xfs_trans_t *tp;
xfs_bmbt_irec_t imaps[1], *imapp;
xfs_bmap_free_t free_list;
uint qblocks, resblks, resrtextents;
int committed;
int error;
trace_xfs_alloc_file_space(ip);
if (XFS_FORCED_SHUTDOWN(mp))
return XFS_ERROR(EIO);
error = xfs_qm_dqattach(ip, 0);
if (error)
return error;
if (len <= 0)
return XFS_ERROR(EINVAL);
rt = XFS_IS_REALTIME_INODE(ip);
extsz = xfs_get_extsz_hint(ip);
count = len;
imapp = &imaps[0];
nimaps = 1;
startoffset_fsb = XFS_B_TO_FSBT(mp, offset);
allocatesize_fsb = XFS_B_TO_FSB(mp, count);
/*
* Allocate file space until done or until there is an error
*/
while (allocatesize_fsb && !error) {
xfs_fileoff_t s, e;
/*
* Determine space reservations for data/realtime.
*/
if (unlikely(extsz)) {
s = startoffset_fsb;
do_div(s, extsz);
s *= extsz;
e = startoffset_fsb + allocatesize_fsb;
if ((temp = do_mod(startoffset_fsb, extsz)))
e += temp;
if ((temp = do_mod(e, extsz)))
e += extsz - temp;
} else {
s = 0;
e = allocatesize_fsb;
}
/*
* The transaction reservation is limited to a 32-bit block
* count, hence we need to limit the number of blocks we are
* trying to reserve to avoid an overflow. We can't allocate
* more than @nimaps extents, and an extent is limited on disk
* to MAXEXTLEN (21 bits), so use that to enforce the limit.
*/
resblks = min_t(xfs_fileoff_t, (e - s), (MAXEXTLEN * nimaps));
if (unlikely(rt)) {
resrtextents = qblocks = resblks;
resrtextents /= mp->m_sb.sb_rextsize;
resblks = XFS_DIOSTRAT_SPACE_RES(mp, 0);
quota_flag = XFS_QMOPT_RES_RTBLKS;
} else {
resrtextents = 0;
resblks = qblocks = XFS_DIOSTRAT_SPACE_RES(mp, resblks);
quota_flag = XFS_QMOPT_RES_REGBLKS;
}
/*
* Allocate and setup the transaction.
*/
tp = xfs_trans_alloc(mp, XFS_TRANS_DIOSTRAT);
error = xfs_trans_reserve(tp, &M_RES(mp)->tr_write,
resblks, resrtextents);
/*
* Check for running out of space
*/
if (error) {
/*
* Free the transaction structure.
*/
ASSERT(error == ENOSPC || XFS_FORCED_SHUTDOWN(mp));
xfs_trans_cancel(tp, 0);
break;
}
xfs_ilock(ip, XFS_ILOCK_EXCL);
error = xfs_trans_reserve_quota_nblks(tp, ip, qblocks,
0, quota_flag);
if (error)
goto error1;
xfs_trans_ijoin(tp, ip, 0);
xfs_bmap_init(&free_list, &firstfsb);
error = xfs_bmapi_write(tp, ip, startoffset_fsb,
allocatesize_fsb, alloc_type, &firstfsb,
0, imapp, &nimaps, &free_list);
if (error) {
goto error0;
}
/*
* Complete the transaction
*/
error = xfs_bmap_finish(&tp, &free_list, &committed);
if (error) {
goto error0;
}
error = xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES);
xfs_iunlock(ip, XFS_ILOCK_EXCL);
if (error) {
break;
}
allocated_fsb = imapp->br_blockcount;
if (nimaps == 0) {
error = XFS_ERROR(ENOSPC);
break;
}
startoffset_fsb += allocated_fsb;
allocatesize_fsb -= allocated_fsb;
}
return error;
error0: /* Cancel bmap, unlock inode, unreserve quota blocks, cancel trans */
xfs_bmap_cancel(&free_list);
xfs_trans_unreserve_quota_nblks(tp, ip, (long)qblocks, 0, quota_flag);
error1: /* Just cancel transaction */
xfs_trans_cancel(tp, XFS_TRANS_RELEASE_LOG_RES | XFS_TRANS_ABORT);
xfs_iunlock(ip, XFS_ILOCK_EXCL);
return error;
}
STATIC ssize_t
xfs_file_aio_read(
struct kiocb *iocb,
const struct iovec *iovp,
unsigned long nr_segs,
loff_t pos)
{
struct file *file = iocb->ki_filp;
struct inode *inode = file->f_mapping->host;
struct xfs_inode *ip = XFS_I(inode);
struct xfs_mount *mp = ip->i_mount;
size_t size = 0;
ssize_t ret = 0;
int ioflags = 0;
xfs_fsize_t n;
XFS_STATS_INC(xs_read_calls);
BUG_ON(iocb->ki_pos != pos);
if (unlikely(file->f_flags & O_DIRECT))
ioflags |= IO_ISDIRECT;
if (file->f_mode & FMODE_NOCMTIME)
ioflags |= IO_INVIS;
ret = generic_segment_checks(iovp, &nr_segs, &size, VERIFY_WRITE);
if (ret < 0)
return ret;
if (unlikely(ioflags & IO_ISDIRECT)) {
xfs_buftarg_t *target =
XFS_IS_REALTIME_INODE(ip) ?
mp->m_rtdev_targp : mp->m_ddev_targp;
if ((iocb->ki_pos & target->bt_smask) ||
(size & target->bt_smask)) {
if (iocb->ki_pos == i_size_read(inode))
return 0;
return -XFS_ERROR(EINVAL);
}
}
n = mp->m_super->s_maxbytes - iocb->ki_pos;
if (n <= 0 || size == 0)
return 0;
if (n < size)
size = n;
if (XFS_FORCED_SHUTDOWN(mp))
return -EIO;
/*
* Locking is a bit tricky here. If we take an exclusive lock
* for direct IO, we effectively serialise all new concurrent
* read IO to this file and block it behind IO that is currently in
* progress because IO in progress holds the IO lock shared. We only
* need to hold the lock exclusive to blow away the page cache, so
* only take lock exclusively if the page cache needs invalidation.
* This allows the normal direct IO case of no page cache pages to
* proceeed concurrently without serialisation.
*/
xfs_rw_ilock(ip, XFS_IOLOCK_SHARED);
if ((ioflags & IO_ISDIRECT) && inode->i_mapping->nrpages) {
xfs_rw_iunlock(ip, XFS_IOLOCK_SHARED);
xfs_rw_ilock(ip, XFS_IOLOCK_EXCL);
if (inode->i_mapping->nrpages) {
ret = -xfs_flushinval_pages(ip,
(iocb->ki_pos & PAGE_CACHE_MASK),
-1, FI_REMAPF_LOCKED);
if (ret) {
xfs_rw_iunlock(ip, XFS_IOLOCK_EXCL);
return ret;
}
}
xfs_rw_ilock_demote(ip, XFS_IOLOCK_EXCL);
}
trace_xfs_file_read(ip, size, iocb->ki_pos, ioflags);
ret = generic_file_aio_read(iocb, iovp, nr_segs, iocb->ki_pos);
if (ret > 0)
XFS_STATS_ADD(xs_read_bytes, ret);
xfs_rw_iunlock(ip, XFS_IOLOCK_SHARED);
return ret;
}
int
xfs_swap_extents(
xfs_inode_t *ip, /* target inode */
xfs_inode_t *tip, /* tmp inode */
xfs_swapext_t *sxp)
{
xfs_mount_t *mp = ip->i_mount;
xfs_trans_t *tp;
xfs_bstat_t *sbp = &sxp->sx_stat;
xfs_ifork_t *tempifp, *ifp, *tifp;
int src_log_flags, target_log_flags;
int error = 0;
int aforkblks = 0;
int taforkblks = 0;
__uint64_t tmp;
tempifp = kmem_alloc(sizeof(xfs_ifork_t), KM_MAYFAIL);
if (!tempifp) {
error = XFS_ERROR(ENOMEM);
goto out;
}
/*
* we have to do two separate lock calls here to keep lockdep
* happy. If we try to get all the locks in one call, lock will
* report false positives when we drop the ILOCK and regain them
* below.
*/
xfs_lock_two_inodes(ip, tip, XFS_IOLOCK_EXCL);
xfs_lock_two_inodes(ip, tip, XFS_ILOCK_EXCL);
/* Verify that both files have the same format */
if ((ip->i_d.di_mode & S_IFMT) != (tip->i_d.di_mode & S_IFMT)) {
error = XFS_ERROR(EINVAL);
goto out_unlock;
}
/* Verify both files are either real-time or non-realtime */
if (XFS_IS_REALTIME_INODE(ip) != XFS_IS_REALTIME_INODE(tip)) {
error = XFS_ERROR(EINVAL);
goto out_unlock;
}
error = -filemap_write_and_wait(VFS_I(tip)->i_mapping);
if (error)
goto out_unlock;
truncate_pagecache_range(VFS_I(tip), 0, -1);
/* Verify O_DIRECT for ftmp */
if (VN_CACHED(VFS_I(tip)) != 0) {
error = XFS_ERROR(EINVAL);
goto out_unlock;
}
/* Verify all data are being swapped */
if (sxp->sx_offset != 0 ||
sxp->sx_length != ip->i_d.di_size ||
sxp->sx_length != tip->i_d.di_size) {
error = XFS_ERROR(EFAULT);
goto out_unlock;
}
trace_xfs_swap_extent_before(ip, 0);
trace_xfs_swap_extent_before(tip, 1);
/* check inode formats now that data is flushed */
error = xfs_swap_extents_check_format(ip, tip);
if (error) {
xfs_notice(mp,
"%s: inode 0x%llx format is incompatible for exchanging.",
__func__, ip->i_ino);
goto out_unlock;
}
/*
* Compare the current change & modify times with that
* passed in. If they differ, we abort this swap.
* This is the mechanism used to ensure the calling
* process that the file was not changed out from
* under it.
*/
if ((sbp->bs_ctime.tv_sec != VFS_I(ip)->i_ctime.tv_sec) ||
(sbp->bs_ctime.tv_nsec != VFS_I(ip)->i_ctime.tv_nsec) ||
(sbp->bs_mtime.tv_sec != VFS_I(ip)->i_mtime.tv_sec) ||
(sbp->bs_mtime.tv_nsec != VFS_I(ip)->i_mtime.tv_nsec)) {
error = XFS_ERROR(EBUSY);
goto out_unlock;
}
/* We need to fail if the file is memory mapped. Once we have tossed
* all existing pages, the page fault will have no option
* but to go to the filesystem for pages. By making the page fault call
* vop_read (or write in the case of autogrow) they block on the iolock
* until we have switched the extents.
*/
if (VN_MAPPED(VFS_I(ip))) {
error = XFS_ERROR(EBUSY);
goto out_unlock;
}
xfs_iunlock(ip, XFS_ILOCK_EXCL);
xfs_iunlock(tip, XFS_ILOCK_EXCL);
/*
* There is a race condition here since we gave up the
* ilock. However, the data fork will not change since
* we have the iolock (locked for truncation too) so we
* are safe. We don't really care if non-io related
* fields change.
*/
truncate_pagecache_range(VFS_I(ip), 0, -1);
tp = xfs_trans_alloc(mp, XFS_TRANS_SWAPEXT);
error = xfs_trans_reserve(tp, &M_RES(mp)->tr_ichange, 0, 0);
if (error) {
xfs_iunlock(ip, XFS_IOLOCK_EXCL);
xfs_iunlock(tip, XFS_IOLOCK_EXCL);
xfs_trans_cancel(tp, 0);
goto out;
}
xfs_lock_two_inodes(ip, tip, XFS_ILOCK_EXCL);
/*
* Count the number of extended attribute blocks
*/
if ( ((XFS_IFORK_Q(ip) != 0) && (ip->i_d.di_anextents > 0)) &&
(ip->i_d.di_aformat != XFS_DINODE_FMT_LOCAL)) {
error = xfs_bmap_count_blocks(tp, ip, XFS_ATTR_FORK, &aforkblks);
if (error)
goto out_trans_cancel;
}
if ( ((XFS_IFORK_Q(tip) != 0) && (tip->i_d.di_anextents > 0)) &&
(tip->i_d.di_aformat != XFS_DINODE_FMT_LOCAL)) {
error = xfs_bmap_count_blocks(tp, tip, XFS_ATTR_FORK,
&taforkblks);
if (error)
goto out_trans_cancel;
}
xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL | XFS_IOLOCK_EXCL);
xfs_trans_ijoin(tp, tip, XFS_ILOCK_EXCL | XFS_IOLOCK_EXCL);
/*
* Before we've swapped the forks, lets set the owners of the forks
* appropriately. We have to do this as we are demand paging the btree
* buffers, and so the validation done on read will expect the owner
* field to be correctly set. Once we change the owners, we can swap the
* inode forks.
*
* Note the trickiness in setting the log flags - we set the owner log
* flag on the opposite inode (i.e. the inode we are setting the new
* owner to be) because once we swap the forks and log that, log
* recovery is going to see the fork as owned by the swapped inode,
* not the pre-swapped inodes.
*/
src_log_flags = XFS_ILOG_CORE;
target_log_flags = XFS_ILOG_CORE;
if (ip->i_d.di_version == 3 &&
ip->i_d.di_format == XFS_DINODE_FMT_BTREE) {
target_log_flags |= XFS_ILOG_DOWNER;
error = xfs_bmbt_change_owner(tp, ip, XFS_DATA_FORK,
tip->i_ino, NULL);
if (error)
goto out_trans_cancel;
}
if (tip->i_d.di_version == 3 &&
tip->i_d.di_format == XFS_DINODE_FMT_BTREE) {
src_log_flags |= XFS_ILOG_DOWNER;
error = xfs_bmbt_change_owner(tp, tip, XFS_DATA_FORK,
ip->i_ino, NULL);
if (error)
goto out_trans_cancel;
}
/*
* Swap the data forks of the inodes
*/
ifp = &ip->i_df;
tifp = &tip->i_df;
*tempifp = *ifp; /* struct copy */
*ifp = *tifp; /* struct copy */
*tifp = *tempifp; /* struct copy */
/*
* Fix the on-disk inode values
*/
tmp = (__uint64_t)ip->i_d.di_nblocks;
ip->i_d.di_nblocks = tip->i_d.di_nblocks - taforkblks + aforkblks;
tip->i_d.di_nblocks = tmp + taforkblks - aforkblks;
tmp = (__uint64_t) ip->i_d.di_nextents;
ip->i_d.di_nextents = tip->i_d.di_nextents;
tip->i_d.di_nextents = tmp;
tmp = (__uint64_t) ip->i_d.di_format;
ip->i_d.di_format = tip->i_d.di_format;
tip->i_d.di_format = tmp;
/*
* The extents in the source inode could still contain speculative
* preallocation beyond EOF (e.g. the file is open but not modified
* while defrag is in progress). In that case, we need to copy over the
* number of delalloc blocks the data fork in the source inode is
* tracking beyond EOF so that when the fork is truncated away when the
* temporary inode is unlinked we don't underrun the i_delayed_blks
* counter on that inode.
*/
ASSERT(tip->i_delayed_blks == 0);
tip->i_delayed_blks = ip->i_delayed_blks;
ip->i_delayed_blks = 0;
switch (ip->i_d.di_format) {
case XFS_DINODE_FMT_EXTENTS:
/* If the extents fit in the inode, fix the
* pointer. Otherwise it's already NULL or
* pointing to the extent.
*/
if (ip->i_d.di_nextents <= XFS_INLINE_EXTS) {
ifp->if_u1.if_extents =
ifp->if_u2.if_inline_ext;
}
src_log_flags |= XFS_ILOG_DEXT;
break;
case XFS_DINODE_FMT_BTREE:
ASSERT(ip->i_d.di_version < 3 ||
(src_log_flags & XFS_ILOG_DOWNER));
src_log_flags |= XFS_ILOG_DBROOT;
break;
}
switch (tip->i_d.di_format) {
case XFS_DINODE_FMT_EXTENTS:
/* If the extents fit in the inode, fix the
* pointer. Otherwise it's already NULL or
* pointing to the extent.
*/
if (tip->i_d.di_nextents <= XFS_INLINE_EXTS) {
tifp->if_u1.if_extents =
tifp->if_u2.if_inline_ext;
}
target_log_flags |= XFS_ILOG_DEXT;
break;
case XFS_DINODE_FMT_BTREE:
target_log_flags |= XFS_ILOG_DBROOT;
ASSERT(tip->i_d.di_version < 3 ||
(target_log_flags & XFS_ILOG_DOWNER));
break;
}
xfs_trans_log_inode(tp, ip, src_log_flags);
xfs_trans_log_inode(tp, tip, target_log_flags);
/*
* If this is a synchronous mount, make sure that the
* transaction goes to disk before returning to the user.
*/
if (mp->m_flags & XFS_MOUNT_WSYNC)
xfs_trans_set_sync(tp);
error = xfs_trans_commit(tp, 0);
trace_xfs_swap_extent_after(ip, 0);
trace_xfs_swap_extent_after(tip, 1);
out:
kmem_free(tempifp);
return error;
out_unlock:
xfs_iunlock(ip, XFS_ILOCK_EXCL | XFS_IOLOCK_EXCL);
xfs_iunlock(tip, XFS_ILOCK_EXCL | XFS_IOLOCK_EXCL);
goto out;
out_trans_cancel:
xfs_trans_cancel(tp, 0);
goto out_unlock;
}
int
xfs_free_file_space(
struct xfs_inode *ip,
xfs_off_t offset,
xfs_off_t len)
{
int committed;
int done;
xfs_fileoff_t endoffset_fsb;
int error;
xfs_fsblock_t firstfsb;
xfs_bmap_free_t free_list;
xfs_bmbt_irec_t imap;
xfs_off_t ioffset;
xfs_extlen_t mod=0;
xfs_mount_t *mp;
int nimap;
uint resblks;
xfs_off_t rounding;
int rt;
xfs_fileoff_t startoffset_fsb;
xfs_trans_t *tp;
mp = ip->i_mount;
trace_xfs_free_file_space(ip);
error = xfs_qm_dqattach(ip, 0);
if (error)
return error;
error = 0;
if (len <= 0) /* if nothing being freed */
return error;
rt = XFS_IS_REALTIME_INODE(ip);
startoffset_fsb = XFS_B_TO_FSB(mp, offset);
endoffset_fsb = XFS_B_TO_FSBT(mp, offset + len);
/* wait for the completion of any pending DIOs */
inode_dio_wait(VFS_I(ip));
rounding = max_t(xfs_off_t, 1 << mp->m_sb.sb_blocklog, PAGE_CACHE_SIZE);
ioffset = offset & ~(rounding - 1);
error = -filemap_write_and_wait_range(VFS_I(ip)->i_mapping,
ioffset, -1);
if (error)
goto out;
truncate_pagecache_range(VFS_I(ip), ioffset, -1);
/*
* Need to zero the stuff we're not freeing, on disk.
* If it's a realtime file & can't use unwritten extents then we
* actually need to zero the extent edges. Otherwise xfs_bunmapi
* will take care of it for us.
*/
if (rt && !xfs_sb_version_hasextflgbit(&mp->m_sb)) {
nimap = 1;
error = xfs_bmapi_read(ip, startoffset_fsb, 1,
&imap, &nimap, 0);
if (error)
goto out;
ASSERT(nimap == 0 || nimap == 1);
if (nimap && imap.br_startblock != HOLESTARTBLOCK) {
xfs_daddr_t block;
ASSERT(imap.br_startblock != DELAYSTARTBLOCK);
block = imap.br_startblock;
mod = do_div(block, mp->m_sb.sb_rextsize);
if (mod)
startoffset_fsb += mp->m_sb.sb_rextsize - mod;
}
nimap = 1;
error = xfs_bmapi_read(ip, endoffset_fsb - 1, 1,
&imap, &nimap, 0);
if (error)
goto out;
ASSERT(nimap == 0 || nimap == 1);
if (nimap && imap.br_startblock != HOLESTARTBLOCK) {
ASSERT(imap.br_startblock != DELAYSTARTBLOCK);
mod++;
if (mod && (mod != mp->m_sb.sb_rextsize))
endoffset_fsb -= mod;
}
}
if ((done = (endoffset_fsb <= startoffset_fsb)))
/*
* One contiguous piece to clear
*/
error = xfs_zero_remaining_bytes(ip, offset, offset + len - 1);
else {
/*
* Some full blocks, possibly two pieces to clear
*/
if (offset < XFS_FSB_TO_B(mp, startoffset_fsb))
error = xfs_zero_remaining_bytes(ip, offset,
XFS_FSB_TO_B(mp, startoffset_fsb) - 1);
if (!error &&
XFS_FSB_TO_B(mp, endoffset_fsb) < offset + len)
error = xfs_zero_remaining_bytes(ip,
XFS_FSB_TO_B(mp, endoffset_fsb),
offset + len - 1);
}
/*
* free file space until done or until there is an error
*/
resblks = XFS_DIOSTRAT_SPACE_RES(mp, 0);
while (!error && !done) {
/*
* allocate and setup the transaction. Allow this
* transaction to dip into the reserve blocks to ensure
* the freeing of the space succeeds at ENOSPC.
*/
tp = xfs_trans_alloc(mp, XFS_TRANS_DIOSTRAT);
tp->t_flags |= XFS_TRANS_RESERVE;
error = xfs_trans_reserve(tp, &M_RES(mp)->tr_write, resblks, 0);
/*
* check for running out of space
*/
if (error) {
/*
* Free the transaction structure.
*/
ASSERT(error == ENOSPC || XFS_FORCED_SHUTDOWN(mp));
xfs_trans_cancel(tp, 0);
break;
}
xfs_ilock(ip, XFS_ILOCK_EXCL);
error = xfs_trans_reserve_quota(tp, mp,
ip->i_udquot, ip->i_gdquot, ip->i_pdquot,
resblks, 0, XFS_QMOPT_RES_REGBLKS);
if (error)
goto error1;
xfs_trans_ijoin(tp, ip, 0);
/*
* issue the bunmapi() call to free the blocks
*/
xfs_bmap_init(&free_list, &firstfsb);
error = xfs_bunmapi(tp, ip, startoffset_fsb,
endoffset_fsb - startoffset_fsb,
0, 2, &firstfsb, &free_list, &done);
if (error) {
goto error0;
}
/*
* complete the transaction
*/
error = xfs_bmap_finish(&tp, &free_list, &committed);
if (error) {
goto error0;
}
error = xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES);
xfs_iunlock(ip, XFS_ILOCK_EXCL);
}
out:
return error;
error0:
xfs_bmap_cancel(&free_list);
error1:
xfs_trans_cancel(tp, XFS_TRANS_RELEASE_LOG_RES | XFS_TRANS_ABORT);
xfs_iunlock(ip, XFS_ILOCK_EXCL);
goto out;
}
/*
* Zero file bytes between startoff and endoff inclusive.
* The iolock is held exclusive and no blocks are buffered.
*
* This function is used by xfs_free_file_space() to zero
* partial blocks when the range to free is not block aligned.
* When unreserving space with boundaries that are not block
* aligned we round up the start and round down the end
* boundaries and then use this function to zero the parts of
* the blocks that got dropped during the rounding.
*/
STATIC int
xfs_zero_remaining_bytes(
xfs_inode_t *ip,
xfs_off_t startoff,
xfs_off_t endoff)
{
xfs_bmbt_irec_t imap;
xfs_fileoff_t offset_fsb;
xfs_off_t lastoffset;
xfs_off_t offset;
xfs_buf_t *bp;
xfs_mount_t *mp = ip->i_mount;
int nimap;
int error = 0;
/*
* Avoid doing I/O beyond eof - it's not necessary
* since nothing can read beyond eof. The space will
* be zeroed when the file is extended anyway.
*/
if (startoff >= XFS_ISIZE(ip))
return 0;
if (endoff > XFS_ISIZE(ip))
endoff = XFS_ISIZE(ip);
bp = xfs_buf_get_uncached(XFS_IS_REALTIME_INODE(ip) ?
mp->m_rtdev_targp : mp->m_ddev_targp,
BTOBB(mp->m_sb.sb_blocksize), 0);
if (!bp)
return XFS_ERROR(ENOMEM);
xfs_buf_unlock(bp);
for (offset = startoff; offset <= endoff; offset = lastoffset + 1) {
uint lock_mode;
offset_fsb = XFS_B_TO_FSBT(mp, offset);
nimap = 1;
lock_mode = xfs_ilock_data_map_shared(ip);
error = xfs_bmapi_read(ip, offset_fsb, 1, &imap, &nimap, 0);
xfs_iunlock(ip, lock_mode);
if (error || nimap < 1)
break;
ASSERT(imap.br_blockcount >= 1);
ASSERT(imap.br_startoff == offset_fsb);
lastoffset = XFS_FSB_TO_B(mp, imap.br_startoff + 1) - 1;
if (lastoffset > endoff)
lastoffset = endoff;
if (imap.br_startblock == HOLESTARTBLOCK)
continue;
ASSERT(imap.br_startblock != DELAYSTARTBLOCK);
if (imap.br_state == XFS_EXT_UNWRITTEN)
continue;
XFS_BUF_UNDONE(bp);
XFS_BUF_UNWRITE(bp);
XFS_BUF_READ(bp);
XFS_BUF_SET_ADDR(bp, xfs_fsb_to_db(ip, imap.br_startblock));
if (XFS_FORCED_SHUTDOWN(mp)) {
error = XFS_ERROR(EIO);
break;
}
xfs_buf_iorequest(bp);
error = xfs_buf_iowait(bp);
if (error) {
xfs_buf_ioerror_alert(bp,
"xfs_zero_remaining_bytes(read)");
break;
}
memset(bp->b_addr +
(offset - XFS_FSB_TO_B(mp, imap.br_startoff)),
0, lastoffset - offset + 1);
XFS_BUF_UNDONE(bp);
XFS_BUF_UNREAD(bp);
XFS_BUF_WRITE(bp);
if (XFS_FORCED_SHUTDOWN(mp)) {
error = XFS_ERROR(EIO);
break;
}
xfs_buf_iorequest(bp);
error = xfs_buf_iowait(bp);
if (error) {
xfs_buf_ioerror_alert(bp,
"xfs_zero_remaining_bytes(write)");
break;
}
}
xfs_buf_free(bp);
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 *gdqp = NULL;
struct xfs_dquot *olddquot = NULL;
int code;
trace_xfs_ioctl_setattr(ip);
if (mp->m_flags & XFS_MOUNT_RDONLY)
return XFS_ERROR(EROFS);
if (XFS_FORCED_SHUTDOWN(mp))
return XFS_ERROR(EIO);
/*
* Disallow 32bit project ids when projid32bit feature is not enabled.
*/
if ((mask & FSX_PROJID) && (fa->fsx_projid > (__uint16_t)-1) &&
!xfs_sb_version_hasprojid32bit(&ip->i_mount->m_sb))
return XFS_ERROR(EINVAL);
/*
* If disk quotas is on, we make sure that the dquots do exist on disk,
* before we start any other transactions. Trying to do this later
* is messy. We don't care to take a readlock to look at the ids
* in inode here, because we can't hold it across the trans_reserve.
* If the IDs do change before we take the ilock, we're covered
* because the i_*dquot fields will get updated anyway.
*/
if (XFS_IS_QUOTA_ON(mp) && (mask & FSX_PROJID)) {
code = xfs_qm_vop_dqalloc(ip, ip->i_d.di_uid,
ip->i_d.di_gid, fa->fsx_projid,
XFS_QMOPT_PQUOTA, &udqp, &gdqp);
if (code)
return code;
}
/*
* For the other attributes, we acquire the inode lock and
* first do an error checking pass.
*/
tp = xfs_trans_alloc(mp, XFS_TRANS_SETATTR_NOT_SIZE);
code = xfs_trans_reserve(tp, 0, XFS_ICHANGE_LOG_RES(mp), 0, 0, 0);
if (code)
goto error_return;
lock_flags = XFS_ILOCK_EXCL;
xfs_ilock(ip, lock_flags);
/*
* CAP_FOWNER overrides the following restrictions:
*
* The user ID of the calling process must be equal
* to the file owner ID, except in cases where the
* CAP_FSETID capability is applicable.
*/
if (current_fsuid() != ip->i_d.di_uid && !capable(CAP_FOWNER)) {
code = XFS_ERROR(EPERM);
goto error_return;
}
/*
* Do a quota reservation only if projid is actually going to change.
*/
if (mask & FSX_PROJID) {
if (XFS_IS_QUOTA_RUNNING(mp) &&
XFS_IS_PQUOTA_ON(mp) &&
xfs_get_projid(ip) != fa->fsx_projid) {
ASSERT(tp);
code = xfs_qm_vop_chown_reserve(tp, ip, udqp, gdqp,
capable(CAP_FOWNER) ?
XFS_QMOPT_FORCE_RES : 0);
if (code) /* out of quota */
goto error_return;
}
}
if (mask & FSX_EXTSIZE) {
/*
* Can't change extent size if any extents are allocated.
*/
if (ip->i_d.di_nextents &&
((ip->i_d.di_extsize << mp->m_sb.sb_blocklog) !=
fa->fsx_extsize)) {
code = XFS_ERROR(EINVAL); /* EFBIG? */
goto error_return;
}
/*
* Extent size must be a multiple of the appropriate block
* size, if set at all. It must also be smaller than the
* maximum extent size supported by the filesystem.
*
* Also, for non-realtime files, limit the extent size hint to
* half the size of the AGs in the filesystem so alignment
* doesn't result in extents larger than an AG.
*/
if (fa->fsx_extsize != 0) {
xfs_extlen_t size;
xfs_fsblock_t extsize_fsb;
extsize_fsb = XFS_B_TO_FSB(mp, fa->fsx_extsize);
if (extsize_fsb > MAXEXTLEN) {
code = XFS_ERROR(EINVAL);
goto error_return;
}
if (XFS_IS_REALTIME_INODE(ip) ||
((mask & FSX_XFLAGS) &&
(fa->fsx_xflags & XFS_XFLAG_REALTIME))) {
size = mp->m_sb.sb_rextsize <<
mp->m_sb.sb_blocklog;
} else {
size = mp->m_sb.sb_blocksize;
if (extsize_fsb > mp->m_sb.sb_agblocks / 2) {
code = XFS_ERROR(EINVAL);
goto error_return;
}
}
if (fa->fsx_extsize % size) {
code = XFS_ERROR(EINVAL);
goto error_return;
}
}
}
if (mask & FSX_XFLAGS) {
/*
* Can't change realtime flag if any extents are allocated.
*/
if ((ip->i_d.di_nextents || ip->i_delayed_blks) &&
(XFS_IS_REALTIME_INODE(ip)) !=
(fa->fsx_xflags & XFS_XFLAG_REALTIME)) {
code = XFS_ERROR(EINVAL); /* EFBIG? */
goto error_return;
}
/*
* If realtime flag is set then must have realtime data.
*/
if ((fa->fsx_xflags & XFS_XFLAG_REALTIME)) {
if ((mp->m_sb.sb_rblocks == 0) ||
(mp->m_sb.sb_rextsize == 0) ||
(ip->i_d.di_extsize % mp->m_sb.sb_rextsize)) {
code = XFS_ERROR(EINVAL);
goto error_return;
}
}
/*
* Can't modify an immutable/append-only file unless
* we have appropriate permission.
*/
if ((ip->i_d.di_flags &
(XFS_DIFLAG_IMMUTABLE|XFS_DIFLAG_APPEND) ||
(fa->fsx_xflags &
(XFS_XFLAG_IMMUTABLE | XFS_XFLAG_APPEND))) &&
!capable(CAP_LINUX_IMMUTABLE)) {
code = XFS_ERROR(EPERM);
goto error_return;
}
}
xfs_trans_ijoin(tp, ip, 0);
/*
* Change file ownership. Must be the owner or privileged.
*/
if (mask & FSX_PROJID) {
/*
* CAP_FSETID overrides the following restrictions:
*
* The set-user-ID and set-group-ID bits of a file will be
* cleared upon successful return from chown()
*/
if ((ip->i_d.di_mode & (S_ISUID|S_ISGID)) &&
!capable(CAP_FSETID))
ip->i_d.di_mode &= ~(S_ISUID|S_ISGID);
/*
* Change the ownerships and register quota modifications
* in the transaction.
*/
if (xfs_get_projid(ip) != fa->fsx_projid) {
if (XFS_IS_QUOTA_RUNNING(mp) && XFS_IS_PQUOTA_ON(mp)) {
olddquot = xfs_qm_vop_chown(tp, ip,
&ip->i_gdquot, gdqp);
}
xfs_set_projid(ip, fa->fsx_projid);
/*
* We may have to rev the inode as well as
* the superblock version number since projids didn't
* exist before DINODE_VERSION_2 and SB_VERSION_NLINK.
*/
if (ip->i_d.di_version == 1)
xfs_bump_ino_vers2(tp, ip);
}
}
if (mask & FSX_EXTSIZE)
ip->i_d.di_extsize = fa->fsx_extsize >> mp->m_sb.sb_blocklog;
if (mask & FSX_XFLAGS) {
xfs_set_diflags(ip, fa->fsx_xflags);
xfs_diflags_to_linux(ip);
}
xfs_trans_ichgtime(tp, ip, XFS_ICHGTIME_CHG);
xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
XFS_STATS_INC(xs_ig_attrchg);
/*
* If this is a synchronous mount, make sure that the
* transaction goes to disk before returning to the user.
* This is slightly sub-optimal in that truncates require
* two sync transactions instead of one for wsync filesystems.
* One for the truncate and one for the timestamps since we
* don't want to change the timestamps unless we're sure the
* truncate worked. Truncates are less than 1% of the laddis
* mix so this probably isn't worth the trouble to optimize.
*/
if (mp->m_flags & XFS_MOUNT_WSYNC)
xfs_trans_set_sync(tp);
code = xfs_trans_commit(tp, 0);
xfs_iunlock(ip, lock_flags);
/*
* Release any dquot(s) the inode had kept before chown.
*/
xfs_qm_dqrele(olddquot);
xfs_qm_dqrele(udqp);
xfs_qm_dqrele(gdqp);
return code;
error_return:
xfs_qm_dqrele(udqp);
xfs_qm_dqrele(gdqp);
xfs_trans_cancel(tp, 0);
if (lock_flags)
xfs_iunlock(ip, lock_flags);
return code;
}
/*
* Note: some of the ioctl's return positive numbers as a
* byte count indicating success, such as readlink_by_handle.
* So we don't "sign flip" like most other routines. This means
* true errors need to be returned as a negative value.
*/
long
xfs_file_ioctl(
struct file *filp,
unsigned int cmd,
unsigned long p)
{
struct inode *inode = file_inode(filp);
struct xfs_inode *ip = XFS_I(inode);
struct xfs_mount *mp = ip->i_mount;
void __user *arg = (void __user *)p;
int ioflags = 0;
int error;
if (filp->f_mode & FMODE_NOCMTIME)
ioflags |= IO_INVIS;
trace_xfs_file_ioctl(ip);
switch (cmd) {
case FITRIM:
return xfs_ioc_trim(mp, arg);
case XFS_IOC_ALLOCSP:
case XFS_IOC_FREESP:
case XFS_IOC_RESVSP:
case XFS_IOC_UNRESVSP:
case XFS_IOC_ALLOCSP64:
case XFS_IOC_FREESP64:
case XFS_IOC_RESVSP64:
case XFS_IOC_UNRESVSP64:
case XFS_IOC_ZERO_RANGE: {
xfs_flock64_t bf;
if (copy_from_user(&bf, arg, sizeof(bf)))
return -XFS_ERROR(EFAULT);
return xfs_ioc_space(ip, inode, filp, ioflags, cmd, &bf);
}
case XFS_IOC_DIOINFO: {
struct dioattr da;
xfs_buftarg_t *target =
XFS_IS_REALTIME_INODE(ip) ?
mp->m_rtdev_targp : mp->m_ddev_targp;
da.d_mem = da.d_miniosz = 1 << target->bt_sshift;
da.d_maxiosz = INT_MAX & ~(da.d_miniosz - 1);
if (copy_to_user(arg, &da, sizeof(da)))
return -XFS_ERROR(EFAULT);
return 0;
}
case XFS_IOC_FSBULKSTAT_SINGLE:
case XFS_IOC_FSBULKSTAT:
case XFS_IOC_FSINUMBERS:
return xfs_ioc_bulkstat(mp, cmd, arg);
case XFS_IOC_FSGEOMETRY_V1:
return xfs_ioc_fsgeometry_v1(mp, arg);
case XFS_IOC_FSGEOMETRY:
return xfs_ioc_fsgeometry(mp, arg);
case XFS_IOC_GETVERSION:
return put_user(inode->i_generation, (int __user *)arg);
case XFS_IOC_FSGETXATTR:
return xfs_ioc_fsgetxattr(ip, 0, arg);
case XFS_IOC_FSGETXATTRA:
return xfs_ioc_fsgetxattr(ip, 1, arg);
case XFS_IOC_FSSETXATTR:
return xfs_ioc_fssetxattr(ip, filp, arg);
case XFS_IOC_GETXFLAGS:
return xfs_ioc_getxflags(ip, arg);
case XFS_IOC_SETXFLAGS:
return xfs_ioc_setxflags(ip, filp, arg);
case XFS_IOC_FSSETDM: {
struct fsdmidata dmi;
if (copy_from_user(&dmi, arg, sizeof(dmi)))
return -XFS_ERROR(EFAULT);
error = mnt_want_write_file(filp);
if (error)
return error;
error = xfs_set_dmattrs(ip, dmi.fsd_dmevmask,
dmi.fsd_dmstate);
mnt_drop_write_file(filp);
return -error;
}
case XFS_IOC_GETBMAP:
case XFS_IOC_GETBMAPA:
return xfs_ioc_getbmap(ip, ioflags, cmd, arg);
case XFS_IOC_GETBMAPX:
return xfs_ioc_getbmapx(ip, arg);
case XFS_IOC_FD_TO_HANDLE:
case XFS_IOC_PATH_TO_HANDLE:
case XFS_IOC_PATH_TO_FSHANDLE: {
xfs_fsop_handlereq_t hreq;
if (copy_from_user(&hreq, arg, sizeof(hreq)))
return -XFS_ERROR(EFAULT);
return xfs_find_handle(cmd, &hreq);
}
case XFS_IOC_OPEN_BY_HANDLE: {
xfs_fsop_handlereq_t hreq;
if (copy_from_user(&hreq, arg, sizeof(xfs_fsop_handlereq_t)))
return -XFS_ERROR(EFAULT);
return xfs_open_by_handle(filp, &hreq);
}
case XFS_IOC_FSSETDM_BY_HANDLE:
return xfs_fssetdm_by_handle(filp, arg);
case XFS_IOC_READLINK_BY_HANDLE: {
xfs_fsop_handlereq_t hreq;
if (copy_from_user(&hreq, arg, sizeof(xfs_fsop_handlereq_t)))
return -XFS_ERROR(EFAULT);
return xfs_readlink_by_handle(filp, &hreq);
}
case XFS_IOC_ATTRLIST_BY_HANDLE:
return xfs_attrlist_by_handle(filp, arg);
case XFS_IOC_ATTRMULTI_BY_HANDLE:
return xfs_attrmulti_by_handle(filp, arg);
case XFS_IOC_SWAPEXT: {
struct xfs_swapext sxp;
if (copy_from_user(&sxp, arg, sizeof(xfs_swapext_t)))
return -XFS_ERROR(EFAULT);
error = mnt_want_write_file(filp);
if (error)
return error;
error = xfs_swapext(&sxp);
mnt_drop_write_file(filp);
return -error;
}
case XFS_IOC_FSCOUNTS: {
xfs_fsop_counts_t out;
error = xfs_fs_counts(mp, &out);
if (error)
return -error;
if (copy_to_user(arg, &out, sizeof(out)))
return -XFS_ERROR(EFAULT);
return 0;
}
case XFS_IOC_SET_RESBLKS: {
xfs_fsop_resblks_t inout;
__uint64_t in;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
if (mp->m_flags & XFS_MOUNT_RDONLY)
return -XFS_ERROR(EROFS);
if (copy_from_user(&inout, arg, sizeof(inout)))
return -XFS_ERROR(EFAULT);
error = mnt_want_write_file(filp);
if (error)
return error;
/* input parameter is passed in resblks field of structure */
in = inout.resblks;
error = xfs_reserve_blocks(mp, &in, &inout);
mnt_drop_write_file(filp);
if (error)
return -error;
if (copy_to_user(arg, &inout, sizeof(inout)))
return -XFS_ERROR(EFAULT);
return 0;
}
case XFS_IOC_GET_RESBLKS: {
xfs_fsop_resblks_t out;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
error = xfs_reserve_blocks(mp, NULL, &out);
if (error)
return -error;
if (copy_to_user(arg, &out, sizeof(out)))
return -XFS_ERROR(EFAULT);
return 0;
}
case XFS_IOC_FSGROWFSDATA: {
xfs_growfs_data_t in;
if (copy_from_user(&in, arg, sizeof(in)))
return -XFS_ERROR(EFAULT);
error = mnt_want_write_file(filp);
if (error)
return error;
error = xfs_growfs_data(mp, &in);
mnt_drop_write_file(filp);
return -error;
}
case XFS_IOC_FSGROWFSLOG: {
xfs_growfs_log_t in;
if (copy_from_user(&in, arg, sizeof(in)))
return -XFS_ERROR(EFAULT);
error = mnt_want_write_file(filp);
if (error)
return error;
error = xfs_growfs_log(mp, &in);
mnt_drop_write_file(filp);
return -error;
}
case XFS_IOC_FSGROWFSRT: {
xfs_growfs_rt_t in;
if (copy_from_user(&in, arg, sizeof(in)))
return -XFS_ERROR(EFAULT);
error = mnt_want_write_file(filp);
if (error)
return error;
error = xfs_growfs_rt(mp, &in);
mnt_drop_write_file(filp);
return -error;
}
case XFS_IOC_GOINGDOWN: {
__uint32_t in;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
if (get_user(in, (__uint32_t __user *)arg))
return -XFS_ERROR(EFAULT);
error = xfs_fs_goingdown(mp, in);
return -error;
}
case XFS_IOC_ERROR_INJECTION: {
xfs_error_injection_t in;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
if (copy_from_user(&in, arg, sizeof(in)))
return -XFS_ERROR(EFAULT);
error = xfs_errortag_add(in.errtag, mp);
return -error;
}
case XFS_IOC_ERROR_CLEARALL:
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
error = xfs_errortag_clearall(mp, 1);
return -error;
case XFS_IOC_FREE_EOFBLOCKS: {
struct xfs_eofblocks eofb;
if (copy_from_user(&eofb, arg, sizeof(eofb)))
return -XFS_ERROR(EFAULT);
if (eofb.eof_version != XFS_EOFBLOCKS_VERSION)
return -XFS_ERROR(EINVAL);
if (eofb.eof_flags & ~XFS_EOF_FLAGS_VALID)
return -XFS_ERROR(EINVAL);
if (memchr_inv(&eofb.pad32, 0, sizeof(eofb.pad32)) ||
memchr_inv(eofb.pad64, 0, sizeof(eofb.pad64)))
return -XFS_ERROR(EINVAL);
error = xfs_icache_free_eofblocks(mp, &eofb);
return -error;
}
default:
return -ENOTTY;
}
}
/*
* xfs_file_dio_aio_write - handle direct IO writes
*
* Lock the inode appropriately to prepare for and issue a direct IO write.
* By separating it from the buffered write path we remove all the tricky to
* follow locking changes and looping.
*
* If there are cached pages or we're extending the file, we need IOLOCK_EXCL
* until we're sure the bytes at the new EOF have been zeroed and/or the cached
* pages are flushed out.
*
* In most cases the direct IO writes will be done holding IOLOCK_SHARED
* allowing them to be done in parallel with reads and other direct IO writes.
* However, if the IO is not aligned to filesystem blocks, the direct IO layer
* needs to do sub-block zeroing and that requires serialisation against other
* direct IOs to the same block. In this case we need to serialise the
* submission of the unaligned IOs so that we don't get racing block zeroing in
* the dio layer. To avoid the problem with aio, we also need to wait for
* outstanding IOs to complete so that unwritten extent conversion is completed
* before we try to map the overlapping block. This is currently implemented by
* hitting it with a big hammer (i.e. inode_dio_wait()).
*
* Returns with locks held indicated by @iolock and errors indicated by
* negative return values.
*/
STATIC ssize_t
xfs_file_dio_aio_write(
struct kiocb *iocb,
const struct iovec *iovp,
unsigned long nr_segs,
loff_t pos,
size_t ocount)
{
struct file *file = iocb->ki_filp;
struct address_space *mapping = file->f_mapping;
struct inode *inode = mapping->host;
struct xfs_inode *ip = XFS_I(inode);
struct xfs_mount *mp = ip->i_mount;
ssize_t ret = 0;
size_t count = ocount;
int unaligned_io = 0;
int iolock;
struct xfs_buftarg *target = XFS_IS_REALTIME_INODE(ip) ?
mp->m_rtdev_targp : mp->m_ddev_targp;
if ((pos & target->bt_smask) || (count & target->bt_smask))
return -XFS_ERROR(EINVAL);
if ((pos & mp->m_blockmask) || ((pos + count) & mp->m_blockmask))
unaligned_io = 1;
/*
* We don't need to take an exclusive lock unless there page cache needs
* to be invalidated or unaligned IO is being executed. We don't need to
* consider the EOF extension case here because
* xfs_file_aio_write_checks() will relock the inode as necessary for
* EOF zeroing cases and fill out the new inode size as appropriate.
*/
if (unaligned_io || mapping->nrpages)
iolock = XFS_IOLOCK_EXCL;
else
iolock = XFS_IOLOCK_SHARED;
xfs_rw_ilock(ip, iolock);
/*
* Recheck if there are cached pages that need invalidate after we got
* the iolock to protect against other threads adding new pages while
* we were waiting for the iolock.
*/
if (mapping->nrpages && iolock == XFS_IOLOCK_SHARED) {
xfs_rw_iunlock(ip, iolock);
iolock = XFS_IOLOCK_EXCL;
xfs_rw_ilock(ip, iolock);
}
ret = xfs_file_aio_write_checks(file, &pos, &count, &iolock);
if (ret)
goto out;
if (mapping->nrpages) {
ret = -xfs_flushinval_pages(ip, (pos & PAGE_CACHE_MASK), -1,
FI_REMAPF_LOCKED);
if (ret)
goto out;
}
/*
* If we are doing unaligned IO, wait for all other IO to drain,
* otherwise demote the lock if we had to flush cached pages
*/
if (unaligned_io)
inode_dio_wait(inode);
else if (iolock == XFS_IOLOCK_EXCL) {
xfs_rw_ilock_demote(ip, XFS_IOLOCK_EXCL);
iolock = XFS_IOLOCK_SHARED;
}
trace_xfs_file_direct_write(ip, count, iocb->ki_pos, 0);
ret = generic_file_direct_write(iocb, iovp,
&nr_segs, pos, &iocb->ki_pos, count, ocount);
out:
xfs_rw_iunlock(ip, iolock);
/* No fallback to buffered IO on errors for XFS. */
ASSERT(ret < 0 || ret == count);
return ret;
}
STATIC int
xfs_file_fsync(
struct file *file,
loff_t start,
loff_t end,
int datasync)
{
struct inode *inode = file->f_mapping->host;
struct xfs_inode *ip = XFS_I(inode);
struct xfs_mount *mp = ip->i_mount;
int error = 0;
int log_flushed = 0;
xfs_lsn_t lsn = 0;
trace_xfs_file_fsync(ip);
error = filemap_write_and_wait_range(inode->i_mapping, start, end);
if (error)
return error;
if (XFS_FORCED_SHUTDOWN(mp))
return -EIO;
xfs_iflags_clear(ip, XFS_ITRUNCATED);
if (mp->m_flags & XFS_MOUNT_BARRIER) {
/*
* If we have an RT and/or log subvolume we need to make sure
* to flush the write cache the device used for file data
* first. This is to ensure newly written file data make
* it to disk before logging the new inode size in case of
* an extending write.
*/
if (XFS_IS_REALTIME_INODE(ip))
xfs_blkdev_issue_flush(mp->m_rtdev_targp);
else if (mp->m_logdev_targp != mp->m_ddev_targp)
xfs_blkdev_issue_flush(mp->m_ddev_targp);
}
/*
* All metadata updates are logged, which means that we just have
* to flush the log up to the latest LSN that touched the inode.
*/
xfs_ilock(ip, XFS_ILOCK_SHARED);
if (xfs_ipincount(ip)) {
if (!datasync ||
(ip->i_itemp->ili_fields & ~XFS_ILOG_TIMESTAMP))
lsn = ip->i_itemp->ili_last_lsn;
}
xfs_iunlock(ip, XFS_ILOCK_SHARED);
if (lsn)
error = _xfs_log_force_lsn(mp, lsn, XFS_LOG_SYNC, &log_flushed);
/*
* If we only have a single device, and the log force about was
* a no-op we might have to flush the data device cache here.
* This can only happen for fdatasync/O_DSYNC if we were overwriting
* an already allocated file and thus do not have any metadata to
* commit.
*/
if ((mp->m_flags & XFS_MOUNT_BARRIER) &&
mp->m_logdev_targp == mp->m_ddev_targp &&
!XFS_IS_REALTIME_INODE(ip) &&
!log_flushed)
xfs_blkdev_issue_flush(mp->m_ddev_targp);
return error;
}
/*
* Quota reservations for setattr(AT_UID|AT_GID|AT_PROJID).
*/
int
xfs_qm_vop_chown_reserve(
xfs_trans_t *tp,
xfs_inode_t *ip,
xfs_dquot_t *udqp,
xfs_dquot_t *gdqp,
uint flags)
{
xfs_mount_t *mp = ip->i_mount;
uint delblks, blkflags, prjflags = 0;
xfs_dquot_t *unresudq, *unresgdq, *delblksudq, *delblksgdq;
int error;
ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL|XFS_ILOCK_SHARED));
ASSERT(XFS_IS_QUOTA_RUNNING(mp));
delblks = ip->i_delayed_blks;
delblksudq = delblksgdq = unresudq = unresgdq = NULL;
blkflags = XFS_IS_REALTIME_INODE(ip) ?
XFS_QMOPT_RES_RTBLKS : XFS_QMOPT_RES_REGBLKS;
if (XFS_IS_UQUOTA_ON(mp) && udqp &&
ip->i_d.di_uid != (uid_t)be32_to_cpu(udqp->q_core.d_id)) {
delblksudq = udqp;
/*
* If there are delayed allocation blocks, then we have to
* unreserve those from the old dquot, and add them to the
* new dquot.
*/
if (delblks) {
ASSERT(ip->i_udquot);
unresudq = ip->i_udquot;
}
}
if (XFS_IS_OQUOTA_ON(ip->i_mount) && gdqp) {
if (XFS_IS_PQUOTA_ON(ip->i_mount) &&
xfs_get_projid(ip) != be32_to_cpu(gdqp->q_core.d_id))
prjflags = XFS_QMOPT_ENOSPC;
if (prjflags ||
(XFS_IS_GQUOTA_ON(ip->i_mount) &&
ip->i_d.di_gid != be32_to_cpu(gdqp->q_core.d_id))) {
delblksgdq = gdqp;
if (delblks) {
ASSERT(ip->i_gdquot);
unresgdq = ip->i_gdquot;
}
}
}
if ((error = xfs_trans_reserve_quota_bydquots(tp, ip->i_mount,
delblksudq, delblksgdq, ip->i_d.di_nblocks, 1,
flags | blkflags | prjflags)))
return (error);
/*
* Do the delayed blks reservations/unreservations now. Since, these
* are done without the help of a transaction, if a reservation fails
* its previous reservations won't be automatically undone by trans
* code. So, we have to do it manually here.
*/
if (delblks) {
/*
* Do the reservations first. Unreservation can't fail.
*/
ASSERT(delblksudq || delblksgdq);
ASSERT(unresudq || unresgdq);
if ((error = xfs_trans_reserve_quota_bydquots(NULL, ip->i_mount,
delblksudq, delblksgdq, (xfs_qcnt_t)delblks, 0,
flags | blkflags | prjflags)))
return (error);
xfs_trans_reserve_quota_bydquots(NULL, ip->i_mount,
unresudq, unresgdq, -((xfs_qcnt_t)delblks), 0,
blkflags);
}
return (0);
}
/* ARGSUSED */
STATIC int
xfs_qm_dqusage_adjust(
xfs_mount_t *mp, /* mount point for filesystem */
xfs_ino_t ino, /* inode number to get data for */
void __user *buffer, /* not used */
int ubsize, /* not used */
int *ubused, /* not used */
int *res) /* result code value */
{
xfs_inode_t *ip;
xfs_qcnt_t nblks, rtblks = 0;
int error;
ASSERT(XFS_IS_QUOTA_RUNNING(mp));
/*
* rootino must have its resources accounted for, not so with the quota
* inodes.
*/
if (ino == mp->m_sb.sb_uquotino || ino == mp->m_sb.sb_gquotino) {
*res = BULKSTAT_RV_NOTHING;
return XFS_ERROR(EINVAL);
}
/*
* We don't _need_ to take the ilock EXCL. However, the xfs_qm_dqget
* interface expects the inode to be exclusively locked because that's
* the case in all other instances. It's OK that we do this because
* quotacheck is done only at mount time.
*/
error = xfs_iget(mp, NULL, ino, 0, XFS_ILOCK_EXCL, &ip);
if (error) {
*res = BULKSTAT_RV_NOTHING;
return error;
}
ASSERT(ip->i_delayed_blks == 0);
if (XFS_IS_REALTIME_INODE(ip)) {
/*
* Walk thru the extent list and count the realtime blocks.
*/
error = xfs_qm_get_rtblks(ip, &rtblks);
if (error)
goto error0;
}
nblks = (xfs_qcnt_t)ip->i_d.di_nblocks - rtblks;
/*
* Add the (disk blocks and inode) resources occupied by this
* inode to its dquots. We do this adjustment in the incore dquot,
* and also copy the changes to its buffer.
* We don't care about putting these changes in a transaction
* envelope because if we crash in the middle of a 'quotacheck'
* we have to start from the beginning anyway.
* Once we're done, we'll log all the dquot bufs.
*
* The *QUOTA_ON checks below may look pretty racy, but quotachecks
* and quotaoffs don't race. (Quotachecks happen at mount time only).
*/
if (XFS_IS_UQUOTA_ON(mp)) {
error = xfs_qm_quotacheck_dqadjust(ip, ip->i_d.di_uid,
XFS_DQ_USER, nblks, rtblks);
if (error)
goto error0;
}
if (XFS_IS_GQUOTA_ON(mp)) {
error = xfs_qm_quotacheck_dqadjust(ip, ip->i_d.di_gid,
XFS_DQ_GROUP, nblks, rtblks);
if (error)
goto error0;
}
if (XFS_IS_PQUOTA_ON(mp)) {
error = xfs_qm_quotacheck_dqadjust(ip, xfs_get_projid(ip),
XFS_DQ_PROJ, nblks, rtblks);
if (error)
goto error0;
}
xfs_iunlock(ip, XFS_ILOCK_EXCL);
IRELE(ip);
*res = BULKSTAT_RV_DIDONE;
return 0;
error0:
xfs_iunlock(ip, XFS_ILOCK_EXCL);
IRELE(ip);
*res = BULKSTAT_RV_GIVEUP;
return error;
}