/*
* trim a range of the filesystem.
*
* Note: the parameters passed from userspace are byte ranges into the
* filesystem which does not match to the format we use for filesystem block
* addressing. FSB addressing is sparse (AGNO|AGBNO), while the incoming format
* is a linear address range. Hence we need to use DADDR based conversions and
* comparisons for determining the correct offset and regions to trim.
*/
int
xfs_ioc_trim(
struct xfs_mount *mp,
struct fstrim_range __user *urange)
{
struct request_queue *q = bdev_get_queue(mp->m_ddev_targp->bt_bdev);
unsigned int granularity = q->limits.discard_granularity;
struct fstrim_range range;
xfs_daddr_t start, end, minlen;
xfs_agnumber_t start_agno, end_agno, agno;
__uint64_t blocks_trimmed = 0;
int error, last_error = 0;
if (!capable(CAP_SYS_ADMIN))
return -XFS_ERROR(EPERM);
if (!blk_queue_discard(q))
return -XFS_ERROR(EOPNOTSUPP);
if (copy_from_user(&range, urange, sizeof(range)))
return -XFS_ERROR(EFAULT);
/*
* Truncating down the len isn't actually quite correct, but using
* BBTOB would mean we trivially get overflows for values
* of ULLONG_MAX or slightly lower. And ULLONG_MAX is the default
* used by the fstrim application. In the end it really doesn't
* matter as trimming blocks is an advisory interface.
*/
if (range.start >= XFS_FSB_TO_B(mp, mp->m_sb.sb_dblocks) ||
range.minlen > XFS_FSB_TO_B(mp, XFS_ALLOC_AG_MAX_USABLE(mp)) ||
range.len < mp->m_sb.sb_blocksize)
return -XFS_ERROR(EINVAL);
start = BTOBB(range.start);
end = start + BTOBBT(range.len) - 1;
minlen = BTOBB(max_t(u64, granularity, range.minlen));
if (end > XFS_FSB_TO_BB(mp, mp->m_sb.sb_dblocks) - 1)
end = XFS_FSB_TO_BB(mp, mp->m_sb.sb_dblocks)- 1;
start_agno = xfs_daddr_to_agno(mp, start);
end_agno = xfs_daddr_to_agno(mp, end);
for (agno = start_agno; agno <= end_agno; agno++) {
error = -xfs_trim_extents(mp, agno, start, end, minlen,
&blocks_trimmed);
if (error)
last_error = error;
}
if (last_error)
return last_error;
range.len = XFS_FSB_TO_B(mp, blocks_trimmed);
if (copy_to_user(urange, &range, sizeof(range)))
return -XFS_ERROR(EFAULT);
return 0;
}
/*
* If we are doing readahead on an inode buffer, we might be in log recovery
* reading an inode allocation buffer that hasn't yet been replayed, and hence
* has not had the inode cores stamped into it. Hence for readahead, the buffer
* may be potentially invalid.
*
* If the readahead buffer is invalid, we need to mark it with an error and
* clear the DONE status of the buffer so that a followup read will re-read it
* from disk. We don't report the error otherwise to avoid warnings during log
* recovery and we don't get unnecssary panics on debug kernels. We use EIO here
* because all we want to do is say readahead failed; there is no-one to report
* the error to, so this will distinguish it from a non-ra verifier failure.
* Changes to this readahead error behavour also need to be reflected in
* xfs_dquot_buf_readahead_verify().
*/
static void
xfs_inode_buf_verify(
struct xfs_buf *bp,
bool readahead)
{
struct xfs_mount *mp = bp->b_target->bt_mount;
xfs_agnumber_t agno;
int i;
int ni;
/*
* Validate the magic number and version of every inode in the buffer
*/
agno = xfs_daddr_to_agno(mp, XFS_BUF_ADDR(bp));
ni = XFS_BB_TO_FSB(mp, bp->b_length) * mp->m_sb.sb_inopblock;
for (i = 0; i < ni; i++) {
int di_ok;
xfs_dinode_t *dip;
xfs_agino_t unlinked_ino;
dip = xfs_buf_offset(bp, (i << mp->m_sb.sb_inodelog));
unlinked_ino = be32_to_cpu(dip->di_next_unlinked);
di_ok = dip->di_magic == cpu_to_be16(XFS_DINODE_MAGIC) &&
xfs_dinode_good_version(mp, dip->di_version) &&
(unlinked_ino == NULLAGINO ||
xfs_verify_agino(mp, agno, unlinked_ino));
if (unlikely(XFS_TEST_ERROR(!di_ok, mp,
XFS_ERRTAG_ITOBP_INOTOBP))) {
if (readahead) {
bp->b_flags &= ~XBF_DONE;
xfs_buf_ioerror(bp, -EIO);
return;
}
#ifdef DEBUG
xfs_alert(mp,
"bad inode magic/vsn daddr %lld #%d (magic=%x)",
(unsigned long long)bp->b_bn, i,
be16_to_cpu(dip->di_magic));
#endif
xfs_buf_verifier_error(bp, -EFSCORRUPTED,
__func__, dip, sizeof(*dip),
NULL);
return;
}
}
}
