static void
xfs_dir3_block_read_verify(
struct xfs_buf *bp)
{
struct xfs_mount *mp = bp->b_target->bt_mount;
if (xfs_sb_version_hascrc(&mp->m_sb) &&
!xfs_buf_verify_cksum(bp, XFS_DIR3_DATA_CRC_OFF))
xfs_buf_ioerror(bp, -EFSBADCRC);
else if (!xfs_dir3_block_verify(bp))
xfs_buf_ioerror(bp, -EFSCORRUPTED);
if (bp->b_error)
xfs_verifier_error(bp);
}
/*
* If the superblock has the CRC feature bit set or the CRC field is non-null,
* check that the CRC is valid. We check the CRC field is non-null because a
* single bit error could clear the feature bit and unused parts of the
* superblock are supposed to be zero. Hence a non-null crc field indicates that
* we've potentially lost a feature bit and we should check it anyway.
*
* However, past bugs (i.e. in growfs) left non-zeroed regions beyond the
* last field in V4 secondary superblocks. So for secondary superblocks,
* we are more forgiving, and ignore CRC failures if the primary doesn't
* indicate that the fs version is V5.
*/
static void
xfs_sb_read_verify(
struct xfs_buf *bp)
{
struct xfs_mount *mp = bp->b_target->bt_mount;
struct xfs_dsb *dsb = XFS_BUF_TO_SBP(bp);
int error;
/*
* open code the version check to avoid needing to convert the entire
* superblock from disk order just to check the version number
*/
if (dsb->sb_magicnum == cpu_to_be32(XFS_SB_MAGIC) &&
(((be16_to_cpu(dsb->sb_versionnum) & XFS_SB_VERSION_NUMBITS) ==
XFS_SB_VERSION_5) ||
dsb->sb_crc != 0)) {
if (!xfs_buf_verify_cksum(bp, XFS_SB_CRC_OFF)) {
/* Only fail bad secondaries on a known V5 filesystem */
if (bp->b_bn == XFS_SB_DADDR ||
xfs_sb_version_hascrc(&mp->m_sb)) {
error = -EFSBADCRC;
goto out_error;
}
}
}
error = xfs_sb_verify(bp, true);
out_error:
if (error) {
xfs_buf_ioerror(bp, error);
if (error == -EFSCORRUPTED || error == -EFSBADCRC)
xfs_verifier_error(bp);
}
}
static void
xfs_dquot_buf_verify(
struct xfs_buf *bp)
{
struct xfs_mount *mp = bp->b_target->bt_mount;
struct xfs_dqblk *d = (struct xfs_dqblk *)bp->b_addr;
struct xfs_disk_dquot *ddq;
xfs_dqid_t id = 0;
int i;
/*
* On the first read of the buffer, verify that each dquot is valid.
* We don't know what the id of the dquot is supposed to be, just that
* they should be increasing monotonically within the buffer. If the
* first id is corrupt, then it will fail on the second dquot in the
* buffer so corruptions could point to the wrong dquot in this case.
*/
for (i = 0; i < mp->m_quotainfo->qi_dqperchunk; i++) {
int error;
ddq = &d[i].dd_diskdq;
if (i == 0)
id = be32_to_cpu(ddq->d_id);
error = xfs_qm_dqcheck(mp, ddq, id + i, 0, XFS_QMOPT_DOWARN,
"xfs_dquot_read_verify");
if (error) {
XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, d);
xfs_buf_ioerror(bp, EFSCORRUPTED);
break;
}
}
}
static void
xfs_attr3_rmt_write_verify(
struct xfs_buf *bp)
{
struct xfs_mount *mp = bp->b_target->bt_mount;
int blksize = mp->m_attr_geo->blksize;
char *ptr;
int len;
xfs_daddr_t bno;
/* no verification of non-crc buffers */
if (!xfs_sb_version_hascrc(&mp->m_sb))
return;
ptr = bp->b_addr;
bno = bp->b_bn;
len = BBTOB(bp->b_length);
ASSERT(len >= blksize);
while (len > 0) {
struct xfs_attr3_rmt_hdr *rmt = (struct xfs_attr3_rmt_hdr *)ptr;
if (!xfs_attr3_rmt_verify(mp, ptr, blksize, bno)) {
xfs_buf_ioerror(bp, -EFSCORRUPTED);
xfs_verifier_error(bp);
return;
}
/*
* Ensure we aren't writing bogus LSNs to disk. See
* xfs_attr3_rmt_hdr_set() for the explanation.
*/
if (rmt->rm_lsn != cpu_to_be64(NULLCOMMITLSN)) {
xfs_buf_ioerror(bp, -EFSCORRUPTED);
xfs_verifier_error(bp);
return;
}
xfs_update_cksum(ptr, blksize, XFS_ATTR3_RMT_CRC_OFF);
len -= blksize;
ptr += blksize;
bno += BTOBB(blksize);
}
ASSERT(len == 0);
}
static void
xfs_allocbt_verify(
struct xfs_buf *bp)
{
struct xfs_mount *mp = bp->b_target->bt_mount;
struct xfs_btree_block *block = XFS_BUF_TO_BLOCK(bp);
struct xfs_perag *pag = bp->b_pag;
unsigned int level;
int sblock_ok; /* block passes checks */
/*
* magic number and level verification
*
* During growfs operations, we can't verify the exact level as the
* perag is not fully initialised and hence not attached to the buffer.
* In this case, check against the maximum tree depth.
*/
level = be16_to_cpu(block->bb_level);
switch (block->bb_magic) {
case cpu_to_be32(XFS_ABTB_MAGIC):
if (pag)
sblock_ok = level < pag->pagf_levels[XFS_BTNUM_BNOi];
else
sblock_ok = level < mp->m_ag_maxlevels;
break;
case cpu_to_be32(XFS_ABTC_MAGIC):
if (pag)
sblock_ok = level < pag->pagf_levels[XFS_BTNUM_CNTi];
else
sblock_ok = level < mp->m_ag_maxlevels;
break;
default:
sblock_ok = 0;
break;
}
/* numrecs verification */
sblock_ok = sblock_ok &&
be16_to_cpu(block->bb_numrecs) <= mp->m_alloc_mxr[level != 0];
/* sibling pointer verification */
sblock_ok = sblock_ok &&
(block->bb_u.s.bb_leftsib == cpu_to_be32(NULLAGBLOCK) ||
be32_to_cpu(block->bb_u.s.bb_leftsib) < mp->m_sb.sb_agblocks) &&
block->bb_u.s.bb_leftsib &&
(block->bb_u.s.bb_rightsib == cpu_to_be32(NULLAGBLOCK) ||
be32_to_cpu(block->bb_u.s.bb_rightsib) < mp->m_sb.sb_agblocks) &&
block->bb_u.s.bb_rightsib;
if (!sblock_ok) {
trace_xfs_btree_corrupt(bp, _RET_IP_);
XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, block);
xfs_buf_ioerror(bp, EFSCORRUPTED);
}
}
static void
xfs_dquot_buf_read_verify(
struct xfs_buf *bp)
{
struct xfs_mount *mp = bp->b_target->bt_mount;
if (!xfs_dquot_buf_verify_crc(mp, bp) || !xfs_dquot_buf_verify(mp, bp)) {
XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, bp->b_addr);
xfs_buf_ioerror(bp, EFSCORRUPTED);
}
}
static void
xfs_attr3_rmt_read_verify(
struct xfs_buf *bp)
{
struct xfs_mount *mp = bp->b_target->bt_mount;
char *ptr;
int len;
xfs_daddr_t bno;
int blksize = mp->m_attr_geo->blksize;
/* no verification of non-crc buffers */
if (!xfs_sb_version_hascrc(&mp->m_sb))
return;
ptr = bp->b_addr;
bno = bp->b_bn;
len = BBTOB(bp->b_length);
ASSERT(len >= blksize);
while (len > 0) {
if (!xfs_verify_cksum(ptr, blksize, XFS_ATTR3_RMT_CRC_OFF)) {
xfs_buf_ioerror(bp, -EFSBADCRC);
break;
}
if (!xfs_attr3_rmt_verify(mp, ptr, blksize, bno)) {
xfs_buf_ioerror(bp, -EFSCORRUPTED);
break;
}
len -= blksize;
ptr += blksize;
bno += BTOBB(blksize);
}
if (bp->b_error)
xfs_verifier_error(bp);
else
ASSERT(len == 0);
}
static void
xfs_dir3_block_read_verify(
struct xfs_buf *bp)
{
struct xfs_mount *mp = bp->b_target->bt_mount;
if ((xfs_sb_version_hascrc(&mp->m_sb) &&
!xfs_verify_cksum(bp->b_addr, BBTOB(bp->b_length),
XFS_DIR3_DATA_CRC_OFF)) ||
!xfs_dir3_block_verify(bp)) {
XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, bp->b_addr);
xfs_buf_ioerror(bp, EFSCORRUPTED);
}
}
/*
* We may be probed for a filesystem match, so we may not want to emit
* messages when the superblock buffer is not actually an XFS superblock.
* If we find an XFS superblock, then run a normal, noisy mount because we are
* really going to mount it and want to know about errors.
*/
static void
xfs_sb_quiet_read_verify(
struct xfs_buf *bp)
{
struct xfs_dsb *dsb = XFS_BUF_TO_SBP(bp);
if (dsb->sb_magicnum == cpu_to_be32(XFS_SB_MAGIC)) {
/* XFS filesystem, verify noisily! */
xfs_sb_read_verify(bp);
return;
}
/* quietly fail */
xfs_buf_ioerror(bp, -EWRONGFS);
}
static void
xfs_dir2_block_verify(
struct xfs_buf *bp)
{
struct xfs_mount *mp = bp->b_target->bt_mount;
struct xfs_dir2_data_hdr *hdr = bp->b_addr;
int block_ok = 0;
block_ok = hdr->magic == cpu_to_be32(XFS_DIR2_BLOCK_MAGIC);
block_ok = block_ok && __xfs_dir2_data_check(NULL, bp) == 0;
if (!block_ok) {
XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, hdr);
xfs_buf_ioerror(bp, EFSCORRUPTED);
}
}
/*
* 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;
}
}
}
/*
* 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 don't want to mark it with an error,
* but we do want to clear the DONE status of the buffer so that a followup read
* will re-read it from disk. This will ensure that we don't get an unnecessary
* warnings during log recovery and we don't get unnecssary panics on debug
* kernels.
*/
static void
xfs_inode_buf_verify(
struct xfs_buf *bp,
bool readahead)
{
struct xfs_mount *mp = bp->b_target->bt_mount;
int i;
int ni;
/*
* Validate the magic number and version of every inode in the buffer
*/
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;
dip = (struct xfs_dinode *)xfs_buf_offset(bp,
(i << mp->m_sb.sb_inodelog));
di_ok = dip->di_magic == cpu_to_be16(XFS_DINODE_MAGIC) &&
XFS_DINODE_GOOD_VERSION(dip->di_version);
if (unlikely(XFS_TEST_ERROR(!di_ok, mp,
XFS_ERRTAG_ITOBP_INOTOBP,
XFS_RANDOM_ITOBP_INOTOBP))) {
if (readahead) {
bp->b_flags &= ~XBF_DONE;
return;
}
xfs_buf_ioerror(bp, -EFSCORRUPTED);
xfs_verifier_error(bp);
#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_inobp_check(mp, bp);
}
static void
xfs_attr3_rmt_write_verify(
struct xfs_buf *bp)
{
struct xfs_mount *mp = bp->b_target->bt_mount;
struct xfs_buf_log_item *bip = bp->b_fspriv;
char *ptr;
int len;
xfs_daddr_t bno;
/* no verification of non-crc buffers */
if (!xfs_sb_version_hascrc(&mp->m_sb))
return;
ptr = bp->b_addr;
bno = bp->b_bn;
len = BBTOB(bp->b_length);
ASSERT(len >= XFS_LBSIZE(mp));
while (len > 0) {
if (!xfs_attr3_rmt_verify(mp, ptr, XFS_LBSIZE(mp), bno)) {
XFS_CORRUPTION_ERROR(__func__,
XFS_ERRLEVEL_LOW, mp, bp->b_addr);
xfs_buf_ioerror(bp, EFSCORRUPTED);
return;
}
if (bip) {
struct xfs_attr3_rmt_hdr *rmt;
rmt = (struct xfs_attr3_rmt_hdr *)ptr;
rmt->rm_lsn = cpu_to_be64(bip->bli_item.li_lsn);
}
xfs_update_cksum(ptr, XFS_LBSIZE(mp), XFS_ATTR3_RMT_CRC_OFF);
len -= XFS_LBSIZE(mp);
ptr += XFS_LBSIZE(mp);
bno += mp->m_bsize;
}
ASSERT(len == 0);
}
static void
xfs_attr3_rmt_write_verify(
struct xfs_buf *bp)
{
struct xfs_mount *mp = bp->b_target->bt_mount;
struct xfs_buf_log_item *bip = bp->b_fspriv;
char *ptr;
int len;
xfs_daddr_t bno;
int blksize = mp->m_attr_geo->blksize;
/* no verification of non-crc buffers */
if (!xfs_sb_version_hascrc(&mp->m_sb))
return;
ptr = bp->b_addr;
bno = bp->b_bn;
len = BBTOB(bp->b_length);
ASSERT(len >= blksize);
while (len > 0) {
if (!xfs_attr3_rmt_verify(mp, ptr, blksize, bno)) {
xfs_buf_ioerror(bp, -EFSCORRUPTED);
xfs_verifier_error(bp);
return;
}
if (bip) {
struct xfs_attr3_rmt_hdr *rmt;
rmt = (struct xfs_attr3_rmt_hdr *)ptr;
rmt->rm_lsn = cpu_to_be64(bip->bli_item.li_lsn);
}
xfs_update_cksum(ptr, blksize, XFS_ATTR3_RMT_CRC_OFF);
len -= blksize;
ptr += blksize;
bno += BTOBB(blksize);
}
ASSERT(len == 0);
}
static void
xfs_attr3_rmt_read_verify(
struct xfs_buf *bp)
{
struct xfs_mount *mp = bp->b_target->bt_mount;
char *ptr;
int len;
bool corrupt = false;
xfs_daddr_t bno;
/* no verification of non-crc buffers */
if (!xfs_sb_version_hascrc(&mp->m_sb))
return;
ptr = bp->b_addr;
bno = bp->b_bn;
len = BBTOB(bp->b_length);
ASSERT(len >= XFS_LBSIZE(mp));
while (len > 0) {
if (!xfs_verify_cksum(ptr, XFS_LBSIZE(mp),
XFS_ATTR3_RMT_CRC_OFF)) {
corrupt = true;
break;
}
if (!xfs_attr3_rmt_verify(mp, ptr, XFS_LBSIZE(mp), bno)) {
corrupt = true;
break;
}
len -= XFS_LBSIZE(mp);
ptr += XFS_LBSIZE(mp);
bno += mp->m_bsize;
}
if (corrupt) {
XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, bp->b_addr);
xfs_buf_ioerror(bp, EFSCORRUPTED);
} else
ASSERT(len == 0);
}
static void
xfs_dir3_block_write_verify(
struct xfs_buf *bp)
{
struct xfs_mount *mp = bp->b_target->bt_mount;
struct xfs_buf_log_item *bip = bp->b_fspriv;
struct xfs_dir3_blk_hdr *hdr3 = bp->b_addr;
if (!xfs_dir3_block_verify(bp)) {
xfs_buf_ioerror(bp, -EFSCORRUPTED);
xfs_verifier_error(bp);
return;
}
if (!xfs_sb_version_hascrc(&mp->m_sb))
return;
if (bip)
hdr3->lsn = cpu_to_be64(bip->bli_item.li_lsn);
xfs_buf_update_cksum(bp, XFS_DIR3_DATA_CRC_OFF);
}
static void
xfs_dir3_block_write_verify(
struct xfs_buf *bp)
{
struct xfs_mount *mp = bp->b_target->bt_mount;
struct xfs_buf_log_item *bip = bp->b_fspriv;
struct xfs_dir3_blk_hdr *hdr3 = bp->b_addr;
if (!xfs_dir3_block_verify(bp)) {
XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, bp->b_addr);
xfs_buf_ioerror(bp, EFSCORRUPTED);
return;
}
if (!xfs_sb_version_hascrc(&mp->m_sb))
return;
if (bip)
hdr3->lsn = cpu_to_be64(bip->bli_item.li_lsn);
xfs_update_cksum(bp->b_addr, BBTOB(bp->b_length), XFS_DIR3_DATA_CRC_OFF);
}
static void
xfs_sb_write_verify(
struct xfs_buf *bp)
{
struct xfs_mount *mp = bp->b_target->bt_mount;
struct xfs_buf_log_item *bip = bp->b_fspriv;
int error;
error = xfs_sb_verify(bp, false);
if (error) {
xfs_buf_ioerror(bp, error);
xfs_verifier_error(bp);
return;
}
if (!xfs_sb_version_hascrc(&mp->m_sb))
return;
if (bip)
XFS_BUF_TO_SBP(bp)->sb_lsn = cpu_to_be64(bip->bli_item.li_lsn);
xfs_buf_update_cksum(bp, XFS_SB_CRC_OFF);
}
/*
* Readahead of the first block of the directory when it is opened is completely
* oblivious to the format of the directory. Hence we can either get a block
* format buffer or a data format buffer on readahead.
*/
static void
xfs_dir3_data_reada_verify(
struct xfs_buf *bp)
{
struct xfs_dir2_data_hdr *hdr = bp->b_addr;
switch (hdr->magic) {
case cpu_to_be32(XFS_DIR2_BLOCK_MAGIC):
case cpu_to_be32(XFS_DIR3_BLOCK_MAGIC):
bp->b_ops = &xfs_dir3_block_buf_ops;
bp->b_ops->verify_read(bp);
return;
case cpu_to_be32(XFS_DIR2_DATA_MAGIC):
case cpu_to_be32(XFS_DIR3_DATA_MAGIC):
bp->b_ops = &xfs_dir3_data_buf_ops;
bp->b_ops->verify_read(bp);
return;
default:
xfs_buf_ioerror(bp, -EFSCORRUPTED);
xfs_verifier_error(bp);
break;
}
}
/*
* This is called to unpin the buffer associated with the buf log
* item which was previously pinned with a call to xfs_buf_item_pin().
*
* Also drop the reference to the buf item for the current transaction.
* If the XFS_BLI_STALE flag is set and we are the last reference,
* then free up the buf log item and unlock the buffer.
*
* If the remove flag is set we are called from uncommit in the
* forced-shutdown path. If that is true and the reference count on
* the log item is going to drop to zero we need to free the item's
* descriptor in the transaction.
*/
STATIC void
xfs_buf_item_unpin(
struct xfs_log_item *lip,
int remove)
{
struct xfs_buf_log_item *bip = BUF_ITEM(lip);
xfs_buf_t *bp = bip->bli_buf;
struct xfs_ail *ailp = lip->li_ailp;
int stale = bip->bli_flags & XFS_BLI_STALE;
int freed;
ASSERT(bp->b_fspriv == bip);
ASSERT(atomic_read(&bip->bli_refcount) > 0);
trace_xfs_buf_item_unpin(bip);
freed = atomic_dec_and_test(&bip->bli_refcount);
if (atomic_dec_and_test(&bp->b_pin_count))
wake_up_all(&bp->b_waiters);
if (freed && stale) {
ASSERT(bip->bli_flags & XFS_BLI_STALE);
ASSERT(xfs_buf_islocked(bp));
ASSERT(XFS_BUF_ISSTALE(bp));
ASSERT(bip->__bli_format.blf_flags & XFS_BLF_CANCEL);
trace_xfs_buf_item_unpin_stale(bip);
if (remove) {
/*
* If we are in a transaction context, we have to
* remove the log item from the transaction as we are
* about to release our reference to the buffer. If we
* don't, the unlock that occurs later in
* xfs_trans_uncommit() will try to reference the
* buffer which we no longer have a hold on.
*/
if (lip->li_desc)
xfs_trans_del_item(lip);
/*
* Since the transaction no longer refers to the buffer,
* the buffer should no longer refer to the transaction.
*/
bp->b_transp = NULL;
}
/*
* If we get called here because of an IO error, we may
* or may not have the item on the AIL. xfs_trans_ail_delete()
* will take care of that situation.
* xfs_trans_ail_delete() drops the AIL lock.
*/
if (bip->bli_flags & XFS_BLI_STALE_INODE) {
xfs_buf_do_callbacks(bp);
bp->b_fspriv = NULL;
bp->b_iodone = NULL;
} else {
spin_lock(&ailp->xa_lock);
xfs_trans_ail_delete(ailp, lip, SHUTDOWN_LOG_IO_ERROR);
xfs_buf_item_relse(bp);
ASSERT(bp->b_fspriv == NULL);
}
xfs_buf_relse(bp);
} else if (freed && remove) {
/*
* There are currently two references to the buffer - the active
* LRU reference and the buf log item. What we are about to do
* here - simulate a failed IO completion - requires 3
* references.
*
* The LRU reference is removed by the xfs_buf_stale() call. The
* buf item reference is removed by the xfs_buf_iodone()
* callback that is run by xfs_buf_do_callbacks() during ioend
* processing (via the bp->b_iodone callback), and then finally
* the ioend processing will drop the IO reference if the buffer
* is marked XBF_ASYNC.
*
* Hence we need to take an additional reference here so that IO
* completion processing doesn't free the buffer prematurely.
*/
xfs_buf_lock(bp);
xfs_buf_hold(bp);
bp->b_flags |= XBF_ASYNC;
xfs_buf_ioerror(bp, EIO);
XFS_BUF_UNDONE(bp);
xfs_buf_stale(bp);
xfs_buf_ioend(bp, 0);
}
}
/*
* This is the iodone() function for buffers which have had callbacks
* attached to them by xfs_buf_attach_iodone(). It should remove each
* log item from the buffer's list and call the callback of each in turn.
* When done, the buffer's fsprivate field is set to NULL and the buffer
* is unlocked with a call to iodone().
*/
void
xfs_buf_iodone_callbacks(
struct xfs_buf *bp)
{
struct xfs_log_item *lip = bp->b_fspriv;
struct xfs_mount *mp = lip->li_mountp;
static ulong lasttime;
static xfs_buftarg_t *lasttarg;
if (likely(!xfs_buf_geterror(bp)))
goto do_callbacks;
/*
* If we've already decided to shutdown the filesystem because of
* I/O errors, there's no point in giving this a retry.
*/
if (XFS_FORCED_SHUTDOWN(mp)) {
xfs_buf_stale(bp);
XFS_BUF_DONE(bp);
trace_xfs_buf_item_iodone(bp, _RET_IP_);
goto do_callbacks;
}
if (bp->b_target != lasttarg ||
time_after(jiffies, (lasttime + 5*HZ))) {
lasttime = jiffies;
xfs_buf_ioerror_alert(bp, __func__);
}
lasttarg = bp->b_target;
/*
* If the write was asynchronous then no one will be looking for the
* error. Clear the error state and write the buffer out again.
*
* XXX: This helps against transient write errors, but we need to find
* a way to shut the filesystem down if the writes keep failing.
*
* In practice we'll shut the filesystem down soon as non-transient
* erorrs tend to affect the whole device and a failing log write
* will make us give up. But we really ought to do better here.
*/
if (XFS_BUF_ISASYNC(bp)) {
ASSERT(bp->b_iodone != NULL);
trace_xfs_buf_item_iodone_async(bp, _RET_IP_);
xfs_buf_ioerror(bp, 0); /* errno of 0 unsets the flag */
if (!XFS_BUF_ISSTALE(bp)) {
bp->b_flags |= XBF_WRITE | XBF_ASYNC | XBF_DONE;
xfs_buf_iorequest(bp);
} else {
xfs_buf_relse(bp);
}
return;
}
/*
* If the write of the buffer was synchronous, we want to make
* sure to return the error to the caller of xfs_bwrite().
*/
xfs_buf_stale(bp);
XFS_BUF_DONE(bp);
trace_xfs_buf_error_relse(bp, _RET_IP_);
do_callbacks:
xfs_buf_do_callbacks(bp);
bp->b_fspriv = NULL;
bp->b_iodone = NULL;
xfs_buf_ioend(bp, 0);
}
