/*
* Fill in the disk block numbers in the state structure for the buffers
* that are attached to the state structure.
* This is done so that we can quickly reattach ourselves to those buffers
* after some set of transaction commits have released these buffers.
*/
STATIC int
xfs_attr_fillstate(xfs_da_state_t *state)
{
xfs_da_state_path_t *path;
xfs_da_state_blk_t *blk;
int level;
trace_xfs_attr_fillstate(state->args);
/*
* Roll down the "path" in the state structure, storing the on-disk
* block number for those buffers in the "path".
*/
path = &state->path;
ASSERT((path->active >= 0) && (path->active < XFS_DA_NODE_MAXDEPTH));
for (blk = path->blk, level = 0; level < path->active; blk++, level++) {
if (blk->bp) {
blk->disk_blkno = XFS_BUF_ADDR(blk->bp);
blk->bp = NULL;
} else {
blk->disk_blkno = 0;
}
}
/*
* Roll down the "altpath" in the state structure, storing the on-disk
* block number for those buffers in the "altpath".
*/
path = &state->altpath;
ASSERT((path->active >= 0) && (path->active < XFS_DA_NODE_MAXDEPTH));
for (blk = path->blk, level = 0; level < path->active; blk++, level++) {
if (blk->bp) {
blk->disk_blkno = XFS_BUF_ADDR(blk->bp);
blk->bp = NULL;
} else {
blk->disk_blkno = 0;
}
}
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;
}
}
}
int
xfs_read_buf(
struct xfs_mount *mp,
xfs_buftarg_t *target,
xfs_daddr_t blkno,
int len,
uint flags,
xfs_buf_t **bpp)
{
xfs_buf_t *bp;
int error;
if (flags)
bp = xfs_buf_read_flags(target, blkno, len, flags);
else
bp = xfs_buf_read(target, blkno, len, flags);
if (!bp)
return XFS_ERROR(EIO);
error = XFS_BUF_GETERROR(bp);
if (bp && !error && !XFS_FORCED_SHUTDOWN(mp)) {
*bpp = bp;
} else {
*bpp = NULL;
if (error) {
xfs_ioerror_alert("xfs_read_buf", mp, bp, XFS_BUF_ADDR(bp));
} else {
error = XFS_ERROR(EIO);
}
if (bp) {
XFS_BUF_UNDONE(bp);
XFS_BUF_UNDELAYWRITE(bp);
XFS_BUF_STALE(bp);
/*
* brelse clears B_ERROR and b_error
*/
xfs_buf_relse(bp);
}
}
return (error);
}
/*
* Recurse (gasp!) through the attribute nodes until we find leaves.
* We're doing a depth-first traversal in order to invalidate everything.
*/
STATIC int
xfs_attr3_node_inactive(
struct xfs_trans **trans,
struct xfs_inode *dp,
struct xfs_buf *bp,
int level)
{
xfs_da_blkinfo_t *info;
xfs_da_intnode_t *node;
xfs_dablk_t child_fsb;
xfs_daddr_t parent_blkno, child_blkno;
int error, i;
struct xfs_buf *child_bp;
struct xfs_da_node_entry *btree;
struct xfs_da3_icnode_hdr ichdr;
/*
* Since this code is recursive (gasp!) we must protect ourselves.
*/
if (level > XFS_DA_NODE_MAXDEPTH) {
xfs_trans_brelse(*trans, bp); /* no locks for later trans */
return -EIO;
}
node = bp->b_addr;
dp->d_ops->node_hdr_from_disk(&ichdr, node);
parent_blkno = bp->b_bn;
if (!ichdr.count) {
xfs_trans_brelse(*trans, bp);
return 0;
}
btree = dp->d_ops->node_tree_p(node);
child_fsb = be32_to_cpu(btree[0].before);
xfs_trans_brelse(*trans, bp); /* no locks for later trans */
/*
* If this is the node level just above the leaves, simply loop
* over the leaves removing all of them. If this is higher up
* in the tree, recurse downward.
*/
for (i = 0; i < ichdr.count; i++) {
/*
* Read the subsidiary block to see what we have to work with.
* Don't do this in a transaction. This is a depth-first
* traversal of the tree so we may deal with many blocks
* before we come back to this one.
*/
error = xfs_da3_node_read(*trans, dp, child_fsb, -2, &child_bp,
XFS_ATTR_FORK);
if (error)
return error;
if (child_bp) {
/* save for re-read later */
child_blkno = XFS_BUF_ADDR(child_bp);
/*
* Invalidate the subtree, however we have to.
*/
info = child_bp->b_addr;
switch (info->magic) {
case cpu_to_be16(XFS_DA_NODE_MAGIC):
case cpu_to_be16(XFS_DA3_NODE_MAGIC):
error = xfs_attr3_node_inactive(trans, dp,
child_bp, level + 1);
break;
case cpu_to_be16(XFS_ATTR_LEAF_MAGIC):
case cpu_to_be16(XFS_ATTR3_LEAF_MAGIC):
error = xfs_attr3_leaf_inactive(trans, dp,
child_bp);
break;
default:
error = -EIO;
xfs_trans_brelse(*trans, child_bp);
break;
}
if (error)
return error;
/*
* Remove the subsidiary block from the cache
* and from the log.
*/
error = xfs_da_get_buf(*trans, dp, 0, child_blkno,
&child_bp, XFS_ATTR_FORK);
if (error)
return error;
xfs_trans_binval(*trans, child_bp);
}
/*
* If we're not done, re-read the parent to get the next
* child block number.
*/
if (i + 1 < ichdr.count) {
error = xfs_da3_node_read(*trans, dp, 0, parent_blkno,
&bp, XFS_ATTR_FORK);
if (error)
return error;
child_fsb = be32_to_cpu(btree[i + 1].before);
xfs_trans_brelse(*trans, bp);
}
/*
* Atomically commit the whole invalidate stuff.
*/
error = xfs_trans_roll(trans, dp);
if (error)
return error;
}
return 0;
}