/*
* Roll a transaction, keeping the AG headers locked and reinitializing
* the btree cursors.
*/
int
xrep_roll_ag_trans(
struct xfs_scrub *sc)
{
int error;
/* Keep the AG header buffers locked so we can keep going. */
if (sc->sa.agi_bp)
xfs_trans_bhold(sc->tp, sc->sa.agi_bp);
if (sc->sa.agf_bp)
xfs_trans_bhold(sc->tp, sc->sa.agf_bp);
if (sc->sa.agfl_bp)
xfs_trans_bhold(sc->tp, sc->sa.agfl_bp);
/*
* Roll the transaction. We still own the buffer and the buffer lock
* regardless of whether or not the roll succeeds. If the roll fails,
* the buffers will be released during teardown on our way out of the
* kernel. If it succeeds, we join them to the new transaction and
* move on.
*/
error = xfs_trans_roll(&sc->tp);
if (error)
return error;
/* Join AG headers to the new transaction. */
if (sc->sa.agi_bp)
xfs_trans_bjoin(sc->tp, sc->sa.agi_bp);
if (sc->sa.agf_bp)
xfs_trans_bjoin(sc->tp, sc->sa.agf_bp);
if (sc->sa.agfl_bp)
xfs_trans_bjoin(sc->tp, sc->sa.agfl_bp);
return 0;
}
/*
* Invalidate buffers for per-AG btree blocks we're dumping. This function
* is not intended for use with file data repairs; we have bunmapi for that.
*/
int
xrep_invalidate_blocks(
struct xfs_scrub *sc,
struct xfs_bitmap *bitmap)
{
struct xfs_bitmap_range *bmr;
struct xfs_bitmap_range *n;
struct xfs_buf *bp;
xfs_fsblock_t fsbno;
/*
* For each block in each extent, see if there's an incore buffer for
* exactly that block; if so, invalidate it. The buffer cache only
* lets us look for one buffer at a time, so we have to look one block
* at a time. Avoid invalidating AG headers and post-EOFS blocks
* because we never own those; and if we can't TRYLOCK the buffer we
* assume it's owned by someone else.
*/
for_each_xfs_bitmap_block(fsbno, bmr, n, bitmap) {
/* Skip AG headers and post-EOFS blocks */
if (!xfs_verify_fsbno(sc->mp, fsbno))
continue;
bp = xfs_buf_incore(sc->mp->m_ddev_targp,
XFS_FSB_TO_DADDR(sc->mp, fsbno),
XFS_FSB_TO_BB(sc->mp, 1), XBF_TRYLOCK);
if (bp) {
xfs_trans_bjoin(sc->tp, bp);
xfs_trans_binval(sc->tp, bp);
}
}
return 0;
}
/*
* Join dabuf to transaction.
*
* Originally from xfs_da_btree.c in the kernel, but only used
* in userspace so it now resides here.
*/
void
libxfs_da_bjoin(xfs_trans_t *tp, xfs_dabuf_t *dabuf)
{
int i;
for (i = 0; i < dabuf->nbuf; i++)
xfs_trans_bjoin(tp, dabuf->bps[i]);
}
/*
* Wrapper around call to libxfs_ialloc. Takes care of committing and
* allocating a new transaction as needed.
*
* Originally there were two copies of this code - one in mkfs, the
* other in repair - now there is just the one.
*/
int
libxfs_inode_alloc(
xfs_trans_t **tp,
xfs_inode_t *pip,
mode_t mode,
nlink_t nlink,
xfs_dev_t rdev,
struct cred *cr,
struct fsxattr *fsx,
xfs_inode_t **ipp)
{
xfs_buf_t *ialloc_context;
xfs_inode_t *ip;
int error;
ialloc_context = (xfs_buf_t *)0;
error = libxfs_ialloc(*tp, pip, mode, nlink, rdev, cr, fsx,
1, &ialloc_context, &ip);
if (error) {
*ipp = NULL;
return error;
}
if (!ialloc_context && !ip) {
*ipp = NULL;
return -ENOSPC;
}
if (ialloc_context) {
xfs_trans_bhold(*tp, ialloc_context);
error = xfs_trans_roll(tp, NULL);
if (error) {
fprintf(stderr, _("%s: cannot duplicate transaction: %s\n"),
progname, strerror(error));
exit(1);
}
xfs_trans_bjoin(*tp, ialloc_context);
error = libxfs_ialloc(*tp, pip, mode, nlink, rdev, cr,
fsx, 1, &ialloc_context, &ip);
if (!ip)
error = -ENOSPC;
if (error)
return error;
}
*ipp = ip;
return error;
}
/*
* Wrapper around call to libxfs_ialloc. Takes care of committing and
* allocating a new transaction as needed.
*
* Originally there were two copies of this code - one in mkfs, the
* other in repair - now there is just the one.
*/
int
libxfs_inode_alloc(
xfs_trans_t **tp,
xfs_inode_t *pip,
mode_t mode,
ushort nlink,
dev_t rdev,
cred_t *cr,
xfs_inode_t **ipp)
{
boolean_t call_again;
int i;
xfs_buf_t *ialloc_context;
xfs_inode_t *ip;
xfs_trans_t *ntp;
int error;
call_again = B_FALSE;
ialloc_context = (xfs_buf_t *)0;
error = libxfs_ialloc(*tp, pip, mode, nlink, rdev, cr, (xfs_prid_t) 0,
1, &ialloc_context, &call_again, &ip);
if (error) {
return error;
}
if (call_again) {
xfs_trans_bhold(*tp, ialloc_context);
ntp = xfs_trans_dup(*tp);
xfs_trans_commit(*tp, 0, NULL);
*tp = ntp;
if ((i = xfs_trans_reserve(*tp, 0, 0, 0, 0, 0))) {
fprintf(stderr, "%s: cannot reserve space: %s\n",
progname, strerror(errno));
exit(1);
}
xfs_trans_bjoin(*tp, ialloc_context);
error = libxfs_ialloc(*tp, pip, mode, nlink, rdev, cr,
(xfs_prid_t) 0, 1, &ialloc_context,
&call_again, &ip);
if (error) {
return error;
}
}
*ipp = ip;
ASSERT(ip);
return error;
}
/*
* Allocates a new inode from disk and return a pointer to the
* incore copy. This routine will internally commit the current
* transaction and allocate a new one if the Space Manager needed
* to do an allocation to replenish the inode free-list.
*
* This routine is designed to be called from xfs_create and
* xfs_create_dir.
*
*/
int
xfs_dir_ialloc(
xfs_trans_t **tpp, /* input: current transaction;
output: may be a new transaction. */
xfs_inode_t *dp, /* directory within whose allocate
the inode. */
mode_t mode,
xfs_nlink_t nlink,
xfs_dev_t rdev,
prid_t prid, /* project id */
int okalloc, /* ok to allocate new space */
xfs_inode_t **ipp, /* pointer to inode; it will be
locked. */
int *committed)
{
xfs_trans_t *tp;
xfs_trans_t *ntp;
xfs_inode_t *ip;
xfs_buf_t *ialloc_context = NULL;
boolean_t call_again = B_FALSE;
int code;
uint log_res;
uint log_count;
void *dqinfo;
uint tflags;
tp = *tpp;
ASSERT(tp->t_flags & XFS_TRANS_PERM_LOG_RES);
/*
* xfs_ialloc will return a pointer to an incore inode if
* the Space Manager has an available inode on the free
* list. Otherwise, it will do an allocation and replenish
* the freelist. Since we can only do one allocation per
* transaction without deadlocks, we will need to commit the
* current transaction and start a new one. We will then
* need to call xfs_ialloc again to get the inode.
*
* If xfs_ialloc did an allocation to replenish the freelist,
* it returns the bp containing the head of the freelist as
* ialloc_context. We will hold a lock on it across the
* transaction commit so that no other process can steal
* the inode(s) that we've just allocated.
*/
code = xfs_ialloc(tp, dp, mode, nlink, rdev, prid, okalloc,
&ialloc_context, &call_again, &ip);
/*
* Return an error if we were unable to allocate a new inode.
* This should only happen if we run out of space on disk or
* encounter a disk error.
*/
if (code) {
*ipp = NULL;
return code;
}
if (!call_again && (ip == NULL)) {
*ipp = NULL;
return XFS_ERROR(ENOSPC);
}
/*
* If call_again is set, then we were unable to get an
* inode in one operation. We need to commit the current
* transaction and call xfs_ialloc() again. It is guaranteed
* to succeed the second time.
*/
if (call_again) {
/*
* Normally, xfs_trans_commit releases all the locks.
* We call bhold to hang on to the ialloc_context across
* the commit. Holding this buffer prevents any other
* processes from doing any allocations in this
* allocation group.
*/
xfs_trans_bhold(tp, ialloc_context);
/*
* Save the log reservation so we can use
* them in the next transaction.
*/
log_res = xfs_trans_get_log_res(tp);
log_count = xfs_trans_get_log_count(tp);
/*
* We want the quota changes to be associated with the next
* transaction, NOT this one. So, detach the dqinfo from this
* and attach it to the next transaction.
*/
dqinfo = NULL;
tflags = 0;
if (tp->t_dqinfo) {
dqinfo = (void *)tp->t_dqinfo;
tp->t_dqinfo = NULL;
tflags = tp->t_flags & XFS_TRANS_DQ_DIRTY;
tp->t_flags &= ~(XFS_TRANS_DQ_DIRTY);
}
ntp = xfs_trans_dup(tp);
code = xfs_trans_commit(tp, 0);
tp = ntp;
if (committed != NULL) {
*committed = 1;
}
/*
* If we get an error during the commit processing,
* release the buffer that is still held and return
* to the caller.
*/
if (code) {
xfs_buf_relse(ialloc_context);
if (dqinfo) {
tp->t_dqinfo = dqinfo;
xfs_trans_free_dqinfo(tp);
}
*tpp = ntp;
*ipp = NULL;
return code;
}
/*
* transaction commit worked ok so we can drop the extra ticket
* reference that we gained in xfs_trans_dup()
*/
xfs_log_ticket_put(tp->t_ticket);
code = xfs_trans_reserve(tp, 0, log_res, 0,
XFS_TRANS_PERM_LOG_RES, log_count);
/*
* Re-attach the quota info that we detached from prev trx.
*/
if (dqinfo) {
tp->t_dqinfo = dqinfo;
tp->t_flags |= tflags;
}
if (code) {
xfs_buf_relse(ialloc_context);
*tpp = ntp;
*ipp = NULL;
return code;
}
xfs_trans_bjoin(tp, ialloc_context);
/*
* Call ialloc again. Since we've locked out all
* other allocations in this allocation group,
* this call should always succeed.
*/
code = xfs_ialloc(tp, dp, mode, nlink, rdev, prid,
okalloc, &ialloc_context, &call_again, &ip);
/*
* If we get an error at this point, return to the caller
* so that the current transaction can be aborted.
*/
if (code) {
*tpp = tp;
*ipp = NULL;
return code;
}
ASSERT ((!call_again) && (ip != NULL));
} else {
if (committed != NULL) {
*committed = 0;
}
}
*ipp = ip;
*tpp = tp;
return 0;
}
int
xfs_attr_set(
struct xfs_inode *dp,
const unsigned char *name,
unsigned char *value,
int valuelen,
int flags)
{
struct xfs_mount *mp = dp->i_mount;
struct xfs_buf *leaf_bp = NULL;
struct xfs_da_args args;
struct xfs_trans_res tres;
int rsvd = (flags & ATTR_ROOT) != 0;
int error, err2, local;
XFS_STATS_INC(mp, xs_attr_set);
if (XFS_FORCED_SHUTDOWN(dp->i_mount))
return -EIO;
error = xfs_attr_args_init(&args, dp, name, flags);
if (error)
return error;
args.value = value;
args.valuelen = valuelen;
args.op_flags = XFS_DA_OP_ADDNAME | XFS_DA_OP_OKNOENT;
args.total = xfs_attr_calc_size(&args, &local);
error = xfs_qm_dqattach(dp);
if (error)
return error;
/*
* If the inode doesn't have an attribute fork, add one.
* (inode must not be locked when we call this routine)
*/
if (XFS_IFORK_Q(dp) == 0) {
int sf_size = sizeof(xfs_attr_sf_hdr_t) +
XFS_ATTR_SF_ENTSIZE_BYNAME(args.namelen, valuelen);
error = xfs_bmap_add_attrfork(dp, sf_size, rsvd);
if (error)
return error;
}
tres.tr_logres = M_RES(mp)->tr_attrsetm.tr_logres +
M_RES(mp)->tr_attrsetrt.tr_logres * args.total;
tres.tr_logcount = XFS_ATTRSET_LOG_COUNT;
tres.tr_logflags = XFS_TRANS_PERM_LOG_RES;
/*
* Root fork attributes can use reserved data blocks for this
* operation if necessary
*/
error = xfs_trans_alloc(mp, &tres, args.total, 0,
rsvd ? XFS_TRANS_RESERVE : 0, &args.trans);
if (error)
return error;
xfs_ilock(dp, XFS_ILOCK_EXCL);
error = xfs_trans_reserve_quota_nblks(args.trans, dp, args.total, 0,
rsvd ? XFS_QMOPT_RES_REGBLKS | XFS_QMOPT_FORCE_RES :
XFS_QMOPT_RES_REGBLKS);
if (error) {
xfs_iunlock(dp, XFS_ILOCK_EXCL);
xfs_trans_cancel(args.trans);
return error;
}
xfs_trans_ijoin(args.trans, dp, 0);
/*
* If the attribute list is non-existent or a shortform list,
* upgrade it to a single-leaf-block attribute list.
*/
if (dp->i_d.di_aformat == XFS_DINODE_FMT_LOCAL ||
(dp->i_d.di_aformat == XFS_DINODE_FMT_EXTENTS &&
dp->i_d.di_anextents == 0)) {
/*
* Build initial attribute list (if required).
*/
if (dp->i_d.di_aformat == XFS_DINODE_FMT_EXTENTS)
xfs_attr_shortform_create(&args);
/*
* Try to add the attr to the attribute list in
* the inode.
*/
error = xfs_attr_shortform_addname(&args);
if (error != -ENOSPC) {
/*
* Commit the shortform mods, and we're done.
* NOTE: this is also the error path (EEXIST, etc).
*/
ASSERT(args.trans != NULL);
/*
* 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(args.trans);
if (!error && (flags & ATTR_KERNOTIME) == 0) {
xfs_trans_ichgtime(args.trans, dp,
XFS_ICHGTIME_CHG);
}
err2 = xfs_trans_commit(args.trans);
xfs_iunlock(dp, XFS_ILOCK_EXCL);
return error ? error : err2;
}
/*
* It won't fit in the shortform, transform to a leaf block.
* GROT: another possible req'mt for a double-split btree op.
*/
error = xfs_attr_shortform_to_leaf(&args, &leaf_bp);
if (error)
goto out;
/*
* Prevent the leaf buffer from being unlocked so that a
* concurrent AIL push cannot grab the half-baked leaf
* buffer and run into problems with the write verifier.
*/
xfs_trans_bhold(args.trans, leaf_bp);
error = xfs_defer_finish(&args.trans);
if (error)
goto out;
/*
* Commit the leaf transformation. We'll need another (linked)
* transaction to add the new attribute to the leaf, which
* means that we have to hold & join the leaf buffer here too.
*/
error = xfs_trans_roll_inode(&args.trans, dp);
if (error)
goto out;
xfs_trans_bjoin(args.trans, leaf_bp);
leaf_bp = NULL;
}
if (xfs_bmap_one_block(dp, XFS_ATTR_FORK))
error = xfs_attr_leaf_addname(&args);
else
error = xfs_attr_node_addname(&args);
if (error)
goto out;
/*
* 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(args.trans);
if ((flags & ATTR_KERNOTIME) == 0)
xfs_trans_ichgtime(args.trans, dp, XFS_ICHGTIME_CHG);
/*
* Commit the last in the sequence of transactions.
*/
xfs_trans_log_inode(args.trans, dp, XFS_ILOG_CORE);
error = xfs_trans_commit(args.trans);
xfs_iunlock(dp, XFS_ILOCK_EXCL);
return error;
out:
if (leaf_bp)
xfs_trans_brelse(args.trans, leaf_bp);
if (args.trans)
xfs_trans_cancel(args.trans);
xfs_iunlock(dp, XFS_ILOCK_EXCL);
return error;
}
/*
* Allocate a block and fill it with dquots.
* This is called when the bmapi finds a hole.
*/
STATIC int
xfs_qm_dqalloc(
xfs_trans_t **tpp,
xfs_mount_t *mp,
xfs_dquot_t *dqp,
xfs_inode_t *quotip,
xfs_fileoff_t offset_fsb,
xfs_buf_t **O_bpp)
{
xfs_fsblock_t firstblock;
xfs_bmap_free_t flist;
xfs_bmbt_irec_t map;
int nmaps, error, committed;
xfs_buf_t *bp;
xfs_trans_t *tp = *tpp;
ASSERT(tp != NULL);
xfs_dqtrace_entry(dqp, "DQALLOC");
/*
* Initialize the bmap freelist prior to calling bmapi code.
*/
XFS_BMAP_INIT(&flist, &firstblock);
xfs_ilock(quotip, XFS_ILOCK_EXCL);
/*
* Return if this type of quotas is turned off while we didn't
* have an inode lock
*/
if (XFS_IS_THIS_QUOTA_OFF(dqp)) {
xfs_iunlock(quotip, XFS_ILOCK_EXCL);
return (ESRCH);
}
/*
* xfs_trans_commit normally decrements the vnode ref count
* when it unlocks the inode. Since we want to keep the quota
* inode around, we bump the vnode ref count now.
*/
VN_HOLD(XFS_ITOV(quotip));
xfs_trans_ijoin(tp, quotip, XFS_ILOCK_EXCL);
nmaps = 1;
if ((error = xfs_bmapi(tp, quotip,
offset_fsb, XFS_DQUOT_CLUSTER_SIZE_FSB,
XFS_BMAPI_METADATA | XFS_BMAPI_WRITE,
&firstblock,
XFS_QM_DQALLOC_SPACE_RES(mp),
&map, &nmaps, &flist))) {
goto error0;
}
ASSERT(map.br_blockcount == XFS_DQUOT_CLUSTER_SIZE_FSB);
ASSERT(nmaps == 1);
ASSERT((map.br_startblock != DELAYSTARTBLOCK) &&
(map.br_startblock != HOLESTARTBLOCK));
/*
* Keep track of the blkno to save a lookup later
*/
dqp->q_blkno = XFS_FSB_TO_DADDR(mp, map.br_startblock);
/* now we can just get the buffer (there's nothing to read yet) */
bp = xfs_trans_get_buf(tp, mp->m_ddev_targp,
dqp->q_blkno,
XFS_QI_DQCHUNKLEN(mp),
0);
if (!bp || (error = XFS_BUF_GETERROR(bp)))
goto error1;
/*
* Make a chunk of dquots out of this buffer and log
* the entire thing.
*/
xfs_qm_init_dquot_blk(tp, mp, be32_to_cpu(dqp->q_core.d_id),
dqp->dq_flags & XFS_DQ_ALLTYPES, bp);
/*
* xfs_bmap_finish() may commit the current transaction and
* start a second transaction if the freelist is not empty.
*
* Since we still want to modify this buffer, we need to
* ensure that the buffer is not released on commit of
* the first transaction and ensure the buffer is added to the
* second transaction.
*
* If there is only one transaction then don't stop the buffer
* from being released when it commits later on.
*/
xfs_trans_bhold(tp, bp);
if ((error = xfs_bmap_finish(tpp, &flist, firstblock, &committed))) {
goto error1;
}
if (committed) {
tp = *tpp;
xfs_trans_bjoin(tp, bp);
} else {
xfs_trans_bhold_release(tp, bp);
}
*O_bpp = bp;
return 0;
error1:
xfs_bmap_cancel(&flist);
error0:
xfs_iunlock(quotip, XFS_ILOCK_EXCL);
return (error);
}
/*
* Allocate a block and fill it with dquots.
* This is called when the bmapi finds a hole.
*/
STATIC int
xfs_qm_dqalloc(
xfs_trans_t **tpp,
xfs_mount_t *mp,
xfs_dquot_t *dqp,
xfs_inode_t *quotip,
xfs_fileoff_t offset_fsb,
xfs_buf_t **O_bpp)
{
xfs_fsblock_t firstblock;
xfs_bmap_free_t flist;
xfs_bmbt_irec_t map;
int nmaps, error, committed;
xfs_buf_t *bp;
xfs_trans_t *tp = *tpp;
ASSERT(tp != NULL);
trace_xfs_dqalloc(dqp);
/*
* Initialize the bmap freelist prior to calling bmapi code.
*/
xfs_bmap_init(&flist, &firstblock);
xfs_ilock(quotip, XFS_ILOCK_EXCL);
/*
* Return if this type of quotas is turned off while we didn't
* have an inode lock
*/
if (!xfs_this_quota_on(dqp->q_mount, dqp->dq_flags)) {
xfs_iunlock(quotip, XFS_ILOCK_EXCL);
return (ESRCH);
}
xfs_trans_ijoin(tp, quotip, XFS_ILOCK_EXCL);
nmaps = 1;
error = xfs_bmapi_write(tp, quotip, offset_fsb,
XFS_DQUOT_CLUSTER_SIZE_FSB, XFS_BMAPI_METADATA,
&firstblock, XFS_QM_DQALLOC_SPACE_RES(mp),
&map, &nmaps, &flist);
if (error)
goto error0;
ASSERT(map.br_blockcount == XFS_DQUOT_CLUSTER_SIZE_FSB);
ASSERT(nmaps == 1);
ASSERT((map.br_startblock != DELAYSTARTBLOCK) &&
(map.br_startblock != HOLESTARTBLOCK));
/*
* Keep track of the blkno to save a lookup later
*/
dqp->q_blkno = XFS_FSB_TO_DADDR(mp, map.br_startblock);
/* now we can just get the buffer (there's nothing to read yet) */
bp = xfs_trans_get_buf(tp, mp->m_ddev_targp,
dqp->q_blkno,
mp->m_quotainfo->qi_dqchunklen,
0);
if (!bp) {
error = ENOMEM;
goto error1;
}
bp->b_ops = &xfs_dquot_buf_ops;
/*
* Make a chunk of dquots out of this buffer and log
* the entire thing.
*/
xfs_qm_init_dquot_blk(tp, mp, be32_to_cpu(dqp->q_core.d_id),
dqp->dq_flags & XFS_DQ_ALLTYPES, bp);
/*
* xfs_bmap_finish() may commit the current transaction and
* start a second transaction if the freelist is not empty.
*
* Since we still want to modify this buffer, we need to
* ensure that the buffer is not released on commit of
* the first transaction and ensure the buffer is added to the
* second transaction.
*
* If there is only one transaction then don't stop the buffer
* from being released when it commits later on.
*/
xfs_trans_bhold(tp, bp);
if ((error = xfs_bmap_finish(tpp, &flist, &committed))) {
goto error1;
}
if (committed) {
tp = *tpp;
xfs_trans_bjoin(tp, bp);
} else {
xfs_trans_bhold_release(tp, bp);
}
*O_bpp = bp;
return 0;
error1:
xfs_bmap_cancel(&flist);
error0:
xfs_iunlock(quotip, XFS_ILOCK_EXCL);
return (error);
}
