/*
* Routine to be called at transaction's end by xfs_bmapi, xfs_bunmapi
* caller. Frees all the extents that need freeing, which must be done
* last due to locking considerations. We never free any extents in
* the first transaction.
*
* Return 1 if the given transaction was committed and a new one
* started, and 0 otherwise in the committed parameter.
*/
int /* error */
xfs_bmap_finish(
xfs_trans_t **tp, /* transaction pointer addr */
xfs_bmap_free_t *flist, /* i/o: list extents to free */
int *committed) /* xact committed or not */
{
xfs_efd_log_item_t *efd; /* extent free data */
xfs_efi_log_item_t *efi; /* extent free intention */
int error; /* error return value */
xfs_bmap_free_item_t *free; /* free extent item */
struct xfs_trans_res tres; /* new log reservation */
xfs_mount_t *mp; /* filesystem mount structure */
xfs_bmap_free_item_t *next; /* next item on free list */
xfs_trans_t *ntp; /* new transaction pointer */
ASSERT((*tp)->t_flags & XFS_TRANS_PERM_LOG_RES);
if (flist->xbf_count == 0) {
*committed = 0;
return 0;
}
ntp = *tp;
efi = xfs_trans_get_efi(ntp, flist->xbf_count);
for (free = flist->xbf_first; free; free = free->xbfi_next)
xfs_trans_log_efi_extent(ntp, efi, free->xbfi_startblock,
free->xbfi_blockcount);
tres.tr_logres = ntp->t_log_res;
tres.tr_logcount = ntp->t_log_count;
tres.tr_logflags = XFS_TRANS_PERM_LOG_RES;
ntp = xfs_trans_dup(*tp);
error = xfs_trans_commit(*tp, 0);
*tp = ntp;
*committed = 1;
/*
* We have a new transaction, so we should return committed=1,
* even though we're returning an error.
*/
if (error)
return error;
/*
* transaction commit worked ok so we can drop the extra ticket
* reference that we gained in xfs_trans_dup()
*/
xfs_log_ticket_put(ntp->t_ticket);
error = xfs_trans_reserve(ntp, &tres, 0, 0);
if (error)
return error;
efd = xfs_trans_get_efd(ntp, efi, flist->xbf_count);
for (free = flist->xbf_first; free != NULL; free = next) {
next = free->xbfi_next;
if ((error = xfs_free_extent(ntp, free->xbfi_startblock,
free->xbfi_blockcount))) {
/*
* The bmap free list will be cleaned up at a
* higher level. The EFI will be canceled when
* this transaction is aborted.
* Need to force shutdown here to make sure it
* happens, since this transaction may not be
* dirty yet.
*/
mp = ntp->t_mountp;
if (!XFS_FORCED_SHUTDOWN(mp))
xfs_force_shutdown(mp,
(error == EFSCORRUPTED) ?
SHUTDOWN_CORRUPT_INCORE :
SHUTDOWN_META_IO_ERROR);
return error;
}
xfs_trans_log_efd_extent(ntp, efd, free->xbfi_startblock,
free->xbfi_blockcount);
xfs_bmap_del_free(flist, NULL, free);
}
return 0;
}
/*
* Free a symlink that has blocks associated with it.
*/
STATIC int
xfs_inactive_symlink_rmt(
xfs_inode_t *ip,
xfs_trans_t **tpp)
{
xfs_buf_t *bp;
int committed;
int done;
int error;
xfs_fsblock_t first_block;
xfs_bmap_free_t free_list;
int i;
xfs_mount_t *mp;
xfs_bmbt_irec_t mval[XFS_SYMLINK_MAPS];
int nmaps;
xfs_trans_t *ntp;
int size;
xfs_trans_t *tp;
tp = *tpp;
mp = ip->i_mount;
ASSERT(ip->i_df.if_flags & XFS_IFEXTENTS);
/*
* We're freeing a symlink that has some
* blocks allocated to it. Free the
* blocks here. We know that we've got
* either 1 or 2 extents and that we can
* free them all in one bunmapi call.
*/
ASSERT(ip->i_d.di_nextents > 0 && ip->i_d.di_nextents <= 2);
/*
* Lock the inode, fix the size, and join it to the transaction.
* Hold it so in the normal path, we still have it locked for
* the second transaction. In the error paths we need it
* held so the cancel won't rele it, see below.
*/
size = (int)ip->i_d.di_size;
ip->i_d.di_size = 0;
xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
/*
* Find the block(s) so we can inval and unmap them.
*/
done = 0;
xfs_bmap_init(&free_list, &first_block);
nmaps = ARRAY_SIZE(mval);
error = xfs_bmapi_read(ip, 0, xfs_symlink_blocks(mp, size),
mval, &nmaps, 0);
if (error)
goto error0;
/*
* Invalidate the block(s). No validation is done.
*/
for (i = 0; i < nmaps; i++) {
bp = xfs_trans_get_buf(tp, mp->m_ddev_targp,
XFS_FSB_TO_DADDR(mp, mval[i].br_startblock),
XFS_FSB_TO_BB(mp, mval[i].br_blockcount), 0);
if (!bp) {
error = ENOMEM;
goto error1;
}
xfs_trans_binval(tp, bp);
}
/*
* Unmap the dead block(s) to the free_list.
*/
if ((error = xfs_bunmapi(tp, ip, 0, size, XFS_BMAPI_METADATA, nmaps,
&first_block, &free_list, &done)))
goto error1;
ASSERT(done);
/*
* Commit the first transaction. This logs the EFI and the inode.
*/
if ((error = xfs_bmap_finish(&tp, &free_list, &committed)))
goto error1;
/*
* The transaction must have been committed, since there were
* actually extents freed by xfs_bunmapi. See xfs_bmap_finish.
* The new tp has the extent freeing and EFDs.
*/
ASSERT(committed);
/*
* The first xact was committed, so add the inode to the new one.
* Mark it dirty so it will be logged and moved forward in the log as
* part of every commit.
*/
xfs_trans_ijoin(tp, ip, 0);
xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
/*
* Get a new, empty transaction to return to our caller.
*/
ntp = xfs_trans_dup(tp);
/*
* Commit the transaction containing extent freeing and EFDs.
* If we get an error on the commit here or on the reserve below,
* we need to unlock the inode since the new transaction doesn't
* have the inode attached.
*/
error = xfs_trans_commit(tp, 0);
tp = ntp;
if (error) {
ASSERT(XFS_FORCED_SHUTDOWN(mp));
goto error0;
}
/*
* 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);
/*
* Remove the memory for extent descriptions (just bookkeeping).
*/
if (ip->i_df.if_bytes)
xfs_idata_realloc(ip, -ip->i_df.if_bytes, XFS_DATA_FORK);
ASSERT(ip->i_df.if_bytes == 0);
/*
* Put an itruncate log reservation in the new transaction
* for our caller.
*/
error = xfs_trans_reserve(tp, &M_RES(mp)->tr_itruncate, 0, 0);
if (error) {
ASSERT(XFS_FORCED_SHUTDOWN(mp));
goto error0;
}
xfs_trans_ijoin(tp, ip, 0);
*tpp = tp;
return 0;
error1:
xfs_bmap_cancel(&free_list);
error0:
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;
}
/*
* Roll from one trans in the sequence of PERMANENT transactions to
* the next: permanent transactions are only flushed out when
* committed with XFS_TRANS_RELEASE_LOG_RES, but we still want as soon
* as possible to let chunks of it go to the log. So we commit the
* chunk we've been working on and get a new transaction to continue.
*/
int
xfs_trans_roll(
struct xfs_trans **tpp,
struct xfs_inode *dp)
{
struct xfs_trans *trans;
unsigned int logres, count;
int error;
/*
* Ensure that the inode is always logged.
*/
trans = *tpp;
xfs_trans_log_inode(trans, dp, XFS_ILOG_CORE);
/*
* Copy the critical parameters from one trans to the next.
*/
logres = trans->t_log_res;
count = trans->t_log_count;
*tpp = xfs_trans_dup(trans);
/*
* Commit the current transaction.
* If this commit failed, then it'd just unlock those items that
* are not marked ihold. That also means that a filesystem shutdown
* is in progress. The caller takes the responsibility to cancel
* the duplicate transaction that gets returned.
*/
error = xfs_trans_commit(trans, 0);
if (error)
return (error);
trans = *tpp;
/*
* transaction commit worked ok so we can drop the extra ticket
* reference that we gained in xfs_trans_dup()
*/
xfs_log_ticket_put(trans->t_ticket);
/*
* Reserve space in the log for th next transaction.
* This also pushes items in the "AIL", the list of logged items,
* out to disk if they are taking up space at the tail of the log
* that we want to use. This requires that either nothing be locked
* across this call, or that anything that is locked be logged in
* the prior and the next transactions.
*/
error = xfs_trans_reserve(trans, 0, logres, 0,
XFS_TRANS_PERM_LOG_RES, count);
/*
* Ensure that the inode is in the new transaction and locked.
*/
if (error)
return error;
xfs_trans_ijoin(trans, dp, XFS_ILOCK_EXCL);
xfs_trans_ihold(trans, dp);
return 0;
}