/*
* This is the dquot flushing I/O completion routine. It is called
* from interrupt level when the buffer containing the dquot is
* flushed to disk. It is responsible for removing the dquot logitem
* from the AIL if it has not been re-logged, and unlocking the dquot's
* flush lock. This behavior is very similar to that of inodes..
*/
STATIC void
xfs_qm_dqflush_done(
struct xfs_buf *bp,
struct xfs_log_item *lip)
{
xfs_dq_logitem_t *qip = (struct xfs_dq_logitem *)lip;
xfs_dquot_t *dqp = qip->qli_dquot;
struct xfs_ail *ailp = lip->li_ailp;
/*
* We only want to pull the item from the AIL if its
* location in the log has not changed since we started the flush.
* Thus, we only bother if the dquot's lsn has
* not changed. First we check the lsn outside the lock
* since it's cheaper, and then we recheck while
* holding the lock before removing the dquot from the AIL.
*/
if ((lip->li_flags & XFS_LI_IN_AIL) &&
lip->li_lsn == qip->qli_flush_lsn) {
/* xfs_trans_ail_delete() drops the AIL lock. */
spin_lock(&ailp->xa_lock);
if (lip->li_lsn == qip->qli_flush_lsn)
xfs_trans_ail_delete(ailp, lip, SHUTDOWN_CORRUPT_INCORE);
else
spin_unlock(&ailp->xa_lock);
}
/*
* Release the dq's flush lock since we're done with it.
*/
xfs_dqfunlock(dqp);
}
void
xfs_iflush_abort(
xfs_inode_t *ip)
{
xfs_inode_log_item_t *iip = ip->i_itemp;
if (iip) {
struct xfs_ail *ailp = iip->ili_item.li_ailp;
if (iip->ili_item.li_flags & XFS_LI_IN_AIL) {
spin_lock(&ailp->xa_lock);
if (iip->ili_item.li_flags & XFS_LI_IN_AIL) {
/* */
xfs_trans_ail_delete(ailp, (xfs_log_item_t *)iip);
} else
spin_unlock(&ailp->xa_lock);
}
iip->ili_logged = 0;
/*
*/
iip->ili_last_fields = 0;
/*
*/
iip->ili_fields = 0;
}
/*
*/
xfs_ifunlock(ip);
}
/*
* This is the inode flushing abort routine. It is called
* from xfs_iflush when the filesystem is shutting down to clean
* up the inode state.
* It is responsible for removing the inode item
* from the AIL if it has not been re-logged, and unlocking the inode's
* flush lock.
*/
void
xfs_iflush_abort(
xfs_inode_t *ip)
{
xfs_inode_log_item_t *iip = ip->i_itemp;
if (iip) {
struct xfs_ail *ailp = iip->ili_item.li_ailp;
if (iip->ili_item.li_flags & XFS_LI_IN_AIL) {
spin_lock(&ailp->xa_lock);
if (iip->ili_item.li_flags & XFS_LI_IN_AIL) {
/* xfs_trans_ail_delete() drops the AIL lock. */
xfs_trans_ail_delete(ailp, (xfs_log_item_t *)iip);
} else
spin_unlock(&ailp->xa_lock);
}
iip->ili_logged = 0;
/*
* Clear the ili_last_fields bits now that we know that the
* data corresponding to them is safely on disk.
*/
iip->ili_last_fields = 0;
/*
* Clear the inode logging fields so no more flushes are
* attempted.
*/
iip->ili_format.ilf_fields = 0;
}
/*
* Release the inode's flush lock since we're done with it.
*/
xfs_ifunlock(ip);
}
void
xfs_inode_free(
struct xfs_inode *ip)
{
switch (ip->i_d.di_mode & S_IFMT) {
case S_IFREG:
case S_IFDIR:
case S_IFLNK:
xfs_idestroy_fork(ip, XFS_DATA_FORK);
break;
}
if (ip->i_afp)
xfs_idestroy_fork(ip, XFS_ATTR_FORK);
if (ip->i_itemp) {
/*
* Only if we are shutting down the fs will we see an
* inode still in the AIL. If it is there, we should remove
* it to prevent a use-after-free from occurring.
*/
xfs_log_item_t *lip = &ip->i_itemp->ili_item;
struct xfs_ail *ailp = lip->li_ailp;
ASSERT(((lip->li_flags & XFS_LI_IN_AIL) == 0) ||
XFS_FORCED_SHUTDOWN(ip->i_mount));
if (lip->li_flags & XFS_LI_IN_AIL) {
spin_lock(&ailp->xa_lock);
if (lip->li_flags & XFS_LI_IN_AIL)
xfs_trans_ail_delete(ailp, lip);
else
spin_unlock(&ailp->xa_lock);
}
xfs_inode_item_destroy(ip);
ip->i_itemp = NULL;
}
/* asserts to verify all state is correct here */
ASSERT(atomic_read(&ip->i_iocount) == 0);
ASSERT(atomic_read(&ip->i_pincount) == 0);
ASSERT(!spin_is_locked(&ip->i_flags_lock));
ASSERT(completion_done(&ip->i_flush));
/*
* Because we use RCU freeing we need to ensure the inode always
* appears to be reclaimed with an invalid inode number when in the
* free state. The ip->i_flags_lock provides the barrier against lookup
* races.
*/
spin_lock(&ip->i_flags_lock);
ip->i_flags = XFS_IRECLAIM;
ip->i_ino = 0;
spin_unlock(&ip->i_flags_lock);
call_rcu(&VFS_I(ip)->i_rcu, xfs_inode_free_callback);
}
/*
* Freeing the efi requires that we remove it from the AIL if it has already
* been placed there. However, the EFI may not yet have been placed in the AIL
* when called by xfs_efi_release() from EFD processing due to the ordering of
* committed vs unpin operations in bulk insert operations. Hence the
* test_and_clear_bit(XFS_EFI_COMMITTED) to ensure only the last caller frees
* the EFI.
*/
STATIC void
__xfs_efi_release(
struct xfs_efi_log_item *efip)
{
struct xfs_ail *ailp = efip->efi_item.li_ailp;
if (!test_and_clear_bit(XFS_EFI_COMMITTED, &efip->efi_flags)) {
spin_lock(&ailp->xa_lock);
/* xfs_trans_ail_delete() drops the AIL lock. */
xfs_trans_ail_delete(ailp, &efip->efi_item);
xfs_efi_item_free(efip);
}
}
/*
* Freeing the efi requires that we remove it from the AIL if it has already
* been placed there. However, the EFI may not yet have been placed in the AIL
* when called by xfs_efi_release() from EFD processing due to the ordering of
* committed vs unpin operations in bulk insert operations. Hence the reference
* count to ensure only the last caller frees the EFI.
*/
STATIC void
__xfs_efi_release(
struct xfs_efi_log_item *efip)
{
struct xfs_ail *ailp = efip->efi_item.li_ailp;
if (atomic_dec_and_test(&efip->efi_refcount)) {
spin_lock(&ailp->xa_lock);
/* xfs_trans_ail_delete() drops the AIL lock. */
xfs_trans_ail_delete(ailp, &efip->efi_item,
SHUTDOWN_LOG_IO_ERROR);
xfs_efi_item_free(efip);
}
}
/*ARGSUSED*/
STATIC void
xfs_efi_item_unpin(xfs_efi_log_item_t *efip, int stale)
{
struct xfs_ail *ailp = efip->efi_item.li_ailp;
spin_lock(&ailp->xa_lock);
if (efip->efi_flags & XFS_EFI_CANCELED) {
/* xfs_trans_ail_delete() drops the AIL lock. */
xfs_trans_ail_delete(ailp, (xfs_log_item_t *)efip);
xfs_efi_item_free(efip);
} else {
efip->efi_flags |= XFS_EFI_COMMITTED;
spin_unlock(&ailp->xa_lock);
}
}
void
xfs_inode_free(
struct xfs_inode *ip)
{
switch (ip->i_d.di_mode & S_IFMT) {
case S_IFREG:
case S_IFDIR:
case S_IFLNK:
xfs_idestroy_fork(ip, XFS_DATA_FORK);
break;
}
if (ip->i_afp)
xfs_idestroy_fork(ip, XFS_ATTR_FORK);
if (ip->i_itemp) {
/*
* Only if we are shutting down the fs will we see an
* inode still in the AIL. If it is there, we should remove
* it to prevent a use-after-free from occurring.
*/
xfs_log_item_t *lip = &ip->i_itemp->ili_item;
struct xfs_ail *ailp = lip->li_ailp;
ASSERT(((lip->li_flags & XFS_LI_IN_AIL) == 0) ||
XFS_FORCED_SHUTDOWN(ip->i_mount));
if (lip->li_flags & XFS_LI_IN_AIL) {
spin_lock(&ailp->xa_lock);
if (lip->li_flags & XFS_LI_IN_AIL)
xfs_trans_ail_delete(ailp, lip);
else
spin_unlock(&ailp->xa_lock);
}
xfs_inode_item_destroy(ip);
ip->i_itemp = NULL;
}
/* asserts to verify all state is correct here */
ASSERT(atomic_read(&ip->i_iocount) == 0);
ASSERT(atomic_read(&ip->i_pincount) == 0);
ASSERT(!spin_is_locked(&ip->i_flags_lock));
ASSERT(completion_done(&ip->i_flush));
kmem_zone_free(xfs_inode_zone, ip);
}
void
xfs_inode_free(
struct xfs_inode *ip)
{
switch (ip->i_d.di_mode & S_IFMT) {
case S_IFREG:
case S_IFDIR:
case S_IFLNK:
xfs_idestroy_fork(ip, XFS_DATA_FORK);
break;
}
if (ip->i_afp)
xfs_idestroy_fork(ip, XFS_ATTR_FORK);
if (ip->i_itemp) {
xfs_log_item_t *lip = &ip->i_itemp->ili_item;
struct xfs_ail *ailp = lip->li_ailp;
ASSERT(((lip->li_flags & XFS_LI_IN_AIL) == 0) ||
XFS_FORCED_SHUTDOWN(ip->i_mount));
if (lip->li_flags & XFS_LI_IN_AIL) {
spin_lock(&ailp->xa_lock);
if (lip->li_flags & XFS_LI_IN_AIL)
xfs_trans_ail_delete(ailp, lip);
else
spin_unlock(&ailp->xa_lock);
}
xfs_inode_item_destroy(ip);
ip->i_itemp = NULL;
}
ASSERT(atomic_read(&ip->i_pincount) == 0);
ASSERT(!spin_is_locked(&ip->i_flags_lock));
ASSERT(!xfs_isiflocked(ip));
spin_lock(&ip->i_flags_lock);
ip->i_flags = XFS_IRECLAIM;
ip->i_ino = 0;
spin_unlock(&ip->i_flags_lock);
call_rcu(&VFS_I(ip)->i_rcu, xfs_inode_free_callback);
}
/*ARGSUSED*/
void
xfs_iflush_done(
xfs_buf_t *bp,
xfs_inode_log_item_t *iip)
{
xfs_inode_t *ip = iip->ili_inode;
struct xfs_ail *ailp = iip->ili_item.li_ailp;
/*
* We only want to pull the item from the AIL if it is
* actually there and its location in the log has not
* changed since we started the flush. Thus, we only bother
* if the ili_logged flag is set and the inode's lsn has not
* changed. First we check the lsn outside
* the lock since it's cheaper, and then we recheck while
* holding the lock before removing the inode from the AIL.
*/
if (iip->ili_logged &&
(iip->ili_item.li_lsn == iip->ili_flush_lsn)) {
spin_lock(&ailp->xa_lock);
if (iip->ili_item.li_lsn == iip->ili_flush_lsn) {
/* xfs_trans_ail_delete() drops the AIL lock. */
xfs_trans_ail_delete(ailp, (xfs_log_item_t*)iip);
} else {
spin_unlock(&ailp->xa_lock);
}
}
iip->ili_logged = 0;
/*
* Clear the ili_last_fields bits now that we know that the
* data corresponding to them is safely on disk.
*/
iip->ili_last_fields = 0;
/*
* Release the inode's flush lock since we're done with it.
*/
xfs_ifunlock(ip);
return;
}
STATIC xfs_lsn_t
xfs_qm_qoffend_logitem_committed(
struct xfs_log_item *lip,
xfs_lsn_t lsn)
{
struct xfs_qoff_logitem *qfe = QOFF_ITEM(lip);
struct xfs_qoff_logitem *qfs = qfe->qql_start_lip;
struct xfs_ail *ailp = qfs->qql_item.li_ailp;
/*
* Delete the qoff-start logitem from the AIL.
* xfs_trans_ail_delete() drops the AIL lock.
*/
spin_lock(&ailp->xa_lock);
xfs_trans_ail_delete(ailp, (xfs_log_item_t *)qfs);
kmem_free(qfs);
kmem_free(qfe);
return (xfs_lsn_t)-1;
}
/*
* While EFIs cannot really be pinned, the unpin operation is the
* last place at which the EFI is manipulated during a transaction.
* Here we coordinate with xfs_efi_cancel() to determine who gets to
* free the EFI.
*/
STATIC void
xfs_efi_item_unpin(
struct xfs_log_item *lip,
int remove)
{
struct xfs_efi_log_item *efip = EFI_ITEM(lip);
struct xfs_ail *ailp = lip->li_ailp;
spin_lock(&ailp->xa_lock);
if (efip->efi_flags & XFS_EFI_CANCELED) {
if (remove)
xfs_trans_del_item(lip);
/* xfs_trans_ail_delete() drops the AIL lock. */
xfs_trans_ail_delete(ailp, lip);
xfs_efi_item_free(efip);
} else {
efip->efi_flags |= XFS_EFI_COMMITTED;
spin_unlock(&ailp->xa_lock);
}
}
/*
* This is called by the efd item code below to release references to
* the given efi item. Each efd calls this with the number of
* extents that it has logged, and when the sum of these reaches
* the total number of extents logged by this efi item we can free
* the efi item.
*
* Freeing the efi item requires that we remove it from the AIL.
* We'll use the AIL lock to protect our counters as well as
* the removal from the AIL.
*/
void
xfs_efi_release(xfs_efi_log_item_t *efip,
uint nextents)
{
struct xfs_ail *ailp = efip->efi_item.li_ailp;
int extents_left;
ASSERT(efip->efi_next_extent > 0);
ASSERT(efip->efi_flags & XFS_EFI_COMMITTED);
spin_lock(&ailp->xa_lock);
ASSERT(efip->efi_next_extent >= nextents);
efip->efi_next_extent -= nextents;
extents_left = efip->efi_next_extent;
if (extents_left == 0) {
/* xfs_trans_ail_delete() drops the AIL lock. */
xfs_trans_ail_delete(ailp, (xfs_log_item_t *)efip);
xfs_efi_item_free(efip);
} else {
spin_unlock(&ailp->xa_lock);
}
}
/*
* like unpin only we have to also clear the xaction descriptor
* pointing the log item if we free the item. This routine duplicates
* unpin because efi_flags is protected by the AIL lock. Freeing
* the descriptor and then calling unpin would force us to drop the AIL
* lock which would open up a race condition.
*/
STATIC void
xfs_efi_item_unpin_remove(xfs_efi_log_item_t *efip, xfs_trans_t *tp)
{
struct xfs_ail *ailp = efip->efi_item.li_ailp;
xfs_log_item_desc_t *lidp;
spin_lock(&ailp->xa_lock);
if (efip->efi_flags & XFS_EFI_CANCELED) {
/*
* free the xaction descriptor pointing to this item
*/
lidp = xfs_trans_find_item(tp, (xfs_log_item_t *) efip);
xfs_trans_free_item(tp, lidp);
/* xfs_trans_ail_delete() drops the AIL lock. */
xfs_trans_ail_delete(ailp, (xfs_log_item_t *)efip);
xfs_efi_item_free(efip);
} else {
efip->efi_flags |= XFS_EFI_COMMITTED;
spin_unlock(&ailp->xa_lock);
}
}
/*
* This is the iodone() function for buffers which have been
* logged. It is called when they are eventually flushed out.
* It should remove the buf item from the AIL, and free the buf item.
* It is called by xfs_buf_iodone_callbacks() above which will take
* care of cleaning up the buffer itself.
*/
void
xfs_buf_iodone(
struct xfs_buf *bp,
struct xfs_log_item *lip)
{
struct xfs_ail *ailp = lip->li_ailp;
ASSERT(BUF_ITEM(lip)->bli_buf == bp);
xfs_buf_rele(bp);
/*
* If we are forcibly shutting down, this may well be
* off the AIL already. That's because we simulate the
* log-committed callbacks to unpin these buffers. Or we may never
* have put this item on AIL because of the transaction was
* aborted forcibly. xfs_trans_ail_delete() takes care of these.
*
* Either way, AIL is useless if we're forcing a shutdown.
*/
spin_lock(&ailp->xa_lock);
xfs_trans_ail_delete(ailp, lip, SHUTDOWN_CORRUPT_INCORE);
xfs_buf_item_free(BUF_ITEM(lip));
}
/*
* 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);
}
}
/*
* Release the buffer associated with the buf log item. If there is no dirty
* logged data associated with the buffer recorded in the buf log item, then
* free the buf log item and remove the reference to it in the buffer.
*
* This call ignores the recursion count. It is only called when the buffer
* should REALLY be unlocked, regardless of the recursion count.
*
* We unconditionally drop the transaction's reference to the log item. If the
* item was logged, then another reference was taken when it was pinned, so we
* can safely drop the transaction reference now. This also allows us to avoid
* potential races with the unpin code freeing the bli by not referencing the
* bli after we've dropped the reference count.
*
* If the XFS_BLI_HOLD flag is set in the buf log item, then free the log item
* if necessary but do not unlock the buffer. This is for support of
* xfs_trans_bhold(). Make sure the XFS_BLI_HOLD field is cleared if we don't
* free the item.
*/
STATIC void
xfs_buf_item_unlock(
struct xfs_log_item *lip)
{
struct xfs_buf_log_item *bip = BUF_ITEM(lip);
struct xfs_buf *bp = bip->bli_buf;
bool clean;
bool aborted;
int flags;
/* Clear the buffer's association with this transaction. */
bp->b_transp = NULL;
/*
* If this is a transaction abort, don't return early. Instead, allow
* the brelse to happen. Normally it would be done for stale
* (cancelled) buffers at unpin time, but we'll never go through the
* pin/unpin cycle if we abort inside commit.
*/
aborted = (lip->li_flags & XFS_LI_ABORTED) ? true : false;
/*
* Before possibly freeing the buf item, copy the per-transaction state
* so we can reference it safely later after clearing it from the
* buffer log item.
*/
flags = bip->bli_flags;
bip->bli_flags &= ~(XFS_BLI_LOGGED | XFS_BLI_HOLD | XFS_BLI_ORDERED);
/*
* If the buf item is marked stale, then don't do anything. We'll
* unlock the buffer and free the buf item when the buffer is unpinned
* for the last time.
*/
if (flags & XFS_BLI_STALE) {
trace_xfs_buf_item_unlock_stale(bip);
ASSERT(bip->__bli_format.blf_flags & XFS_BLF_CANCEL);
if (!aborted) {
atomic_dec(&bip->bli_refcount);
return;
}
}
trace_xfs_buf_item_unlock(bip);
/*
* If the buf item isn't tracking any data, free it, otherwise drop the
* reference we hold to it. If we are aborting the transaction, this may
* be the only reference to the buf item, so we free it anyway
* regardless of whether it is dirty or not. A dirty abort implies a
* shutdown, anyway.
*
* Ordered buffers are dirty but may have no recorded changes, so ensure
* we only release clean items here.
*/
clean = (flags & XFS_BLI_DIRTY) ? false : true;
if (clean) {
int i;
for (i = 0; i < bip->bli_format_count; i++) {
if (!xfs_bitmap_empty(bip->bli_formats[i].blf_data_map,
bip->bli_formats[i].blf_map_size)) {
clean = false;
break;
}
}
}
/*
* Clean buffers, by definition, cannot be in the AIL. However, aborted
* buffers may be dirty and hence in the AIL. Therefore if we are
* aborting a buffer and we've just taken the last refernce away, we
* have to check if it is in the AIL before freeing it. We need to free
* it in this case, because an aborted transaction has already shut the
* filesystem down and this is the last chance we will have to do so.
*/
if (atomic_dec_and_test(&bip->bli_refcount)) {
if (clean)
xfs_buf_item_relse(bp);
else if (aborted) {
ASSERT(XFS_FORCED_SHUTDOWN(lip->li_mountp));
if (lip->li_flags & XFS_LI_IN_AIL) {
spin_lock(&lip->li_ailp->xa_lock);
xfs_trans_ail_delete(lip->li_ailp, lip,
SHUTDOWN_LOG_IO_ERROR);
}
xfs_buf_item_relse(bp);
}
}
if (!(flags & XFS_BLI_HOLD))
xfs_buf_relse(bp);
}
/*
* 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(XFS_BUF_FSPRIVATE(bp, xfs_buf_log_item_t *) == 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_VALUSEMA(bp) <= 0);
ASSERT(!(XFS_BUF_ISDELAYWRITE(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.
*/
XFS_BUF_SET_FSPRIVATE2(bp, 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);
XFS_BUF_SET_FSPRIVATE(bp, NULL);
XFS_BUF_CLR_IODONE_FUNC(bp);
} else {
spin_lock(&ailp->xa_lock);
xfs_trans_ail_delete(ailp, (xfs_log_item_t *)bip);
xfs_buf_item_relse(bp);
ASSERT(XFS_BUF_FSPRIVATE(bp, void *) == NULL);
}
xfs_buf_relse(bp);
}
/*
* Write a modified dquot to disk.
* The dquot must be locked and the flush lock too taken by caller.
* The flush lock will not be unlocked until the dquot reaches the disk,
* but the dquot is free to be unlocked and modified by the caller
* in the interim. Dquot is still locked on return. This behavior is
* identical to that of inodes.
*/
int
xfs_qm_dqflush(
struct xfs_dquot *dqp,
struct xfs_buf **bpp)
{
struct xfs_mount *mp = dqp->q_mount;
struct xfs_buf *bp;
struct xfs_disk_dquot *ddqp;
int error;
ASSERT(XFS_DQ_IS_LOCKED(dqp));
ASSERT(!completion_done(&dqp->q_flush));
trace_xfs_dqflush(dqp);
*bpp = NULL;
xfs_qm_dqunpin_wait(dqp);
/*
* This may have been unpinned because the filesystem is shutting
* down forcibly. If that's the case we must not write this dquot
* to disk, because the log record didn't make it to disk.
*
* We also have to remove the log item from the AIL in this case,
* as we wait for an emptry AIL as part of the unmount process.
*/
if (XFS_FORCED_SHUTDOWN(mp)) {
struct xfs_log_item *lip = &dqp->q_logitem.qli_item;
dqp->dq_flags &= ~XFS_DQ_DIRTY;
spin_lock(&mp->m_ail->xa_lock);
if (lip->li_flags & XFS_LI_IN_AIL)
xfs_trans_ail_delete(mp->m_ail, lip,
SHUTDOWN_CORRUPT_INCORE);
else
spin_unlock(&mp->m_ail->xa_lock);
error = XFS_ERROR(EIO);
goto out_unlock;
}
/*
* Get the buffer containing the on-disk dquot
*/
error = xfs_trans_read_buf(mp, NULL, mp->m_ddev_targp, dqp->q_blkno,
mp->m_quotainfo->qi_dqchunklen, 0, &bp, NULL);
if (error)
goto out_unlock;
/*
* Calculate the location of the dquot inside the buffer.
*/
ddqp = bp->b_addr + dqp->q_bufoffset;
/*
* A simple sanity check in case we got a corrupted dquot..
*/
error = xfs_dqcheck(mp, &dqp->q_core, be32_to_cpu(ddqp->d_id), 0,
XFS_QMOPT_DOWARN, "dqflush (incore copy)");
if (error) {
xfs_buf_relse(bp);
xfs_dqfunlock(dqp);
xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE);
return XFS_ERROR(EIO);
}
/* This is the only portion of data that needs to persist */
memcpy(ddqp, &dqp->q_core, sizeof(xfs_disk_dquot_t));
/*
* Clear the dirty field and remember the flush lsn for later use.
*/
dqp->dq_flags &= ~XFS_DQ_DIRTY;
xfs_trans_ail_copy_lsn(mp->m_ail, &dqp->q_logitem.qli_flush_lsn,
&dqp->q_logitem.qli_item.li_lsn);
/*
* copy the lsn into the on-disk dquot now while we have the in memory
* dquot here. This can't be done later in the write verifier as we
* can't get access to the log item at that point in time.
*
* We also calculate the CRC here so that the on-disk dquot in the
* buffer always has a valid CRC. This ensures there is no possibility
* of a dquot without an up-to-date CRC getting to disk.
*/
if (xfs_sb_version_hascrc(&mp->m_sb)) {
struct xfs_dqblk *dqb = (struct xfs_dqblk *)ddqp;
dqb->dd_lsn = cpu_to_be64(dqp->q_logitem.qli_item.li_lsn);
xfs_update_cksum((char *)dqb, sizeof(struct xfs_dqblk),
XFS_DQUOT_CRC_OFF);
}
/*
* Attach an iodone routine so that we can remove this dquot from the
* AIL and release the flush lock once the dquot is synced to disk.
*/
xfs_buf_attach_iodone(bp, xfs_qm_dqflush_done,
&dqp->q_logitem.qli_item);
/*
* If the buffer is pinned then push on the log so we won't
* get stuck waiting in the write for too long.
*/
if (xfs_buf_ispinned(bp)) {
trace_xfs_dqflush_force(dqp);
xfs_log_force(mp, 0);
}
trace_xfs_dqflush_done(dqp);
*bpp = bp;
return 0;
out_unlock:
xfs_dqfunlock(dqp);
return XFS_ERROR(EIO);
}
