STATIC uint
xfs_buf_item_push(
struct xfs_log_item *lip,
struct list_head *buffer_list)
{
struct xfs_buf_log_item *bip = BUF_ITEM(lip);
struct xfs_buf *bp = bip->bli_buf;
uint rval = XFS_ITEM_SUCCESS;
if (xfs_buf_ispinned(bp))
return XFS_ITEM_PINNED;
if (!xfs_buf_trylock(bp)) {
/*
* If we have just raced with a buffer being pinned and it has
* been marked stale, we could end up stalling until someone else
* issues a log force to unpin the stale buffer. Check for the
* race condition here so xfsaild recognizes the buffer is pinned
* and queues a log force to move it along.
*/
if (xfs_buf_ispinned(bp))
return XFS_ITEM_PINNED;
return XFS_ITEM_LOCKED;
}
ASSERT(!(bip->bli_flags & XFS_BLI_STALE));
trace_xfs_buf_item_push(bip);
if (!xfs_buf_delwri_queue(bp, buffer_list))
rval = XFS_ITEM_FLUSHING;
xfs_buf_unlock(bp);
return rval;
}
/*
* This is called to fill in the vector of log iovecs for the
* given log buf item. It fills the first entry with a buf log
* format structure, and the rest point to contiguous chunks
* within the buffer.
*/
STATIC void
xfs_buf_item_format(
struct xfs_log_item *lip,
struct xfs_log_vec *lv)
{
struct xfs_buf_log_item *bip = BUF_ITEM(lip);
struct xfs_buf *bp = bip->bli_buf;
struct xfs_log_iovec *vecp = NULL;
uint offset = 0;
int i;
ASSERT(atomic_read(&bip->bli_refcount) > 0);
ASSERT((bip->bli_flags & XFS_BLI_LOGGED) ||
(bip->bli_flags & XFS_BLI_STALE));
/*
* If it is an inode buffer, transfer the in-memory state to the
* format flags and clear the in-memory state.
*
* For buffer based inode allocation, we do not transfer
* this state if the inode buffer allocation has not yet been committed
* to the log as setting the XFS_BLI_INODE_BUF flag will prevent
* correct replay of the inode allocation.
*
* For icreate item based inode allocation, the buffers aren't written
* to the journal during allocation, and hence we should always tag the
* buffer as an inode buffer so that the correct unlinked list replay
* occurs during recovery.
*/
if (bip->bli_flags & XFS_BLI_INODE_BUF) {
if (xfs_sb_version_hascrc(&lip->li_mountp->m_sb) ||
!((bip->bli_flags & XFS_BLI_INODE_ALLOC_BUF) &&
xfs_log_item_in_current_chkpt(lip)))
bip->__bli_format.blf_flags |= XFS_BLF_INODE_BUF;
bip->bli_flags &= ~XFS_BLI_INODE_BUF;
}
if ((bip->bli_flags & (XFS_BLI_ORDERED|XFS_BLI_STALE)) ==
XFS_BLI_ORDERED) {
/*
* The buffer has been logged just to order it. It is not being
* included in the transaction commit, so don't format it.
*/
trace_xfs_buf_item_format_ordered(bip);
return;
}
for (i = 0; i < bip->bli_format_count; i++) {
xfs_buf_item_format_segment(bip, lv, &vecp, offset,
&bip->bli_formats[i]);
offset += bp->b_maps[i].bm_len;
}
/*
* Check to make sure everything is consistent.
*/
trace_xfs_buf_item_format(bip);
}
/*
* This returns the number of log iovecs needed to log the given buf log item.
*
* It calculates this as 1 iovec for the buf log format structure and 1 for each
* stretch of non-contiguous chunks to be logged. Contiguous chunks are logged
* in a single iovec.
*
* Discontiguous buffers need a format structure per region that that is being
* logged. This makes the changes in the buffer appear to log recovery as though
* they came from separate buffers, just like would occur if multiple buffers
* were used instead of a single discontiguous buffer. This enables
* discontiguous buffers to be in-memory constructs, completely transparent to
* what ends up on disk.
*
* If the XFS_BLI_STALE flag has been set, then log nothing but the buf log
* format structures.
*/
STATIC void
xfs_buf_item_size(
struct xfs_log_item *lip,
int *nvecs,
int *nbytes)
{
struct xfs_buf_log_item *bip = BUF_ITEM(lip);
int i;
ASSERT(atomic_read(&bip->bli_refcount) > 0);
if (bip->bli_flags & XFS_BLI_STALE) {
/*
* The buffer is stale, so all we need to log
* is the buf log format structure with the
* cancel flag in it.
*/
trace_xfs_buf_item_size_stale(bip);
ASSERT(bip->__bli_format.blf_flags & XFS_BLF_CANCEL);
*nvecs += bip->bli_format_count;
for (i = 0; i < bip->bli_format_count; i++) {
*nbytes += xfs_buf_log_format_size(&bip->bli_formats[i]);
}
return;
}
ASSERT(bip->bli_flags & XFS_BLI_LOGGED);
if (bip->bli_flags & XFS_BLI_ORDERED) {
/*
* The buffer has been logged just to order it.
* It is not being included in the transaction
* commit, so no vectors are used at all.
*/
trace_xfs_buf_item_size_ordered(bip);
*nvecs = XFS_LOG_VEC_ORDERED;
return;
}
/*
* the vector count is based on the number of buffer vectors we have
* dirty bits in. This will only be greater than one when we have a
* compound buffer with more than one segment dirty. Hence for compound
* buffers we need to track which segment the dirty bits correspond to,
* and when we move from one segment to the next increment the vector
* count for the extra buf log format structure that will need to be
* written.
*/
for (i = 0; i < bip->bli_format_count; i++) {
xfs_buf_item_size_segment(bip, &bip->bli_formats[i],
nvecs, nbytes);
}
trace_xfs_buf_item_size(bip);
}
/*
* This is called to find out where the oldest active copy of the
* buf log item in the on disk log resides now that the last log
* write of it completed at the given lsn.
* We always re-log all the dirty data in a buffer, so usually the
* latest copy in the on disk log is the only one that matters. For
* those cases we simply return the given lsn.
*
* The one exception to this is for buffers full of newly allocated
* inodes. These buffers are only relogged with the XFS_BLI_INODE_BUF
* flag set, indicating that only the di_next_unlinked fields from the
* inodes in the buffers will be replayed during recovery. If the
* original newly allocated inode images have not yet been flushed
* when the buffer is so relogged, then we need to make sure that we
* keep the old images in the 'active' portion of the log. We do this
* by returning the original lsn of that transaction here rather than
* the current one.
*/
STATIC xfs_lsn_t
xfs_buf_item_committed(
struct xfs_log_item *lip,
xfs_lsn_t lsn)
{
struct xfs_buf_log_item *bip = BUF_ITEM(lip);
trace_xfs_buf_item_committed(bip);
if ((bip->bli_flags & XFS_BLI_INODE_ALLOC_BUF) && lip->li_lsn != 0)
return lip->li_lsn;
return lsn;
}
/*
* This is called to pin the buffer associated with the buf log item in memory
* so it cannot be written out.
*
* We also always take a reference to the buffer log item here so that the bli
* is held while the item is pinned in memory. This means that we can
* unconditionally drop the reference count a transaction holds when the
* transaction is completed.
*/
STATIC void
xfs_buf_item_pin(
struct xfs_log_item *lip)
{
struct xfs_buf_log_item *bip = BUF_ITEM(lip);
ASSERT(atomic_read(&bip->bli_refcount) > 0);
ASSERT((bip->bli_flags & XFS_BLI_LOGGED) ||
(bip->bli_flags & XFS_BLI_STALE));
trace_xfs_buf_item_pin(bip);
atomic_inc(&bip->bli_refcount);
atomic_inc(&bip->bli_buf->b_pin_count);
}
/*
* 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));
}
STATIC uint
xfs_buf_item_push(
struct xfs_log_item *lip,
struct list_head *buffer_list)
{
struct xfs_buf_log_item *bip = BUF_ITEM(lip);
struct xfs_buf *bp = bip->bli_buf;
uint rval = XFS_ITEM_SUCCESS;
if (xfs_buf_ispinned(bp))
return XFS_ITEM_PINNED;
if (!xfs_buf_trylock(bp)) {
/*
* If we have just raced with a buffer being pinned and it has
* been marked stale, we could end up stalling until someone else
* issues a log force to unpin the stale buffer. Check for the
* race condition here so xfsaild recognizes the buffer is pinned
* and queues a log force to move it along.
*/
if (xfs_buf_ispinned(bp))
return XFS_ITEM_PINNED;
return XFS_ITEM_LOCKED;
}
ASSERT(!(bip->bli_flags & XFS_BLI_STALE));
trace_xfs_buf_item_push(bip);
/* has a previous flush failed due to IO errors? */
if ((bp->b_flags & XBF_WRITE_FAIL) &&
___ratelimit(&xfs_buf_write_fail_rl_state, "XFS:")) {
xfs_warn(bp->b_target->bt_mount,
"Detected failing async write on buffer block 0x%llx. Retrying async write.\n",
(long long)bp->b_bn);
}
if (!xfs_buf_delwri_queue(bp, buffer_list))
rval = XFS_ITEM_FLUSHING;
xfs_buf_unlock(bp);
return rval;
}
/*
* This is called to fill in the vector of log iovecs for the
* given log buf item. It fills the first entry with a buf log
* format structure, and the rest point to contiguous chunks
* within the buffer.
*/
STATIC void
xfs_buf_item_format(
struct xfs_log_item *lip,
struct xfs_log_iovec *vecp)
{
struct xfs_buf_log_item *bip = BUF_ITEM(lip);
struct xfs_buf *bp = bip->bli_buf;
uint offset = 0;
int i;
ASSERT(atomic_read(&bip->bli_refcount) > 0);
ASSERT((bip->bli_flags & XFS_BLI_LOGGED) ||
(bip->bli_flags & XFS_BLI_STALE));
/*
* If it is an inode buffer, transfer the in-memory state to the
* format flags and clear the in-memory state. We do not transfer
* this state if the inode buffer allocation has not yet been committed
* to the log as setting the XFS_BLI_INODE_BUF flag will prevent
* correct replay of the inode allocation.
*/
if (bip->bli_flags & XFS_BLI_INODE_BUF) {
if (!((bip->bli_flags & XFS_BLI_INODE_ALLOC_BUF) &&
xfs_log_item_in_current_chkpt(lip)))
bip->__bli_format.blf_flags |= XFS_BLF_INODE_BUF;
bip->bli_flags &= ~XFS_BLI_INODE_BUF;
}
for (i = 0; i < bip->bli_format_count; i++) {
vecp = xfs_buf_item_format_segment(bip, vecp, offset,
&bip->bli_formats[i]);
offset += bp->b_maps[i].bm_len;
}
/*
* Check to make sure everything is consistent.
*/
trace_xfs_buf_item_format(bip);
xfs_buf_item_log_check(bip);
}
/*
* This returns the number of log iovecs needed to log the given buf log item.
*
* It calculates this as 1 iovec for the buf log format structure and 1 for each
* stretch of non-contiguous chunks to be logged. Contiguous chunks are logged
* in a single iovec.
*
* Discontiguous buffers need a format structure per region that that is being
* logged. This makes the changes in the buffer appear to log recovery as though
* they came from separate buffers, just like would occur if multiple buffers
* were used instead of a single discontiguous buffer. This enables
* discontiguous buffers to be in-memory constructs, completely transparent to
* what ends up on disk.
*
* If the XFS_BLI_STALE flag has been set, then log nothing but the buf log
* format structures.
*/
STATIC uint
xfs_buf_item_size(
struct xfs_log_item *lip)
{
struct xfs_buf_log_item *bip = BUF_ITEM(lip);
uint nvecs;
int i;
ASSERT(atomic_read(&bip->bli_refcount) > 0);
if (bip->bli_flags & XFS_BLI_STALE) {
/*
* The buffer is stale, so all we need to log
* is the buf log format structure with the
* cancel flag in it.
*/
trace_xfs_buf_item_size_stale(bip);
ASSERT(bip->__bli_format.blf_flags & XFS_BLF_CANCEL);
return bip->bli_format_count;
}
ASSERT(bip->bli_flags & XFS_BLI_LOGGED);
/*
* the vector count is based on the number of buffer vectors we have
* dirty bits in. This will only be greater than one when we have a
* compound buffer with more than one segment dirty. Hence for compound
* buffers we need to track which segment the dirty bits correspond to,
* and when we move from one segment to the next increment the vector
* count for the extra buf log format structure that will need to be
* written.
*/
nvecs = 0;
for (i = 0; i < bip->bli_format_count; i++) {
nvecs += xfs_buf_item_size_segment(bip, &bip->bli_formats[i]);
}
trace_xfs_buf_item_size(bip);
return nvecs;
}
STATIC uint
xfs_buf_item_push(
struct xfs_log_item *lip,
struct list_head *buffer_list)
{
struct xfs_buf_log_item *bip = BUF_ITEM(lip);
struct xfs_buf *bp = bip->bli_buf;
uint rval = XFS_ITEM_SUCCESS;
if (xfs_buf_ispinned(bp))
return XFS_ITEM_PINNED;
if (!xfs_buf_trylock(bp))
return XFS_ITEM_LOCKED;
ASSERT(!(bip->bli_flags & XFS_BLI_STALE));
trace_xfs_buf_item_push(bip);
if (!xfs_buf_delwri_queue(bp, buffer_list))
rval = XFS_ITEM_FLUSHING;
xfs_buf_unlock(bp);
return rval;
}
/*
* 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;
int aborted, clean, i;
uint hold;
/* 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) != 0;
/*
* Before possibly freeing the buf item, determine if we should
* release the buffer at the end of this routine.
*/
hold = bip->bli_flags & XFS_BLI_HOLD;
/* Clear the per transaction state. */
bip->bli_flags &= ~(XFS_BLI_LOGGED | XFS_BLI_HOLD);
/*
* 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 (bip->bli_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.
*/
clean = 1;
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 = 0;
break;
}
}
if (clean)
xfs_buf_item_relse(bp);
else if (aborted) {
if (atomic_dec_and_test(&bip->bli_refcount)) {
ASSERT(XFS_FORCED_SHUTDOWN(lip->li_mountp));
xfs_buf_item_relse(bp);
}
} else
atomic_dec(&bip->bli_refcount);
if (!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(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);
}
/*
* This is called to fill in the vector of log iovecs for the
* given log buf item. It fills the first entry with a buf log
* format structure, and the rest point to contiguous chunks
* within the buffer.
*/
STATIC void
xfs_buf_item_format(
struct xfs_log_item *lip,
struct xfs_log_iovec *vecp)
{
struct xfs_buf_log_item *bip = BUF_ITEM(lip);
struct xfs_buf *bp = bip->bli_buf;
uint base_size;
uint nvecs;
int first_bit;
int last_bit;
int next_bit;
uint nbits;
uint buffer_offset;
ASSERT(atomic_read(&bip->bli_refcount) > 0);
ASSERT((bip->bli_flags & XFS_BLI_LOGGED) ||
(bip->bli_flags & XFS_BLI_STALE));
/*
* The size of the base structure is the size of the
* declared structure plus the space for the extra words
* of the bitmap. We subtract one from the map size, because
* the first element of the bitmap is accounted for in the
* size of the base structure.
*/
base_size =
(uint)(sizeof(xfs_buf_log_format_t) +
((bip->bli_format.blf_map_size - 1) * sizeof(uint)));
vecp->i_addr = &bip->bli_format;
vecp->i_len = base_size;
vecp->i_type = XLOG_REG_TYPE_BFORMAT;
vecp++;
nvecs = 1;
/*
* If it is an inode buffer, transfer the in-memory state to the
* format flags and clear the in-memory state. We do not transfer
* this state if the inode buffer allocation has not yet been committed
* to the log as setting the XFS_BLI_INODE_BUF flag will prevent
* correct replay of the inode allocation.
*/
if (bip->bli_flags & XFS_BLI_INODE_BUF) {
if (!((bip->bli_flags & XFS_BLI_INODE_ALLOC_BUF) &&
xfs_log_item_in_current_chkpt(lip)))
bip->bli_format.blf_flags |= XFS_BLF_INODE_BUF;
bip->bli_flags &= ~XFS_BLI_INODE_BUF;
}
if (bip->bli_flags & XFS_BLI_STALE) {
/*
* The buffer is stale, so all we need to log
* is the buf log format structure with the
* cancel flag in it.
*/
trace_xfs_buf_item_format_stale(bip);
ASSERT(bip->bli_format.blf_flags & XFS_BLF_CANCEL);
bip->bli_format.blf_size = nvecs;
return;
}
/*
* Fill in an iovec for each set of contiguous chunks.
*/
first_bit = xfs_next_bit(bip->bli_format.blf_data_map,
bip->bli_format.blf_map_size, 0);
ASSERT(first_bit != -1);
last_bit = first_bit;
nbits = 1;
for (;;) {
/*
* This takes the bit number to start looking from and
* returns the next set bit from there. It returns -1
* if there are no more bits set or the start bit is
* beyond the end of the bitmap.
*/
next_bit = xfs_next_bit(bip->bli_format.blf_data_map,
bip->bli_format.blf_map_size,
(uint)last_bit + 1);
/*
* If we run out of bits fill in the last iovec and get
* out of the loop.
* Else if we start a new set of bits then fill in the
* iovec for the series we were looking at and start
* counting the bits in the new one.
* Else we're still in the same set of bits so just
* keep counting and scanning.
*/
if (next_bit == -1) {
buffer_offset = first_bit * XFS_BLF_CHUNK;
vecp->i_addr = xfs_buf_offset(bp, buffer_offset);
vecp->i_len = nbits * XFS_BLF_CHUNK;
vecp->i_type = XLOG_REG_TYPE_BCHUNK;
nvecs++;
break;
} else if (next_bit != last_bit + 1) {
buffer_offset = first_bit * XFS_BLF_CHUNK;
vecp->i_addr = xfs_buf_offset(bp, buffer_offset);
vecp->i_len = nbits * XFS_BLF_CHUNK;
vecp->i_type = XLOG_REG_TYPE_BCHUNK;
nvecs++;
vecp++;
first_bit = next_bit;
last_bit = next_bit;
nbits = 1;
} else if (xfs_buf_offset(bp, next_bit << XFS_BLF_SHIFT) !=
(xfs_buf_offset(bp, last_bit << XFS_BLF_SHIFT) +
XFS_BLF_CHUNK)) {
buffer_offset = first_bit * XFS_BLF_CHUNK;
vecp->i_addr = xfs_buf_offset(bp, buffer_offset);
vecp->i_len = nbits * XFS_BLF_CHUNK;
vecp->i_type = XLOG_REG_TYPE_BCHUNK;
/* You would think we need to bump the nvecs here too, but we do not
* this number is used by recovery, and it gets confused by the boundary
* split here
* nvecs++;
*/
vecp++;
first_bit = next_bit;
last_bit = next_bit;
nbits = 1;
} else {
last_bit++;
nbits++;
}
}
bip->bli_format.blf_size = nvecs;
/*
* Check to make sure everything is consistent.
*/
trace_xfs_buf_item_format(bip);
xfs_buf_item_log_check(bip);
}
/*
* This returns the number of log iovecs needed to log the
* given buf log item.
*
* It calculates this as 1 iovec for the buf log format structure
* and 1 for each stretch of non-contiguous chunks to be logged.
* Contiguous chunks are logged in a single iovec.
*
* If the XFS_BLI_STALE flag has been set, then log nothing.
*/
STATIC uint
xfs_buf_item_size(
struct xfs_log_item *lip)
{
struct xfs_buf_log_item *bip = BUF_ITEM(lip);
struct xfs_buf *bp = bip->bli_buf;
uint nvecs;
int next_bit;
int last_bit;
ASSERT(atomic_read(&bip->bli_refcount) > 0);
if (bip->bli_flags & XFS_BLI_STALE) {
/*
* The buffer is stale, so all we need to log
* is the buf log format structure with the
* cancel flag in it.
*/
trace_xfs_buf_item_size_stale(bip);
ASSERT(bip->bli_format.blf_flags & XFS_BLF_CANCEL);
return 1;
}
ASSERT(bip->bli_flags & XFS_BLI_LOGGED);
nvecs = 1;
last_bit = xfs_next_bit(bip->bli_format.blf_data_map,
bip->bli_format.blf_map_size, 0);
ASSERT(last_bit != -1);
nvecs++;
while (last_bit != -1) {
/*
* This takes the bit number to start looking from and
* returns the next set bit from there. It returns -1
* if there are no more bits set or the start bit is
* beyond the end of the bitmap.
*/
next_bit = xfs_next_bit(bip->bli_format.blf_data_map,
bip->bli_format.blf_map_size,
last_bit + 1);
/*
* If we run out of bits, leave the loop,
* else if we find a new set of bits bump the number of vecs,
* else keep scanning the current set of bits.
*/
if (next_bit == -1) {
last_bit = -1;
} else if (next_bit != last_bit + 1) {
last_bit = next_bit;
nvecs++;
} else if (xfs_buf_offset(bp, next_bit * XFS_BLF_CHUNK) !=
(xfs_buf_offset(bp, last_bit * XFS_BLF_CHUNK) +
XFS_BLF_CHUNK)) {
last_bit = next_bit;
nvecs++;
} else {
last_bit++;
}
}
trace_xfs_buf_item_size(bip);
return nvecs;
}