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)
flags = XBF_LOCK | XBF_MAPPED;
bp = xfs_buf_read(target, blkno, len, flags);
if (!bp)
return XFS_ERROR(EIO);
error = bp->b_error;
if (!error && !XFS_FORCED_SHUTDOWN(mp)) {
*bpp = bp;
} else {
*bpp = NULL;
if (error) {
xfs_buf_ioerror_alert(bp, __func__);
} else {
error = XFS_ERROR(EIO);
}
if (bp) {
XFS_BUF_UNDONE(bp);
xfs_buf_stale(bp);
xfs_buf_relse(bp);
}
}
return (error);
}
/*
* 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);
}
}
/*
* This is the iodone() function for buffers which have had callbacks
* attached to them by xfs_buf_attach_iodone(). It should remove each
* log item from the buffer's list and call the callback of each in turn.
* When done, the buffer's fsprivate field is set to NULL and the buffer
* is unlocked with a call to iodone().
*/
void
xfs_buf_iodone_callbacks(
struct xfs_buf *bp)
{
struct xfs_log_item *lip = bp->b_fspriv;
struct xfs_mount *mp = lip->li_mountp;
static ulong lasttime;
static xfs_buftarg_t *lasttarg;
if (likely(!xfs_buf_geterror(bp)))
goto do_callbacks;
/*
* If we've already decided to shutdown the filesystem because of
* I/O errors, there's no point in giving this a retry.
*/
if (XFS_FORCED_SHUTDOWN(mp)) {
xfs_buf_stale(bp);
XFS_BUF_DONE(bp);
trace_xfs_buf_item_iodone(bp, _RET_IP_);
goto do_callbacks;
}
if (bp->b_target != lasttarg ||
time_after(jiffies, (lasttime + 5*HZ))) {
lasttime = jiffies;
xfs_buf_ioerror_alert(bp, __func__);
}
lasttarg = bp->b_target;
/*
* If the write was asynchronous then no one will be looking for the
* error. Clear the error state and write the buffer out again.
*
* XXX: This helps against transient write errors, but we need to find
* a way to shut the filesystem down if the writes keep failing.
*
* In practice we'll shut the filesystem down soon as non-transient
* erorrs tend to affect the whole device and a failing log write
* will make us give up. But we really ought to do better here.
*/
if (XFS_BUF_ISASYNC(bp)) {
ASSERT(bp->b_iodone != NULL);
trace_xfs_buf_item_iodone_async(bp, _RET_IP_);
xfs_buf_ioerror(bp, 0); /* errno of 0 unsets the flag */
if (!XFS_BUF_ISSTALE(bp)) {
bp->b_flags |= XBF_WRITE | XBF_ASYNC | XBF_DONE;
xfs_buf_iorequest(bp);
} else {
xfs_buf_relse(bp);
}
return;
}
/*
* If the write of the buffer was synchronous, we want to make
* sure to return the error to the caller of xfs_bwrite().
*/
xfs_buf_stale(bp);
XFS_BUF_DONE(bp);
trace_xfs_buf_error_relse(bp, _RET_IP_);
do_callbacks:
xfs_buf_do_callbacks(bp);
bp->b_fspriv = NULL;
bp->b_iodone = NULL;
xfs_buf_ioend(bp, 0);
}
/*
* Remove the value associated with an attribute by deleting the
* out-of-line buffer that it is stored on.
*/
int
xfs_attr_rmtval_remove(
struct xfs_da_args *args)
{
struct xfs_mount *mp = args->dp->i_mount;
xfs_dablk_t lblkno;
int blkcnt;
int error;
int done;
trace_xfs_attr_rmtval_remove(args);
/*
* Roll through the "value", invalidating the attribute value's blocks.
*/
lblkno = args->rmtblkno;
blkcnt = args->rmtblkcnt;
while (blkcnt > 0) {
struct xfs_bmbt_irec map;
struct xfs_buf *bp;
xfs_daddr_t dblkno;
int dblkcnt;
int nmap;
/*
* Try to remember where we decided to put the value.
*/
nmap = 1;
error = xfs_bmapi_read(args->dp, (xfs_fileoff_t)lblkno,
blkcnt, &map, &nmap, XFS_BMAPI_ATTRFORK);
if (error)
return error;
ASSERT(nmap == 1);
ASSERT((map.br_startblock != DELAYSTARTBLOCK) &&
(map.br_startblock != HOLESTARTBLOCK));
dblkno = XFS_FSB_TO_DADDR(mp, map.br_startblock),
dblkcnt = XFS_FSB_TO_BB(mp, map.br_blockcount);
/*
* If the "remote" value is in the cache, remove it.
*/
bp = xfs_incore(mp->m_ddev_targp, dblkno, dblkcnt, XBF_TRYLOCK);
if (bp) {
xfs_buf_stale(bp);
xfs_buf_relse(bp);
bp = NULL;
}
lblkno += map.br_blockcount;
blkcnt -= map.br_blockcount;
}
/*
* Keep de-allocating extents until the remote-value region is gone.
*/
lblkno = args->rmtblkno;
blkcnt = args->rmtblkcnt;
done = 0;
while (!done) {
int committed;
xfs_bmap_init(args->flist, args->firstblock);
error = xfs_bunmapi(args->trans, args->dp, lblkno, blkcnt,
XFS_BMAPI_ATTRFORK | XFS_BMAPI_METADATA,
1, args->firstblock, args->flist,
&done);
if (!error) {
error = xfs_bmap_finish(&args->trans, args->flist,
&committed);
}
if (error) {
ASSERT(committed);
args->trans = NULL;
xfs_bmap_cancel(args->flist);
return error;
}
/*
* bmap_finish() may have committed the last trans and started
* a new one. We need the inode to be in all transactions.
*/
if (committed)
xfs_trans_ijoin(args->trans, args->dp, 0);
/*
* Close out trans and start the next one in the chain.
*/
error = xfs_trans_roll(&args->trans, args->dp);
if (error)
return error;
}
return 0;
}
/*
* Remove the value associated with an attribute by deleting the
* out-of-line buffer that it is stored on.
*/
int
xfs_attr_rmtval_remove(
struct xfs_da_args *args)
{
struct xfs_mount *mp = args->dp->i_mount;
xfs_dablk_t lblkno;
int blkcnt;
int error;
int done;
trace_xfs_attr_rmtval_remove(args);
/*
* Roll through the "value", invalidating the attribute value's blocks.
*/
lblkno = args->rmtblkno;
blkcnt = args->rmtblkcnt;
while (blkcnt > 0) {
struct xfs_bmbt_irec map;
struct xfs_buf *bp;
xfs_daddr_t dblkno;
int dblkcnt;
int nmap;
/*
* Try to remember where we decided to put the value.
*/
nmap = 1;
error = xfs_bmapi_read(args->dp, (xfs_fileoff_t)lblkno,
blkcnt, &map, &nmap, XFS_BMAPI_ATTRFORK);
if (error)
return error;
ASSERT(nmap == 1);
ASSERT((map.br_startblock != DELAYSTARTBLOCK) &&
(map.br_startblock != HOLESTARTBLOCK));
dblkno = XFS_FSB_TO_DADDR(mp, map.br_startblock),
dblkcnt = XFS_FSB_TO_BB(mp, map.br_blockcount);
/*
* If the "remote" value is in the cache, remove it.
*/
bp = xfs_buf_incore(mp->m_ddev_targp, dblkno, dblkcnt, XBF_TRYLOCK);
if (bp) {
xfs_buf_stale(bp);
xfs_buf_relse(bp);
bp = NULL;
}
lblkno += map.br_blockcount;
blkcnt -= map.br_blockcount;
}
/*
* Keep de-allocating extents until the remote-value region is gone.
*/
lblkno = args->rmtblkno;
blkcnt = args->rmtblkcnt;
done = 0;
while (!done) {
error = xfs_bunmapi(args->trans, args->dp, lblkno, blkcnt,
XFS_BMAPI_ATTRFORK, 1, &done);
if (error)
goto out_defer_cancel;
error = xfs_defer_finish(&args->trans);
if (error)
return error;
/*
* Close out trans and start the next one in the chain.
*/
error = xfs_trans_roll_inode(&args->trans, args->dp);
if (error)
return error;
}
return 0;
out_defer_cancel:
xfs_defer_cancel(args->trans);
return error;
}