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 gets called by xfs_trans_push_ail(), when IOP_TRYLOCK
* failed to get the inode flush lock but did get the inode locked SHARED.
* Here we're trying to see if the inode buffer is incore, and if so whether it's
* marked delayed write. If that's the case, we'll promote it and that will
* allow the caller to write the buffer by triggering the xfsbufd to run.
*/
STATIC bool
xfs_inode_item_pushbuf(
struct xfs_log_item *lip)
{
struct xfs_inode_log_item *iip = INODE_ITEM(lip);
struct xfs_inode *ip = iip->ili_inode;
struct xfs_buf *bp;
bool ret = true;
ASSERT(xfs_isilocked(ip, XFS_ILOCK_SHARED));
/*
* If a flush is not in progress anymore, chances are that the
* inode was taken off the AIL. So, just get out.
*/
if (completion_done(&ip->i_flush) ||
!(lip->li_flags & XFS_LI_IN_AIL)) {
xfs_iunlock(ip, XFS_ILOCK_SHARED);
return true;
}
bp = xfs_incore(ip->i_mount->m_ddev_targp, iip->ili_format.ilf_blkno,
iip->ili_format.ilf_len, XBF_TRYLOCK);
xfs_iunlock(ip, XFS_ILOCK_SHARED);
if (!bp)
return true;
if (XFS_BUF_ISDELAYWRITE(bp))
xfs_buf_delwri_promote(bp);
if (xfs_buf_ispinned(bp))
ret = false;
xfs_buf_relse(bp);
return ret;
}
/*
* This is called when IOP_TRYLOCK returns XFS_ITEM_PUSHBUF to indicate that
* the dquot is locked by us, but the flush lock isn't. So, here we are
* going to see if the relevant dquot buffer is incore, waiting on DELWRI.
* If so, we want to push it out to help us take this item off the AIL as soon
* as possible.
*
* We must not be holding the AIL lock at this point. Calling incore() to
* search the buffer cache can be a time consuming thing, and AIL lock is a
* spinlock.
*/
STATIC bool
xfs_qm_dquot_logitem_pushbuf(
struct xfs_log_item *lip)
{
struct xfs_dq_logitem *qlip = DQUOT_ITEM(lip);
struct xfs_dquot *dqp = qlip->qli_dquot;
struct xfs_buf *bp;
bool ret = true;
ASSERT(XFS_DQ_IS_LOCKED(dqp));
/*
* If flushlock isn't locked anymore, chances are that the
* inode flush completed and the inode was taken off the AIL.
* So, just get out.
*/
if (completion_done(&dqp->q_flush) ||
!(lip->li_flags & XFS_LI_IN_AIL)) {
xfs_dqunlock(dqp);
return true;
}
bp = xfs_incore(dqp->q_mount->m_ddev_targp, qlip->qli_format.qlf_blkno,
dqp->q_mount->m_quotainfo->qi_dqchunklen, XBF_TRYLOCK);
xfs_dqunlock(dqp);
if (!bp)
return true;
if (XFS_BUF_ISDELAYWRITE(bp))
xfs_buf_delwri_promote(bp);
if (xfs_buf_ispinned(bp))
ret = false;
xfs_buf_relse(bp);
return ret;
}
/*
* Give the buffer a little push if it is incore and
* wait on the flush lock.
*/
void
xfs_dqflock_pushbuf_wait(
xfs_dquot_t *dqp)
{
xfs_mount_t *mp = dqp->q_mount;
xfs_buf_t *bp;
/*
* Check to see if the dquot has been flushed delayed
* write. If so, grab its buffer and send it
* out immediately. We'll be able to acquire
* the flush lock when the I/O completes.
*/
bp = xfs_incore(mp->m_ddev_targp, dqp->q_blkno,
mp->m_quotainfo->qi_dqchunklen, XBF_TRYLOCK);
if (!bp)
goto out_lock;
if (XFS_BUF_ISDELAYWRITE(bp)) {
if (xfs_buf_ispinned(bp))
xfs_log_force(mp, 0);
xfs_buf_delwri_promote(bp);
wake_up_process(bp->b_target->bt_task);
}
xfs_buf_relse(bp);
out_lock:
xfs_dqflock(dqp);
}
STATIC bool
xfs_inode_item_pushbuf(
struct xfs_log_item *lip)
{
struct xfs_inode_log_item *iip = INODE_ITEM(lip);
struct xfs_inode *ip = iip->ili_inode;
struct xfs_buf *bp;
bool ret = true;
ASSERT(xfs_isilocked(ip, XFS_ILOCK_SHARED));
/*
*/
if (!xfs_isiflocked(ip) ||
!(lip->li_flags & XFS_LI_IN_AIL)) {
xfs_iunlock(ip, XFS_ILOCK_SHARED);
return true;
}
bp = xfs_incore(ip->i_mount->m_ddev_targp, iip->ili_format.ilf_blkno,
iip->ili_format.ilf_len, XBF_TRYLOCK);
xfs_iunlock(ip, XFS_ILOCK_SHARED);
if (!bp)
return true;
if (XFS_BUF_ISDELAYWRITE(bp))
xfs_buf_delwri_promote(bp);
if (xfs_buf_ispinned(bp))
ret = false;
xfs_buf_relse(bp);
return ret;
}
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;
}
STATIC int
xfs_sync_fsdata(
struct xfs_mount *mp)
{
struct xfs_buf *bp;
int error;
bp = xfs_getsb(mp, 0);
if (xfs_buf_ispinned(bp))
xfs_log_force(mp, 0);
error = xfs_bwrite(bp);
xfs_buf_relse(bp);
return error;
}
STATIC int
xfs_sync_fsdata(
struct xfs_mount *mp)
{
struct xfs_buf *bp;
/*
* If the buffer is pinned then push on the log so we won't get stuck
* waiting in the write for someone, maybe ourselves, to flush the log.
*
* Even though we just pushed the log above, we did not have the
* superblock buffer locked at that point so it can become pinned in
* between there and here.
*/
bp = xfs_getsb(mp, 0);
if (xfs_buf_ispinned(bp))
xfs_log_force(mp, 0);
return xfs_bwrite(mp, bp);
}
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;
}
/*
* 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);
}
/*
* 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(
xfs_dquot_t *dqp,
uint flags)
{
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);
/*
* If not dirty, or it's pinned and we are not supposed to block, nada.
*/
if (!XFS_DQ_IS_DIRTY(dqp) ||
((flags & SYNC_TRYLOCK) && atomic_read(&dqp->q_pincount) > 0)) {
xfs_dqfunlock(dqp);
return 0;
}
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!
*/
if (XFS_FORCED_SHUTDOWN(mp)) {
dqp->dq_flags &= ~XFS_DQ_DIRTY;
xfs_dqfunlock(dqp);
return XFS_ERROR(EIO);
}
/*
* 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);
if (error) {
ASSERT(error != ENOENT);
xfs_dqfunlock(dqp);
return error;
}
/*
* 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_qm_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);
/*
* 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);
}
if (flags & SYNC_WAIT)
error = xfs_bwrite(bp);
else
xfs_buf_delwri_queue(bp);
xfs_buf_relse(bp);
trace_xfs_dqflush_done(dqp);
/*
* dqp is still locked, but caller is free to unlock it now.
*/
return error;
}
