/*
* xfs sync routine for internal use
*
* This routine supports all of the flags defined for the generic VFS_SYNC
* interface as explained above under xfs_sync. In the interests of not
* changing interfaces within the 6.5 family, additional internallly-
* required functions are specified within a separate xflags parameter,
* only available by calling this routine.
*
*/
int
xfs_syncsub(
xfs_mount_t *mp,
int flags,
int xflags,
int *bypassed)
{
int error = 0;
int last_error = 0;
uint log_flags = XFS_LOG_FORCE;
xfs_buf_t *bp;
xfs_buf_log_item_t *bip;
/*
* Sync out the log. This ensures that the log is periodically
* flushed even if there is not enough activity to fill it up.
*/
if (flags & SYNC_WAIT)
log_flags |= XFS_LOG_SYNC;
xfs_log_force(mp, (xfs_lsn_t)0, log_flags);
if (flags & (SYNC_ATTR|SYNC_DELWRI)) {
if (flags & SYNC_BDFLUSH)
xfs_finish_reclaim_all(mp, 1);
else
error = xfs_sync_inodes(mp, flags, xflags, bypassed);
}
/*
* Flushing out dirty data above probably generated more
* log activity, so if this isn't vfs_sync() then flush
* the log again.
*/
if (flags & SYNC_DELWRI) {
xfs_log_force(mp, (xfs_lsn_t)0, log_flags);
}
if (flags & SYNC_FSDATA) {
/*
* If this is vfs_sync() then only sync the superblock
* if we can lock it without sleeping and it is not pinned.
*/
if (flags & SYNC_BDFLUSH) {
bp = xfs_getsb(mp, XFS_BUF_TRYLOCK);
if (bp != NULL) {
bip = XFS_BUF_FSPRIVATE(bp,xfs_buf_log_item_t*);
if ((bip != NULL) &&
xfs_buf_item_dirty(bip)) {
if (!(XFS_BUF_ISPINNED(bp))) {
XFS_BUF_ASYNC(bp);
error = xfs_bwrite(mp, bp);
} else {
xfs_buf_relse(bp);
}
} else {
xfs_buf_relse(bp);
}
}
} else {
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);
}
/*
* Purge a dquot from all tracking data structures and free it.
*/
STATIC int
xfs_qm_dqpurge(
struct xfs_dquot *dqp,
void *data)
{
struct xfs_mount *mp = dqp->q_mount;
struct xfs_quotainfo *qi = mp->m_quotainfo;
struct xfs_dquot *gdqp = NULL;
xfs_dqlock(dqp);
if ((dqp->dq_flags & XFS_DQ_FREEING) || dqp->q_nrefs != 0) {
xfs_dqunlock(dqp);
return EAGAIN;
}
/*
* If this quota has a group hint attached, prepare for releasing it
* now.
*/
gdqp = dqp->q_gdquot;
if (gdqp) {
xfs_dqlock(gdqp);
dqp->q_gdquot = NULL;
}
dqp->dq_flags |= XFS_DQ_FREEING;
xfs_dqflock(dqp);
/*
* If we are turning this type of quotas off, we don't care
* about the dirty metadata sitting in this dquot. OTOH, if
* we're unmounting, we do care, so we flush it and wait.
*/
if (XFS_DQ_IS_DIRTY(dqp)) {
struct xfs_buf *bp = NULL;
int error;
/*
* We don't care about getting disk errors here. We need
* to purge this dquot anyway, so we go ahead regardless.
*/
error = xfs_qm_dqflush(dqp, &bp);
if (error) {
xfs_warn(mp, "%s: dquot %p flush failed",
__func__, dqp);
} else {
error = xfs_bwrite(bp);
xfs_buf_relse(bp);
}
xfs_dqflock(dqp);
}
ASSERT(atomic_read(&dqp->q_pincount) == 0);
ASSERT(XFS_FORCED_SHUTDOWN(mp) ||
!(dqp->q_logitem.qli_item.li_flags & XFS_LI_IN_AIL));
xfs_dqfunlock(dqp);
xfs_dqunlock(dqp);
radix_tree_delete(XFS_DQUOT_TREE(qi, dqp->q_core.d_flags),
be32_to_cpu(dqp->q_core.d_id));
qi->qi_dquots--;
/*
* We move dquots to the freelist as soon as their reference count
* hits zero, so it really should be on the freelist here.
*/
mutex_lock(&qi->qi_lru_lock);
ASSERT(!list_empty(&dqp->q_lru));
list_del_init(&dqp->q_lru);
qi->qi_lru_count--;
XFS_STATS_DEC(xs_qm_dquot_unused);
mutex_unlock(&qi->qi_lru_lock);
xfs_qm_dqdestroy(dqp);
if (gdqp)
xfs_qm_dqput(gdqp);
return 0;
}
/*
* 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)
{
xfs_mount_t *mp;
xfs_buf_t *bp;
xfs_disk_dquot_t *ddqp;
int error;
SPLDECL(s);
ASSERT(XFS_DQ_IS_LOCKED(dqp));
ASSERT(XFS_DQ_IS_FLUSH_LOCKED(dqp));
xfs_dqtrace_entry(dqp, "DQFLUSH");
/*
* If not dirty, nada.
*/
if (!XFS_DQ_IS_DIRTY(dqp)) {
xfs_dqfunlock(dqp);
return (0);
}
/*
* Cant flush a pinned dquot. Wait for it.
*/
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(dqp->q_mount)) {
dqp->dq_flags &= ~(XFS_DQ_DIRTY);
xfs_dqfunlock(dqp);
return XFS_ERROR(EIO);
}
/*
* Get the buffer containing the on-disk dquot
* We don't need a transaction envelope because we know that the
* the ondisk-dquot has already been allocated for.
*/
if ((error = xfs_qm_dqtobp(NULL, dqp, &ddqp, &bp, XFS_QMOPT_DOWARN))) {
xfs_dqtrace_entry(dqp, "DQTOBP FAIL");
ASSERT(error != ENOENT);
/*
* Quotas could have gotten turned off (ESRCH)
*/
xfs_dqfunlock(dqp);
return (error);
}
if (xfs_qm_dqcheck(&dqp->q_core, be32_to_cpu(ddqp->d_id),
0, XFS_QMOPT_DOWARN, "dqflush (incore copy)")) {
xfs_force_shutdown(dqp->q_mount, XFS_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);
mp = dqp->q_mount;
/* lsn is 64 bits */
AIL_LOCK(mp, s);
dqp->q_logitem.qli_flush_lsn = dqp->q_logitem.qli_item.li_lsn;
AIL_UNLOCK(mp, s);
/*
* 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, (void(*)(xfs_buf_t *, xfs_log_item_t *))
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)) {
xfs_dqtrace_entry(dqp, "DQFLUSH LOG FORCE");
xfs_log_force(mp, (xfs_lsn_t)0, XFS_LOG_FORCE);
}
if (flags & XFS_QMOPT_DELWRI) {
xfs_bdwrite(mp, bp);
} else if (flags & XFS_QMOPT_ASYNC) {
xfs_bawrite(mp, bp);
} else {
error = xfs_bwrite(mp, bp);
}
xfs_dqtrace_entry(dqp, "DQFLUSH END");
/*
* dqp is still locked, but caller is free to unlock it now.
*/
return (error);
}
/*
* Inodes in different states need to be treated differently. The following
* table lists the inode states and the reclaim actions necessary:
*
* inode state iflush ret required action
* --------------- ---------- ---------------
* bad - reclaim
* shutdown EIO unpin and reclaim
* clean, unpinned 0 reclaim
* stale, unpinned 0 reclaim
* clean, pinned(*) 0 requeue
* stale, pinned EAGAIN requeue
* dirty, async - requeue
* dirty, sync 0 reclaim
*
* (*) dgc: I don't think the clean, pinned state is possible but it gets
* handled anyway given the order of checks implemented.
*
* Also, because we get the flush lock first, we know that any inode that has
* been flushed delwri has had the flush completed by the time we check that
* the inode is clean.
*
* Note that because the inode is flushed delayed write by AIL pushing, the
* flush lock may already be held here and waiting on it can result in very
* long latencies. Hence for sync reclaims, where we wait on the flush lock,
* the caller should push the AIL first before trying to reclaim inodes to
* minimise the amount of time spent waiting. For background relaim, we only
* bother to reclaim clean inodes anyway.
*
* Hence the order of actions after gaining the locks should be:
* bad => reclaim
* shutdown => unpin and reclaim
* pinned, async => requeue
* pinned, sync => unpin
* stale => reclaim
* clean => reclaim
* dirty, async => requeue
* dirty, sync => flush, wait and reclaim
*/
STATIC int
xfs_reclaim_inode(
struct xfs_inode *ip,
struct xfs_perag *pag,
int sync_mode)
{
struct xfs_buf *bp = NULL;
xfs_ino_t ino = ip->i_ino; /* for radix_tree_delete */
int error;
restart:
error = 0;
xfs_ilock(ip, XFS_ILOCK_EXCL);
if (!xfs_iflock_nowait(ip)) {
if (!(sync_mode & SYNC_WAIT))
goto out;
xfs_iflock(ip);
}
if (XFS_FORCED_SHUTDOWN(ip->i_mount)) {
xfs_iunpin_wait(ip);
/* xfs_iflush_abort() drops the flush lock */
xfs_iflush_abort(ip, false);
goto reclaim;
}
if (xfs_ipincount(ip)) {
if (!(sync_mode & SYNC_WAIT))
goto out_ifunlock;
xfs_iunpin_wait(ip);
}
if (xfs_iflags_test(ip, XFS_ISTALE) || xfs_inode_clean(ip)) {
xfs_ifunlock(ip);
goto reclaim;
}
/*
* Never flush out dirty data during non-blocking reclaim, as it would
* just contend with AIL pushing trying to do the same job.
*/
if (!(sync_mode & SYNC_WAIT))
goto out_ifunlock;
/*
* Now we have an inode that needs flushing.
*
* Note that xfs_iflush will never block on the inode buffer lock, as
* xfs_ifree_cluster() can lock the inode buffer before it locks the
* ip->i_lock, and we are doing the exact opposite here. As a result,
* doing a blocking xfs_imap_to_bp() to get the cluster buffer would
* result in an ABBA deadlock with xfs_ifree_cluster().
*
* As xfs_ifree_cluser() must gather all inodes that are active in the
* cache to mark them stale, if we hit this case we don't actually want
* to do IO here - we want the inode marked stale so we can simply
* reclaim it. Hence if we get an EAGAIN error here, just unlock the
* inode, back off and try again. Hopefully the next pass through will
* see the stale flag set on the inode.
*/
error = xfs_iflush(ip, &bp);
if (error == -EAGAIN) {
xfs_iunlock(ip, XFS_ILOCK_EXCL);
/* backoff longer than in xfs_ifree_cluster */
delay(2);
goto restart;
}
if (!error) {
error = xfs_bwrite(bp);
xfs_buf_relse(bp);
}
reclaim:
ASSERT(!xfs_isiflocked(ip));
/*
* 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.
* We do this as early as possible under the ILOCK so that
* xfs_iflush_cluster() can be guaranteed to detect races with us here.
* By doing this, we guarantee that once xfs_iflush_cluster has locked
* XFS_ILOCK that it will see either a valid, flushable inode that will
* serialise correctly, or it will see a clean (and invalid) inode that
* it can skip.
*/
spin_lock(&ip->i_flags_lock);
ip->i_flags = XFS_IRECLAIM;
ip->i_ino = 0;
spin_unlock(&ip->i_flags_lock);
xfs_iunlock(ip, XFS_ILOCK_EXCL);
XFS_STATS_INC(ip->i_mount, xs_ig_reclaims);
/*
* Remove the inode from the per-AG radix tree.
*
* Because radix_tree_delete won't complain even if the item was never
* added to the tree assert that it's been there before to catch
* problems with the inode life time early on.
*/
spin_lock(&pag->pag_ici_lock);
if (!radix_tree_delete(&pag->pag_ici_root,
XFS_INO_TO_AGINO(ip->i_mount, ino)))
ASSERT(0);
xfs_perag_clear_reclaim_tag(pag);
spin_unlock(&pag->pag_ici_lock);
/*
* Here we do an (almost) spurious inode lock in order to coordinate
* with inode cache radix tree lookups. This is because the lookup
* can reference the inodes in the cache without taking references.
*
* We make that OK here by ensuring that we wait until the inode is
* unlocked after the lookup before we go ahead and free it.
*/
xfs_ilock(ip, XFS_ILOCK_EXCL);
xfs_qm_dqdetach(ip);
xfs_iunlock(ip, XFS_ILOCK_EXCL);
__xfs_inode_free(ip);
return error;
out_ifunlock:
xfs_ifunlock(ip);
out:
xfs_iflags_clear(ip, XFS_IRECLAIM);
xfs_iunlock(ip, XFS_ILOCK_EXCL);
/*
* We could return -EAGAIN here to make reclaim rescan the inode tree in
* a short while. However, this just burns CPU time scanning the tree
* waiting for IO to complete and the reclaim work never goes back to
* the idle state. Instead, return 0 to let the next scheduled
* background reclaim attempt to reclaim the inode again.
*/
return 0;
}
/*
* 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;
}
/*
* Write the value associated with an attribute into the out-of-line buffer
* that we have defined for it.
*/
int
xfs_attr_rmtval_set(
struct xfs_da_args *args)
{
struct xfs_inode *dp = args->dp;
struct xfs_mount *mp = dp->i_mount;
struct xfs_bmbt_irec map;
xfs_dablk_t lblkno;
xfs_fileoff_t lfileoff = 0;
__uint8_t *src = args->value;
int blkcnt;
int valuelen;
int nmap;
int error;
int offset = 0;
trace_xfs_attr_rmtval_set(args);
/*
* Find a "hole" in the attribute address space large enough for
* us to drop the new attribute's value into. Because CRC enable
* attributes have headers, we can't just do a straight byte to FSB
* conversion and have to take the header space into account.
*/
blkcnt = xfs_attr3_rmt_blocks(mp, args->rmtvaluelen);
error = xfs_bmap_first_unused(args->trans, args->dp, blkcnt, &lfileoff,
XFS_ATTR_FORK);
if (error)
return error;
args->rmtblkno = lblkno = (xfs_dablk_t)lfileoff;
args->rmtblkcnt = blkcnt;
/*
* Roll through the "value", allocating blocks on disk as required.
*/
while (blkcnt > 0) {
int committed;
/*
* Allocate a single extent, up to the size of the value.
*/
xfs_bmap_init(args->flist, args->firstblock);
nmap = 1;
error = xfs_bmapi_write(args->trans, dp, (xfs_fileoff_t)lblkno,
blkcnt,
XFS_BMAPI_ATTRFORK | XFS_BMAPI_METADATA,
args->firstblock, args->total, &map, &nmap,
args->flist);
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, dp, 0);
ASSERT(nmap == 1);
ASSERT((map.br_startblock != DELAYSTARTBLOCK) &&
(map.br_startblock != HOLESTARTBLOCK));
lblkno += map.br_blockcount;
blkcnt -= map.br_blockcount;
/*
* Start the next trans in the chain.
*/
error = xfs_trans_roll(&args->trans, dp);
if (error)
return error;
}
/*
* Roll through the "value", copying the attribute value to the
* already-allocated blocks. Blocks are written synchronously
* so that we can know they are all on disk before we turn off
* the INCOMPLETE flag.
*/
lblkno = args->rmtblkno;
blkcnt = args->rmtblkcnt;
valuelen = args->rmtvaluelen;
while (valuelen > 0) {
struct xfs_buf *bp;
xfs_daddr_t dblkno;
int dblkcnt;
ASSERT(blkcnt > 0);
xfs_bmap_init(args->flist, args->firstblock);
nmap = 1;
error = xfs_bmapi_read(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);
bp = xfs_buf_get(mp->m_ddev_targp, dblkno, dblkcnt, 0);
if (!bp)
return -ENOMEM;
bp->b_ops = &xfs_attr3_rmt_buf_ops;
xfs_attr_rmtval_copyin(mp, bp, args->dp->i_ino, &offset,
&valuelen, &src);
error = xfs_bwrite(bp); /* GROT: NOTE: synchronous write */
xfs_buf_relse(bp);
if (error)
return error;
/* roll attribute extent map forwards */
lblkno += map.br_blockcount;
blkcnt -= map.br_blockcount;
}
ASSERT(valuelen == 0);
return 0;
}
/*
* Write the value associated with an attribute into the out-of-line buffer
* that we have defined for it.
*/
int
xfs_attr_rmtval_set(
struct xfs_da_args *args)
{
struct xfs_inode *dp = args->dp;
struct xfs_mount *mp = dp->i_mount;
struct xfs_bmbt_irec map;
xfs_dablk_t lblkno;
xfs_fileoff_t lfileoff = 0;
uint8_t *src = args->value;
int blkcnt;
int valuelen;
int nmap;
int error;
int offset = 0;
trace_xfs_attr_rmtval_set(args);
/*
* Find a "hole" in the attribute address space large enough for
* us to drop the new attribute's value into. Because CRC enable
* attributes have headers, we can't just do a straight byte to FSB
* conversion and have to take the header space into account.
*/
blkcnt = xfs_attr3_rmt_blocks(mp, args->rmtvaluelen);
error = xfs_bmap_first_unused(args->trans, args->dp, blkcnt, &lfileoff,
XFS_ATTR_FORK);
if (error)
return error;
args->rmtblkno = lblkno = (xfs_dablk_t)lfileoff;
args->rmtblkcnt = blkcnt;
/*
* Roll through the "value", allocating blocks on disk as required.
*/
while (blkcnt > 0) {
/*
* Allocate a single extent, up to the size of the value.
*
* Note that we have to consider this a data allocation as we
* write the remote attribute without logging the contents.
* Hence we must ensure that we aren't using blocks that are on
* the busy list so that we don't overwrite blocks which have
* recently been freed but their transactions are not yet
* committed to disk. If we overwrite the contents of a busy
* extent and then crash then the block may not contain the
* correct metadata after log recovery occurs.
*/
xfs_defer_init(args->dfops, args->firstblock);
nmap = 1;
error = xfs_bmapi_write(args->trans, dp, (xfs_fileoff_t)lblkno,
blkcnt, XFS_BMAPI_ATTRFORK, args->firstblock,
args->total, &map, &nmap, args->dfops);
if (!error)
error = xfs_defer_finish(&args->trans, args->dfops, dp);
if (error) {
args->trans = NULL;
xfs_defer_cancel(args->dfops);
return error;
}
ASSERT(nmap == 1);
ASSERT((map.br_startblock != DELAYSTARTBLOCK) &&
(map.br_startblock != HOLESTARTBLOCK));
lblkno += map.br_blockcount;
blkcnt -= map.br_blockcount;
/*
* Start the next trans in the chain.
*/
error = xfs_trans_roll(&args->trans, dp);
if (error)
return error;
}
/*
* Roll through the "value", copying the attribute value to the
* already-allocated blocks. Blocks are written synchronously
* so that we can know they are all on disk before we turn off
* the INCOMPLETE flag.
*/
lblkno = args->rmtblkno;
blkcnt = args->rmtblkcnt;
valuelen = args->rmtvaluelen;
while (valuelen > 0) {
struct xfs_buf *bp;
xfs_daddr_t dblkno;
int dblkcnt;
ASSERT(blkcnt > 0);
xfs_defer_init(args->dfops, args->firstblock);
nmap = 1;
error = xfs_bmapi_read(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);
bp = xfs_buf_get(mp->m_ddev_targp, dblkno, dblkcnt, 0);
if (!bp)
return -ENOMEM;
bp->b_ops = &xfs_attr3_rmt_buf_ops;
xfs_attr_rmtval_copyin(mp, bp, args->dp->i_ino, &offset,
&valuelen, &src);
error = xfs_bwrite(bp); /* GROT: NOTE: synchronous write */
xfs_buf_relse(bp);
if (error)
return error;
/* roll attribute extent map forwards */
lblkno += map.br_blockcount;
blkcnt -= map.br_blockcount;
}
ASSERT(valuelen == 0);
return 0;
}
