/* must be called with pag_ici_lock held and releases it */
int
xfs_sync_inode_valid(
struct xfs_inode *ip,
struct xfs_perag *pag)
{
struct inode *inode = VFS_I(ip);
int error = EFSCORRUPTED;
/* nothing to sync during shutdown */
if (XFS_FORCED_SHUTDOWN(ip->i_mount))
goto out_unlock;
/* avoid new or reclaimable inodes. Leave for reclaim code to flush */
error = ENOENT;
if (xfs_iflags_test(ip, XFS_INEW | XFS_IRECLAIMABLE | XFS_IRECLAIM))
goto out_unlock;
/* If we can't grab the inode, it must on it's way to reclaim. */
if (!igrab(inode))
goto out_unlock;
if (is_bad_inode(inode)) {
IRELE(ip);
goto out_unlock;
}
/* inode is valid */
error = 0;
out_unlock:
read_unlock(&pag->pag_ici_lock);
return error;
}
/*
* Look up an inode by number in the given file system.
* The inode is looked up in the cache held in each AG.
* If the inode is found in the cache, initialise the vfs inode
* if necessary.
*
* If it is not in core, read it in from the file system's device,
* add it to the cache and initialise the vfs inode.
*
* The inode is locked according to the value of the lock_flags parameter.
* This flag parameter indicates how and if the inode's IO lock and inode lock
* should be taken.
*
* mp -- the mount point structure for the current file system. It points
* to the inode hash table.
* tp -- a pointer to the current transaction if there is one. This is
* simply passed through to the xfs_iread() call.
* ino -- the number of the inode desired. This is the unique identifier
* within the file system for the inode being requested.
* lock_flags -- flags indicating how to lock the inode. See the comment
* for xfs_ilock() for a list of valid values.
*/
int
xfs_iget(
xfs_mount_t *mp,
xfs_trans_t *tp,
xfs_ino_t ino,
uint flags,
uint lock_flags,
xfs_inode_t **ipp)
{
xfs_inode_t *ip;
int error;
xfs_perag_t *pag;
xfs_agino_t agino;
/* reject inode numbers outside existing AGs */
if (!ino || XFS_INO_TO_AGNO(mp, ino) >= mp->m_sb.sb_agcount)
return EINVAL;
/* get the perag structure and ensure that it's inode capable */
pag = xfs_perag_get(mp, XFS_INO_TO_AGNO(mp, ino));
agino = XFS_INO_TO_AGINO(mp, ino);
again:
error = 0;
rcu_read_lock();
ip = radix_tree_lookup(&pag->pag_ici_root, agino);
if (ip) {
error = xfs_iget_cache_hit(pag, ip, ino, flags, lock_flags);
if (error)
goto out_error_or_again;
} else {
rcu_read_unlock();
XFS_STATS_INC(xs_ig_missed);
error = xfs_iget_cache_miss(mp, pag, tp, ino, &ip,
flags, lock_flags);
if (error)
goto out_error_or_again;
}
xfs_perag_put(pag);
*ipp = ip;
/*
* If we have a real type for an on-disk inode, we can set ops(&unlock)
* now. If it's a new inode being created, xfs_ialloc will handle it.
*/
if (xfs_iflags_test(ip, XFS_INEW) && ip->i_d.di_mode != 0)
xfs_setup_inode(ip);
return 0;
out_error_or_again:
if (error == EAGAIN) {
delay(1);
goto again;
}
xfs_perag_put(pag);
return error;
}
int
xfs_iget(
xfs_mount_t *mp,
xfs_trans_t *tp,
xfs_ino_t ino,
uint flags,
uint lock_flags,
xfs_inode_t **ipp)
{
xfs_inode_t *ip;
int error;
xfs_perag_t *pag;
xfs_agino_t agino;
ASSERT((lock_flags & (XFS_IOLOCK_EXCL | XFS_IOLOCK_SHARED)) == 0);
if (!ino || XFS_INO_TO_AGNO(mp, ino) >= mp->m_sb.sb_agcount)
return EINVAL;
pag = xfs_perag_get(mp, XFS_INO_TO_AGNO(mp, ino));
agino = XFS_INO_TO_AGINO(mp, ino);
again:
error = 0;
rcu_read_lock();
ip = radix_tree_lookup(&pag->pag_ici_root, agino);
if (ip) {
error = xfs_iget_cache_hit(pag, ip, ino, flags, lock_flags);
if (error)
goto out_error_or_again;
} else {
rcu_read_unlock();
XFS_STATS_INC(xs_ig_missed);
error = xfs_iget_cache_miss(mp, pag, tp, ino, &ip,
flags, lock_flags);
if (error)
goto out_error_or_again;
}
xfs_perag_put(pag);
*ipp = ip;
if (xfs_iflags_test(ip, XFS_INEW) && ip->i_d.di_mode != 0)
xfs_setup_inode(ip);
return 0;
out_error_or_again:
if (error == EAGAIN) {
delay(1);
goto again;
}
xfs_perag_put(pag);
return error;
}
/*
* This is called to find out where the oldest active copy of the inode log
* item in the on disk log resides now that the last log write of it completed
* at the given lsn. Since we always re-log all dirty data in an inode, the
* latest copy in the on disk log is the only one that matters. Therefore,
* simply return the given lsn.
*
* If the inode has been marked stale because the cluster is being freed, we
* don't want to (re-)insert this inode into the AIL. There is a race condition
* where the cluster buffer may be unpinned before the inode is inserted into
* the AIL during transaction committed processing. If the buffer is unpinned
* before the inode item has been committed and inserted, then it is possible
* for the buffer to be written and IO completions before the inode is inserted
* into the AIL. In that case, we'd be inserting a clean, stale inode into the
* AIL which will never get removed. It will, however, get reclaimed which
* triggers an assert in xfs_inode_free() complaining about freein an inode
* still in the AIL.
*
* To avoid this, return a lower LSN than the one passed in so that the
* transaction committed code will not move the inode forward in the AIL but
* will still unpin it properly.
*/
STATIC xfs_lsn_t
xfs_inode_item_committed(
struct xfs_log_item *lip,
xfs_lsn_t lsn)
{
struct xfs_inode_log_item *iip = INODE_ITEM(lip);
struct xfs_inode *ip = iip->ili_inode;
if (xfs_iflags_test(ip, XFS_ISTALE))
return lsn - 1;
return lsn;
}
static void
xfs_inew_wait(
struct xfs_inode *ip)
{
wait_queue_head_t *wq = bit_waitqueue(&ip->i_flags, __XFS_INEW_BIT);
DEFINE_WAIT_BIT(wait, &ip->i_flags, __XFS_INEW_BIT);
do {
prepare_to_wait(wq, &wait.wq_entry, TASK_UNINTERRUPTIBLE);
if (!xfs_iflags_test(ip, XFS_INEW))
break;
schedule();
} while (true);
finish_wait(wq, &wait.wq_entry);
}
STATIC int
xfs_reclaim_inode(
struct xfs_inode *ip,
struct xfs_perag *pag,
int sync_mode)
{
int error;
restart:
error = 0;
xfs_ilock(ip, XFS_ILOCK_EXCL);
if (!xfs_iflock_nowait(ip)) {
if (!(sync_mode & SYNC_WAIT))
goto out;
xfs_promote_inode(ip);
xfs_iflock(ip);
}
if (is_bad_inode(VFS_I(ip)))
goto reclaim;
if (XFS_FORCED_SHUTDOWN(ip->i_mount)) {
xfs_iunpin_wait(ip);
goto reclaim;
}
if (xfs_ipincount(ip)) {
if (!(sync_mode & SYNC_WAIT)) {
xfs_ifunlock(ip);
goto out;
}
xfs_iunpin_wait(ip);
}
if (xfs_iflags_test(ip, XFS_ISTALE))
goto reclaim;
if (xfs_inode_clean(ip))
goto reclaim;
error = xfs_iflush(ip, SYNC_TRYLOCK | sync_mode);
if (sync_mode & SYNC_WAIT) {
if (error == EAGAIN) {
xfs_iunlock(ip, XFS_ILOCK_EXCL);
delay(2);
goto restart;
}
xfs_iflock(ip);
goto reclaim;
}
if (error && error != EAGAIN && !XFS_FORCED_SHUTDOWN(ip->i_mount)) {
xfs_warn(ip->i_mount,
"inode 0x%llx background reclaim flush failed with %d",
(long long)ip->i_ino, error);
}
out:
xfs_iflags_clear(ip, XFS_IRECLAIM);
xfs_iunlock(ip, XFS_ILOCK_EXCL);
return 0;
reclaim:
xfs_ifunlock(ip);
xfs_iunlock(ip, XFS_ILOCK_EXCL);
XFS_STATS_INC(xs_ig_reclaims);
spin_lock(&pag->pag_ici_lock);
if (!radix_tree_delete(&pag->pag_ici_root,
XFS_INO_TO_AGINO(ip->i_mount, ip->i_ino)))
ASSERT(0);
__xfs_inode_clear_reclaim(pag, ip);
spin_unlock(&pag->pag_ici_lock);
xfs_ilock(ip, XFS_ILOCK_EXCL);
xfs_qm_dqdetach(ip);
xfs_iunlock(ip, XFS_ILOCK_EXCL);
xfs_inode_free(ip);
return error;
}
/*
* Look up an inode by number in the given file system.
* The inode is looked up in the cache held in each AG.
* If the inode is found in the cache, initialise the vfs inode
* if necessary.
*
* If it is not in core, read it in from the file system's device,
* add it to the cache and initialise the vfs inode.
*
* The inode is locked according to the value of the lock_flags parameter.
* This flag parameter indicates how and if the inode's IO lock and inode lock
* should be taken.
*
* mp -- the mount point structure for the current file system. It points
* to the inode hash table.
* tp -- a pointer to the current transaction if there is one. This is
* simply passed through to the xfs_iread() call.
* ino -- the number of the inode desired. This is the unique identifier
* within the file system for the inode being requested.
* lock_flags -- flags indicating how to lock the inode. See the comment
* for xfs_ilock() for a list of valid values.
*/
int
xfs_iget(
xfs_mount_t *mp,
xfs_trans_t *tp,
xfs_ino_t ino,
uint flags,
uint lock_flags,
xfs_inode_t **ipp)
{
xfs_inode_t *ip;
int error;
xfs_perag_t *pag;
xfs_agino_t agino;
/*
* xfs_reclaim_inode() uses the ILOCK to ensure an inode
* doesn't get freed while it's being referenced during a
* radix tree traversal here. It assumes this function
* aqcuires only the ILOCK (and therefore it has no need to
* involve the IOLOCK in this synchronization).
*/
ASSERT((lock_flags & (XFS_IOLOCK_EXCL | XFS_IOLOCK_SHARED)) == 0);
/* reject inode numbers outside existing AGs */
if (!ino || XFS_INO_TO_AGNO(mp, ino) >= mp->m_sb.sb_agcount)
return EINVAL;
/* get the perag structure and ensure that it's inode capable */
pag = xfs_perag_get(mp, XFS_INO_TO_AGNO(mp, ino));
agino = XFS_INO_TO_AGINO(mp, ino);
again:
error = 0;
rcu_read_lock();
ip = radix_tree_lookup(&pag->pag_ici_root, agino);
if (ip) {
error = xfs_iget_cache_hit(pag, ip, ino, flags, lock_flags);
if (error)
goto out_error_or_again;
} else {
rcu_read_unlock();
XFS_STATS_INC(xs_ig_missed);
error = xfs_iget_cache_miss(mp, pag, tp, ino, &ip,
flags, lock_flags);
if (error)
goto out_error_or_again;
}
xfs_perag_put(pag);
*ipp = ip;
/*
* If we have a real type for an on-disk inode, we can set ops(&unlock)
* now. If it's a new inode being created, xfs_ialloc will handle it.
*/
if (xfs_iflags_test(ip, XFS_INEW) && ip->i_d.di_mode != 0)
xfs_setup_inode(ip);
return 0;
out_error_or_again:
if (error == EAGAIN) {
delay(1);
goto again;
}
xfs_perag_put(pag);
return error;
}
/*
* Inodes in different states need to be treated differently, and the return
* value of xfs_iflush is not sufficient to get this right. The following table
* lists the inode states and the reclaim actions necessary for non-blocking
* reclaim:
*
*
* 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, delwri ok 0 requeue
* dirty, delwri blocked EAGAIN requeue
* dirty, sync flush 0 reclaim
*
* (*) dgc: I don't think the clean, pinned state is possible but it gets
* handled anyway given the order of checks implemented.
*
* As can be seen from the table, the return value of xfs_iflush() is not
* sufficient to correctly decide the reclaim action here. The checks in
* xfs_iflush() might look like duplicates, but they are not.
*
* 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. The clean inode check needs to be done before flushing
* the inode delwri otherwise we would loop forever requeuing clean inodes as
* we cannot tell apart a successful delwri flush and a clean inode from the
* return value of xfs_iflush().
*
* Note that because the inode is flushed delayed write by background
* writeback, 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 out delayed write inodes first before
* trying to reclaim them to minimise the amount of time spent waiting. For
* background relaim, we just requeue the inode for the next pass.
*
* Hence the order of actions after gaining the locks should be:
* bad => reclaim
* shutdown => unpin and reclaim
* pinned, delwri => requeue
* pinned, sync => unpin
* stale => reclaim
* clean => reclaim
* dirty, delwri => flush and requeue
* dirty, sync => flush, wait and reclaim
*/
STATIC int
xfs_reclaim_inode(
struct xfs_inode *ip,
struct xfs_perag *pag,
int sync_mode)
{
int error;
restart:
error = 0;
xfs_ilock(ip, XFS_ILOCK_EXCL);
if (!xfs_iflock_nowait(ip)) {
if (!(sync_mode & SYNC_WAIT))
goto out;
/*
* If we only have a single dirty inode in a cluster there is
* a fair chance that the AIL push may have pushed it into
* the buffer, but xfsbufd won't touch it until 30 seconds
* from now, and thus we will lock up here.
*
* Promote the inode buffer to the front of the delwri list
* and wake up xfsbufd now.
*/
xfs_promote_inode(ip);
xfs_iflock(ip);
}
if (is_bad_inode(VFS_I(ip)))
goto reclaim;
if (XFS_FORCED_SHUTDOWN(ip->i_mount)) {
xfs_iunpin_wait(ip);
goto reclaim;
}
if (xfs_ipincount(ip)) {
if (!(sync_mode & SYNC_WAIT)) {
xfs_ifunlock(ip);
goto out;
}
xfs_iunpin_wait(ip);
}
if (xfs_iflags_test(ip, XFS_ISTALE))
goto reclaim;
if (xfs_inode_clean(ip))
goto reclaim;
/*
* Now we have an inode that needs flushing.
*
* We do a nonblocking flush here even if we are doing a SYNC_WAIT
* reclaim as we can deadlock with inode cluster removal.
* 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_itobp() to get the cluster buffer will 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 on a SYNC_WAIT flush,
* 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, SYNC_TRYLOCK | sync_mode);
if (sync_mode & SYNC_WAIT) {
if (error == EAGAIN) {
xfs_iunlock(ip, XFS_ILOCK_EXCL);
/* backoff longer than in xfs_ifree_cluster */
delay(2);
goto restart;
}
xfs_iflock(ip);
goto reclaim;
}
/*
* When we have to flush an inode but don't have SYNC_WAIT set, we
* flush the inode out using a delwri buffer and wait for the next
* call into reclaim to find it in a clean state instead of waiting for
* it now. We also don't return errors here - if the error is transient
* then the next reclaim pass will flush the inode, and if the error
* is permanent then the next sync reclaim will reclaim the inode and
* pass on the error.
*/
if (error && error != EAGAIN && !XFS_FORCED_SHUTDOWN(ip->i_mount)) {
xfs_warn(ip->i_mount,
"inode 0x%llx background reclaim flush failed with %d",
(long long)ip->i_ino, error);
}
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 xfssyncd 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;
reclaim:
xfs_ifunlock(ip);
xfs_iunlock(ip, XFS_ILOCK_EXCL);
XFS_STATS_INC(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, ip->i_ino)))
ASSERT(0);
__xfs_inode_clear_reclaim(pag, ip);
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. We get
* both the ilock and the iolock because the code may need to drop the
* ilock one but will still hold the iolock.
*/
xfs_ilock(ip, XFS_ILOCK_EXCL | XFS_IOLOCK_EXCL);
xfs_qm_dqdetach(ip);
xfs_iunlock(ip, XFS_ILOCK_EXCL | XFS_IOLOCK_EXCL);
xfs_inode_free(ip);
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;
}
STATIC int
xfs_inode_ag_walk(
struct xfs_mount *mp,
struct xfs_perag *pag,
int (*execute)(struct xfs_inode *ip, int flags,
void *args),
int flags,
void *args,
int tag,
int iter_flags)
{
uint32_t first_index;
int last_error = 0;
int skipped;
int done;
int nr_found;
restart:
done = 0;
skipped = 0;
first_index = 0;
nr_found = 0;
do {
struct xfs_inode *batch[XFS_LOOKUP_BATCH];
int error = 0;
int i;
rcu_read_lock();
if (tag == -1)
nr_found = radix_tree_gang_lookup(&pag->pag_ici_root,
(void **)batch, first_index,
XFS_LOOKUP_BATCH);
else
nr_found = radix_tree_gang_lookup_tag(
&pag->pag_ici_root,
(void **) batch, first_index,
XFS_LOOKUP_BATCH, tag);
if (!nr_found) {
rcu_read_unlock();
break;
}
/*
* Grab the inodes before we drop the lock. if we found
* nothing, nr == 0 and the loop will be skipped.
*/
for (i = 0; i < nr_found; i++) {
struct xfs_inode *ip = batch[i];
if (done || xfs_inode_ag_walk_grab(ip, iter_flags))
batch[i] = NULL;
/*
* Update the index for the next lookup. Catch
* overflows into the next AG range which can occur if
* we have inodes in the last block of the AG and we
* are currently pointing to the last inode.
*
* Because we may see inodes that are from the wrong AG
* due to RCU freeing and reallocation, only update the
* index if it lies in this AG. It was a race that lead
* us to see this inode, so another lookup from the
* same index will not find it again.
*/
if (XFS_INO_TO_AGNO(mp, ip->i_ino) != pag->pag_agno)
continue;
first_index = XFS_INO_TO_AGINO(mp, ip->i_ino + 1);
if (first_index < XFS_INO_TO_AGINO(mp, ip->i_ino))
done = 1;
}
/* unlock now we've grabbed the inodes. */
rcu_read_unlock();
for (i = 0; i < nr_found; i++) {
if (!batch[i])
continue;
if ((iter_flags & XFS_AGITER_INEW_WAIT) &&
xfs_iflags_test(batch[i], XFS_INEW))
xfs_inew_wait(batch[i]);
error = execute(batch[i], flags, args);
xfs_irele(batch[i]);
if (error == -EAGAIN) {
skipped++;
continue;
}
if (error && last_error != -EFSCORRUPTED)
last_error = error;
}
/* bail out if the filesystem is corrupted. */
if (error == -EFSCORRUPTED)
break;
cond_resched();
} while (nr_found && !done);
if (skipped) {
delay(1);
goto restart;
}
return last_error;
}
/*
* Sync all the inodes in the given AG according to the
* direction given by the flags.
*/
STATIC int
xfs_sync_inodes_ag(
xfs_mount_t *mp,
int ag,
int flags)
{
xfs_perag_t *pag = &mp->m_perag[ag];
int nr_found;
uint32_t first_index = 0;
int error = 0;
int last_error = 0;
int fflag = XFS_B_ASYNC;
if (flags & SYNC_DELWRI)
fflag = XFS_B_DELWRI;
if (flags & SYNC_WAIT)
fflag = 0; /* synchronous overrides all */
do {
struct inode *inode;
xfs_inode_t *ip = NULL;
int lock_flags = XFS_ILOCK_SHARED;
/*
* use a gang lookup to find the next inode in the tree
* as the tree is sparse and a gang lookup walks to find
* the number of objects requested.
*/
read_lock(&pag->pag_ici_lock);
nr_found = radix_tree_gang_lookup(&pag->pag_ici_root,
(void**)&ip, first_index, 1);
if (!nr_found) {
read_unlock(&pag->pag_ici_lock);
break;
}
/*
* Update the index for the next lookup. Catch overflows
* into the next AG range which can occur if we have inodes
* in the last block of the AG and we are currently
* pointing to the last inode.
*/
first_index = XFS_INO_TO_AGINO(mp, ip->i_ino + 1);
if (first_index < XFS_INO_TO_AGINO(mp, ip->i_ino)) {
read_unlock(&pag->pag_ici_lock);
break;
}
/* nothing to sync during shutdown */
if (XFS_FORCED_SHUTDOWN(mp)) {
read_unlock(&pag->pag_ici_lock);
return 0;
}
/*
* If we can't get a reference on the inode, it must be
* in reclaim. Leave it for the reclaim code to flush.
*/
inode = VFS_I(ip);
if (!igrab(inode)) {
read_unlock(&pag->pag_ici_lock);
continue;
}
read_unlock(&pag->pag_ici_lock);
/* avoid new or bad inodes */
if (is_bad_inode(inode) ||
xfs_iflags_test(ip, XFS_INEW)) {
IRELE(ip);
continue;
}
/*
* If we have to flush data or wait for I/O completion
* we need to hold the iolock.
*/
if ((flags & SYNC_DELWRI) && VN_DIRTY(inode)) {
xfs_ilock(ip, XFS_IOLOCK_SHARED);
lock_flags |= XFS_IOLOCK_SHARED;
error = xfs_flush_pages(ip, 0, -1, fflag, FI_NONE);
if (flags & SYNC_IOWAIT)
xfs_ioend_wait(ip);
}
xfs_ilock(ip, XFS_ILOCK_SHARED);
if ((flags & SYNC_ATTR) && !xfs_inode_clean(ip)) {
if (flags & SYNC_WAIT) {
xfs_iflock(ip);
if (!xfs_inode_clean(ip))
error = xfs_iflush(ip, XFS_IFLUSH_SYNC);
else
xfs_ifunlock(ip);
} else if (xfs_iflock_nowait(ip)) {
if (!xfs_inode_clean(ip))
error = xfs_iflush(ip, XFS_IFLUSH_DELWRI);
else
xfs_ifunlock(ip);
}
}
xfs_iput(ip, lock_flags);
if (error)
last_error = error;
/*
* bail out if the filesystem is corrupted.
*/
if (error == EFSCORRUPTED)
return XFS_ERROR(error);
} while (nr_found);
return last_error;
}