int
xfs_inode_ag_iterator_tag(
struct xfs_mount *mp,
int (*execute)(struct xfs_inode *ip, int flags,
void *args),
int flags,
void *args,
int tag)
{
struct xfs_perag *pag;
int error = 0;
int last_error = 0;
xfs_agnumber_t ag;
ag = 0;
while ((pag = xfs_perag_get_tag(mp, ag, tag))) {
ag = pag->pag_agno + 1;
error = xfs_inode_ag_walk(mp, pag, execute, flags, args, tag);
xfs_perag_put(pag);
if (error) {
last_error = error;
if (error == -EFSCORRUPTED)
break;
}
}
return last_error;
}
int
xfs_reclaim_inodes_count(
struct xfs_mount *mp)
{
struct xfs_perag *pag;
xfs_agnumber_t ag = 0;
int reclaimable = 0;
while ((pag = xfs_perag_get_tag(mp, ag, XFS_ICI_RECLAIM_TAG))) {
ag = pag->pag_agno + 1;
reclaimable += pag->pag_ici_reclaimable;
xfs_perag_put(pag);
}
return reclaimable;
}
/*
* Inode cache shrinker.
*
* When called we make sure that there is a background (fast) inode reclaim in
* progress, while we will throttle the speed of reclaim via doiing synchronous
* reclaim of inodes. That means if we come across dirty inodes, we wait for
* them to be cleaned, which we hope will not be very long due to the
* background walker having already kicked the IO off on those dirty inodes.
*/
static int
xfs_reclaim_inode_shrink(
struct shrinker *shrink,
struct shrink_control *sc)
{
struct xfs_mount *mp;
struct xfs_perag *pag;
xfs_agnumber_t ag;
int reclaimable;
int nr_to_scan = sc->nr_to_scan;
gfp_t gfp_mask = sc->gfp_mask;
mp = container_of(shrink, struct xfs_mount, m_inode_shrink);
if (nr_to_scan) {
/* kick background reclaimer and push the AIL */
xfs_syncd_queue_reclaim(mp);
xfs_ail_push_all(mp->m_ail);
if (!(gfp_mask & __GFP_FS))
return -1;
xfs_reclaim_inodes_ag(mp, SYNC_TRYLOCK | SYNC_WAIT,
&nr_to_scan);
/* terminate if we don't exhaust the scan */
if (nr_to_scan > 0)
return -1;
}
reclaimable = 0;
ag = 0;
while ((pag = xfs_perag_get_tag(mp, ag, XFS_ICI_RECLAIM_TAG))) {
ag = pag->pag_agno + 1;
reclaimable += pag->pag_ici_reclaimable;
xfs_perag_put(pag);
}
return reclaimable;
}
int
xfs_reclaim_inodes_ag(
struct xfs_mount *mp,
int flags,
int *nr_to_scan)
{
struct xfs_perag *pag;
int error = 0;
int last_error = 0;
xfs_agnumber_t ag;
int trylock = flags & SYNC_TRYLOCK;
int skipped;
restart:
ag = 0;
skipped = 0;
while ((pag = xfs_perag_get_tag(mp, ag, XFS_ICI_RECLAIM_TAG))) {
unsigned long first_index = 0;
int done = 0;
int nr_found = 0;
ag = pag->pag_agno + 1;
if (trylock) {
if (!mutex_trylock(&pag->pag_ici_reclaim_lock)) {
skipped++;
xfs_perag_put(pag);
continue;
}
first_index = pag->pag_ici_reclaim_cursor;
} else
mutex_lock(&pag->pag_ici_reclaim_lock);
do {
struct xfs_inode *batch[XFS_LOOKUP_BATCH];
int i;
rcu_read_lock();
nr_found = radix_tree_gang_lookup_tag(
&pag->pag_ici_root,
(void **)batch, first_index,
XFS_LOOKUP_BATCH,
XFS_ICI_RECLAIM_TAG);
if (!nr_found) {
done = 1;
rcu_read_unlock();
break;
}
for (i = 0; i < nr_found; i++) {
struct xfs_inode *ip = batch[i];
if (done || xfs_reclaim_inode_grab(ip, flags))
batch[i] = NULL;
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;
}
rcu_read_unlock();
for (i = 0; i < nr_found; i++) {
if (!batch[i])
continue;
error = xfs_reclaim_inode(batch[i], pag, flags);
if (error && last_error != EFSCORRUPTED)
last_error = error;
}
*nr_to_scan -= XFS_LOOKUP_BATCH;
cond_resched();
} while (nr_found && !done && *nr_to_scan > 0);
if (trylock && !done)
pag->pag_ici_reclaim_cursor = first_index;
else
pag->pag_ici_reclaim_cursor = 0;
mutex_unlock(&pag->pag_ici_reclaim_lock);
xfs_perag_put(pag);
}
if (skipped && (flags & SYNC_WAIT) && *nr_to_scan > 0) {
trylock = 0;
goto restart;
}
return XFS_ERROR(last_error);
}
/*
* Walk the AGs and reclaim the inodes in them. Even if the filesystem is
* corrupted, we still want to try to reclaim all the inodes. If we don't,
* then a shut down during filesystem unmount reclaim walk leak all the
* unreclaimed inodes.
*/
int
xfs_reclaim_inodes_ag(
struct xfs_mount *mp,
int flags,
int *nr_to_scan)
{
struct xfs_perag *pag;
int error = 0;
int last_error = 0;
xfs_agnumber_t ag;
int trylock = flags & SYNC_TRYLOCK;
int skipped;
restart:
ag = 0;
skipped = 0;
while ((pag = xfs_perag_get_tag(mp, ag, XFS_ICI_RECLAIM_TAG))) {
unsigned long first_index = 0;
int done = 0;
int nr_found = 0;
ag = pag->pag_agno + 1;
if (trylock) {
if (!mutex_trylock(&pag->pag_ici_reclaim_lock)) {
skipped++;
xfs_perag_put(pag);
continue;
}
first_index = pag->pag_ici_reclaim_cursor;
} else
mutex_lock(&pag->pag_ici_reclaim_lock);
do {
struct xfs_inode *batch[XFS_LOOKUP_BATCH];
int i;
rcu_read_lock();
nr_found = radix_tree_gang_lookup_tag(
&pag->pag_ici_root,
(void **)batch, first_index,
XFS_LOOKUP_BATCH,
XFS_ICI_RECLAIM_TAG);
if (!nr_found) {
done = 1;
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_reclaim_inode_grab(ip, 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;
error = xfs_reclaim_inode(batch[i], pag, flags);
if (error && last_error != EFSCORRUPTED)
last_error = error;
}
*nr_to_scan -= XFS_LOOKUP_BATCH;
} while (nr_found && !done && *nr_to_scan > 0);
if (trylock && !done)
pag->pag_ici_reclaim_cursor = first_index;
else
pag->pag_ici_reclaim_cursor = 0;
mutex_unlock(&pag->pag_ici_reclaim_lock);
xfs_perag_put(pag);
}
/*
* if we skipped any AG, and we still have scan count remaining, do
* another pass this time using blocking reclaim semantics (i.e
* waiting on the reclaim locks and ignoring the reclaim cursors). This
* ensure that when we get more reclaimers than AGs we block rather
* than spin trying to execute reclaim.
*/
if (trylock && skipped && *nr_to_scan > 0) {
trylock = 0;
goto restart;
}
return XFS_ERROR(last_error);
}
