/*
* 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;
}
static void
__xfs_inode_clear_eofblocks_tag(
xfs_inode_t *ip,
void (*clear_tp)(struct xfs_mount *mp, xfs_agnumber_t agno,
int error, unsigned long caller_ip),
int tag)
{
struct xfs_mount *mp = ip->i_mount;
struct xfs_perag *pag;
spin_lock(&ip->i_flags_lock);
ip->i_flags &= ~XFS_IEOFBLOCKS;
spin_unlock(&ip->i_flags_lock);
pag = xfs_perag_get(mp, XFS_INO_TO_AGNO(mp, ip->i_ino));
spin_lock(&pag->pag_ici_lock);
radix_tree_tag_clear(&pag->pag_ici_root,
XFS_INO_TO_AGINO(ip->i_mount, ip->i_ino), tag);
if (!radix_tree_tagged(&pag->pag_ici_root, tag)) {
/* clear the eofblocks tag from the perag radix tree */
spin_lock(&ip->i_mount->m_perag_lock);
radix_tree_tag_clear(&ip->i_mount->m_perag_tree,
XFS_INO_TO_AGNO(ip->i_mount, ip->i_ino),
tag);
spin_unlock(&ip->i_mount->m_perag_lock);
clear_tp(ip->i_mount, pag->pag_agno, -1, _RET_IP_);
}
spin_unlock(&pag->pag_ici_lock);
xfs_perag_put(pag);
}
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;
}
void
xfs_inode_clear_eofblocks_tag(
xfs_inode_t *ip)
{
struct xfs_mount *mp = ip->i_mount;
struct xfs_perag *pag;
pag = xfs_perag_get(mp, XFS_INO_TO_AGNO(mp, ip->i_ino));
spin_lock(&pag->pag_ici_lock);
trace_xfs_inode_clear_eofblocks_tag(ip);
radix_tree_tag_clear(&pag->pag_ici_root,
XFS_INO_TO_AGINO(ip->i_mount, ip->i_ino),
XFS_ICI_EOFBLOCKS_TAG);
if (!radix_tree_tagged(&pag->pag_ici_root, XFS_ICI_EOFBLOCKS_TAG)) {
/* clear the eofblocks tag from the perag radix tree */
spin_lock(&ip->i_mount->m_perag_lock);
radix_tree_tag_clear(&ip->i_mount->m_perag_tree,
XFS_INO_TO_AGNO(ip->i_mount, ip->i_ino),
XFS_ICI_EOFBLOCKS_TAG);
spin_unlock(&ip->i_mount->m_perag_lock);
trace_xfs_perag_clear_eofblocks(ip->i_mount, pag->pag_agno,
-1, _RET_IP_);
}
spin_unlock(&pag->pag_ici_lock);
xfs_perag_put(pag);
}
void
xfs_inode_set_eofblocks_tag(
xfs_inode_t *ip)
{
struct xfs_mount *mp = ip->i_mount;
struct xfs_perag *pag;
int tagged;
pag = xfs_perag_get(mp, XFS_INO_TO_AGNO(mp, ip->i_ino));
spin_lock(&pag->pag_ici_lock);
trace_xfs_inode_set_eofblocks_tag(ip);
tagged = radix_tree_tagged(&pag->pag_ici_root,
XFS_ICI_EOFBLOCKS_TAG);
radix_tree_tag_set(&pag->pag_ici_root,
XFS_INO_TO_AGINO(ip->i_mount, ip->i_ino),
XFS_ICI_EOFBLOCKS_TAG);
if (!tagged) {
/* propagate the eofblocks tag up into the perag radix tree */
spin_lock(&ip->i_mount->m_perag_lock);
radix_tree_tag_set(&ip->i_mount->m_perag_tree,
XFS_INO_TO_AGNO(ip->i_mount, ip->i_ino),
XFS_ICI_EOFBLOCKS_TAG);
spin_unlock(&ip->i_mount->m_perag_lock);
/* kick off background trimming */
xfs_queue_eofblocks(ip->i_mount);
trace_xfs_perag_set_eofblocks(ip->i_mount, pag->pag_agno,
-1, _RET_IP_);
}
spin_unlock(&pag->pag_ici_lock);
xfs_perag_put(pag);
}
int
xfs_inode_ag_iterator(
struct xfs_mount *mp,
int (*execute)(struct xfs_inode *ip,
struct xfs_perag *pag, int flags),
int flags)
{
struct xfs_perag *pag;
int error = 0;
int last_error = 0;
xfs_agnumber_t ag;
ag = 0;
while ((pag = xfs_perag_get(mp, ag))) {
ag = pag->pag_agno + 1;
error = xfs_inode_ag_walk(mp, pag, execute, flags);
xfs_perag_put(pag);
if (error) {
last_error = error;
if (error == EFSCORRUPTED)
break;
}
}
return XFS_ERROR(last_error);
}
static void
xfs_filestream_put_ag(
xfs_mount_t *mp,
xfs_agnumber_t agno)
{
struct xfs_perag *pag;
pag = xfs_perag_get(mp, agno);
atomic_dec(&pag->pagf_fstrms);
xfs_perag_put(pag);
}
static int
xfs_filestream_get_ag(
xfs_mount_t *mp,
xfs_agnumber_t agno)
{
struct xfs_perag *pag;
int ret;
pag = xfs_perag_get(mp, agno);
ret = atomic_inc_return(&pag->pagf_fstrms);
xfs_perag_put(pag);
return ret;
}
int
xfs_inode_ag_iterator(
struct xfs_mount *mp,
int (*execute)(struct xfs_inode *ip,
struct xfs_perag *pag, int flags),
int flags,
int tag,
int exclusive,
int *nr_to_scan)
{
int error = 0;
int last_error = 0;
xfs_agnumber_t ag;
int nr;
nr = nr_to_scan ? *nr_to_scan : INT_MAX;
for (ag = 0; ag < mp->m_sb.sb_agcount; ag++) {
struct xfs_perag *pag;
pag = xfs_perag_get(mp, ag);
if (!pag->pag_ici_init) {
xfs_perag_put(pag);
continue;
}
error = xfs_inode_ag_walk(mp, pag, execute, flags, tag,
exclusive, &nr);
xfs_perag_put(pag);
if (error) {
last_error = error;
if (error == EFSCORRUPTED)
break;
}
if (nr <= 0)
break;
}
if (nr_to_scan)
*nr_to_scan = nr;
return XFS_ERROR(last_error);
}
/*
* xfs_initialize_perag_data
*
* Read in each per-ag structure so we can count up the number of
* allocated inodes, free inodes and used filesystem blocks as this
* information is no longer persistent in the superblock. Once we have
* this information, write it into the in-core superblock structure.
*/
int
xfs_initialize_perag_data(
struct xfs_mount *mp,
xfs_agnumber_t agcount)
{
xfs_agnumber_t index;
xfs_perag_t *pag;
xfs_sb_t *sbp = &mp->m_sb;
uint64_t ifree = 0;
uint64_t ialloc = 0;
uint64_t bfree = 0;
uint64_t bfreelst = 0;
uint64_t btree = 0;
int error;
for (index = 0; index < agcount; index++) {
/*
* read the agf, then the agi. This gets us
* all the information we need and populates the
* per-ag structures for us.
*/
error = xfs_alloc_pagf_init(mp, NULL, index, 0);
if (error)
return error;
error = xfs_ialloc_pagi_init(mp, NULL, index);
if (error)
return error;
pag = xfs_perag_get(mp, index);
ifree += pag->pagi_freecount;
ialloc += pag->pagi_count;
bfree += pag->pagf_freeblks;
bfreelst += pag->pagf_flcount;
btree += pag->pagf_btreeblks;
xfs_perag_put(pag);
}
/*
* Overwrite incore superblock counters with just-read data
*/
spin_lock(&mp->m_sb_lock);
sbp->sb_ifree = ifree;
sbp->sb_icount = ialloc;
sbp->sb_fdblocks = bfree + bfreelst + btree;
spin_unlock(&mp->m_sb_lock);
/* Fixup the per-cpu counters as well. */
xfs_icsb_reinit_counters(mp);
return 0;
}
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;
}
void
xfs_inode_set_reclaim_tag(
xfs_inode_t *ip)
{
struct xfs_mount *mp = ip->i_mount;
struct xfs_perag *pag;
pag = xfs_perag_get(mp, XFS_INO_TO_AGNO(mp, ip->i_ino));
spin_lock(&pag->pag_ici_lock);
spin_lock(&ip->i_flags_lock);
__xfs_inode_set_reclaim_tag(pag, ip);
__xfs_iflags_set(ip, XFS_IRECLAIMABLE);
spin_unlock(&ip->i_flags_lock);
spin_unlock(&pag->pag_ici_lock);
xfs_perag_put(pag);
}
static void
__xfs_inode_set_eofblocks_tag(
xfs_inode_t *ip,
void (*execute)(struct xfs_mount *mp),
void (*set_tp)(struct xfs_mount *mp, xfs_agnumber_t agno,
int error, unsigned long caller_ip),
int tag)
{
struct xfs_mount *mp = ip->i_mount;
struct xfs_perag *pag;
int tagged;
/*
* Don't bother locking the AG and looking up in the radix trees
* if we already know that we have the tag set.
*/
if (ip->i_flags & XFS_IEOFBLOCKS)
return;
spin_lock(&ip->i_flags_lock);
ip->i_flags |= XFS_IEOFBLOCKS;
spin_unlock(&ip->i_flags_lock);
pag = xfs_perag_get(mp, XFS_INO_TO_AGNO(mp, ip->i_ino));
spin_lock(&pag->pag_ici_lock);
tagged = radix_tree_tagged(&pag->pag_ici_root, tag);
radix_tree_tag_set(&pag->pag_ici_root,
XFS_INO_TO_AGINO(ip->i_mount, ip->i_ino), tag);
if (!tagged) {
/* propagate the eofblocks tag up into the perag radix tree */
spin_lock(&ip->i_mount->m_perag_lock);
radix_tree_tag_set(&ip->i_mount->m_perag_tree,
XFS_INO_TO_AGNO(ip->i_mount, ip->i_ino),
tag);
spin_unlock(&ip->i_mount->m_perag_lock);
/* kick off background trimming */
execute(ip->i_mount);
set_tp(ip->i_mount, pag->pag_agno, -1, _RET_IP_);
}
spin_unlock(&pag->pag_ici_lock);
xfs_perag_put(pag);
}
/*
* Do we have enough reserve in this AG to handle a reflink? The refcount
* btree already reserved all the space it needs, but the rmap btree can grow
* infinitely, so we won't allow more reflinks when the AG is down to the
* btree reserves.
*/
static int
xfs_reflink_ag_has_free_space(
struct xfs_mount *mp,
xfs_agnumber_t agno)
{
struct xfs_perag *pag;
int error = 0;
if (!xfs_sb_version_hasrmapbt(&mp->m_sb))
return 0;
pag = xfs_perag_get(mp, agno);
if (xfs_ag_resv_critical(pag, XFS_AG_RESV_AGFL) ||
xfs_ag_resv_critical(pag, XFS_AG_RESV_METADATA))
error = -ENOSPC;
xfs_perag_put(pag);
return error;
}
/*
* We set the inode flag atomically with the radix tree tag.
* Once we get tag lookups on the radix tree, this inode flag
* can go away.
*/
void
xfs_inode_set_reclaim_tag(
struct xfs_inode *ip)
{
struct xfs_mount *mp = ip->i_mount;
struct xfs_perag *pag;
pag = xfs_perag_get(mp, XFS_INO_TO_AGNO(mp, ip->i_ino));
spin_lock(&pag->pag_ici_lock);
spin_lock(&ip->i_flags_lock);
radix_tree_tag_set(&pag->pag_ici_root, XFS_INO_TO_AGINO(mp, ip->i_ino),
XFS_ICI_RECLAIM_TAG);
xfs_perag_set_reclaim_tag(pag);
__xfs_iflags_set(ip, XFS_IRECLAIMABLE);
spin_unlock(&ip->i_flags_lock);
spin_unlock(&pag->pag_ici_lock);
xfs_perag_put(pag);
}
STATIC void
xfs_refcountbt_set_root(
struct xfs_btree_cur *cur,
union xfs_btree_ptr *ptr,
int inc)
{
struct xfs_buf *agbp = cur->bc_private.a.agbp;
struct xfs_agf *agf = XFS_BUF_TO_AGF(agbp);
xfs_agnumber_t seqno = be32_to_cpu(agf->agf_seqno);
struct xfs_perag *pag = xfs_perag_get(cur->bc_mp, seqno);
ASSERT(ptr->s != 0);
agf->agf_refcount_root = ptr->s;
be32_add_cpu(&agf->agf_refcount_level, inc);
pag->pagf_refcount_level += inc;
xfs_perag_put(pag);
xfs_alloc_log_agf(cur->bc_tp, agbp,
XFS_AGF_REFCOUNT_ROOT | XFS_AGF_REFCOUNT_LEVEL);
}
/*
* 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;
}
static int
libxfs_initialize_perag(
xfs_mount_t *mp,
xfs_agnumber_t agcount,
xfs_agnumber_t *maxagi)
{
xfs_agnumber_t index, max_metadata;
xfs_agnumber_t first_initialised = 0;
xfs_perag_t *pag;
xfs_agino_t agino;
xfs_ino_t ino;
xfs_sb_t *sbp = &mp->m_sb;
int error = -ENOMEM;
/*
* Walk the current per-ag tree so we don't try to initialise AGs
* that already exist (growfs case). Allocate and insert all the
* AGs we don't find ready for initialisation.
*/
for (index = 0; index < agcount; index++) {
pag = xfs_perag_get(mp, index);
if (pag) {
xfs_perag_put(pag);
continue;
}
if (!first_initialised)
first_initialised = index;
pag = kmem_zalloc(sizeof(*pag), KM_MAYFAIL);
if (!pag)
goto out_unwind;
pag->pag_agno = index;
pag->pag_mount = mp;
if (radix_tree_insert(&mp->m_perag_tree, index, pag)) {
error = -EEXIST;
goto out_unwind;
}
}
/*
* If we mount with the inode64 option, or no inode overflows
* the legacy 32-bit address space clear the inode32 option.
*/
agino = XFS_OFFBNO_TO_AGINO(mp, sbp->sb_agblocks - 1, 0);
ino = XFS_AGINO_TO_INO(mp, agcount - 1, agino);
if ((mp->m_flags & XFS_MOUNT_SMALL_INUMS) && ino > XFS_MAXINUMBER_32)
mp->m_flags |= XFS_MOUNT_32BITINODES;
else
mp->m_flags &= ~XFS_MOUNT_32BITINODES;
if (mp->m_flags & XFS_MOUNT_32BITINODES) {
/*
* Calculate how much should be reserved for inodes to meet
* the max inode percentage.
*/
if (mp->m_maxicount) {
__uint64_t icount;
icount = sbp->sb_dblocks * sbp->sb_imax_pct;
do_div(icount, 100);
icount += sbp->sb_agblocks - 1;
do_div(icount, sbp->sb_agblocks);
max_metadata = icount;
} else {
max_metadata = agcount;
}
for (index = 0; index < agcount; index++) {
ino = XFS_AGINO_TO_INO(mp, index, agino);
if (ino > XFS_MAXINUMBER_32) {
index++;
break;
}
pag = xfs_perag_get(mp, index);
pag->pagi_inodeok = 1;
if (index < max_metadata)
pag->pagf_metadata = 1;
xfs_perag_put(pag);
}
} else {
for (index = 0; index < agcount; index++) {
pag = xfs_perag_get(mp, index);
pag->pagi_inodeok = 1;
xfs_perag_put(pag);
}
}
if (maxagi)
*maxagi = index;
return 0;
out_unwind:
kmem_free(pag);
for (; index > first_initialised; index--) {
pag = radix_tree_delete(&mp->m_perag_tree, index);
kmem_free(pag);
}
return error;
}
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);
}
/*
* Figure out how many blocks to reserve for an AG repair. We calculate the
* worst case estimate for the number of blocks we'd need to rebuild one of
* any type of per-AG btree.
*/
xfs_extlen_t
xrep_calc_ag_resblks(
struct xfs_scrub *sc)
{
struct xfs_mount *mp = sc->mp;
struct xfs_scrub_metadata *sm = sc->sm;
struct xfs_perag *pag;
struct xfs_buf *bp;
xfs_agino_t icount = NULLAGINO;
xfs_extlen_t aglen = NULLAGBLOCK;
xfs_extlen_t usedlen;
xfs_extlen_t freelen;
xfs_extlen_t bnobt_sz;
xfs_extlen_t inobt_sz;
xfs_extlen_t rmapbt_sz;
xfs_extlen_t refcbt_sz;
int error;
if (!(sm->sm_flags & XFS_SCRUB_IFLAG_REPAIR))
return 0;
pag = xfs_perag_get(mp, sm->sm_agno);
if (pag->pagi_init) {
/* Use in-core icount if possible. */
icount = pag->pagi_count;
} else {
/* Try to get the actual counters from disk. */
error = xfs_ialloc_read_agi(mp, NULL, sm->sm_agno, &bp);
if (!error) {
icount = pag->pagi_count;
xfs_buf_relse(bp);
}
}
/* Now grab the block counters from the AGF. */
error = xfs_alloc_read_agf(mp, NULL, sm->sm_agno, 0, &bp);
if (!error) {
aglen = be32_to_cpu(XFS_BUF_TO_AGF(bp)->agf_length);
freelen = be32_to_cpu(XFS_BUF_TO_AGF(bp)->agf_freeblks);
usedlen = aglen - freelen;
xfs_buf_relse(bp);
}
xfs_perag_put(pag);
/* If the icount is impossible, make some worst-case assumptions. */
if (icount == NULLAGINO ||
!xfs_verify_agino(mp, sm->sm_agno, icount)) {
xfs_agino_t first, last;
xfs_agino_range(mp, sm->sm_agno, &first, &last);
icount = last - first + 1;
}
/* If the block counts are impossible, make worst-case assumptions. */
if (aglen == NULLAGBLOCK ||
aglen != xfs_ag_block_count(mp, sm->sm_agno) ||
freelen >= aglen) {
aglen = xfs_ag_block_count(mp, sm->sm_agno);
freelen = aglen;
usedlen = aglen;
}
trace_xrep_calc_ag_resblks(mp, sm->sm_agno, icount, aglen,
freelen, usedlen);
/*
* Figure out how many blocks we'd need worst case to rebuild
* each type of btree. Note that we can only rebuild the
* bnobt/cntbt or inobt/finobt as pairs.
*/
bnobt_sz = 2 * xfs_allocbt_calc_size(mp, freelen);
if (xfs_sb_version_hassparseinodes(&mp->m_sb))
inobt_sz = xfs_iallocbt_calc_size(mp, icount /
XFS_INODES_PER_HOLEMASK_BIT);
else
inobt_sz = xfs_iallocbt_calc_size(mp, icount /
XFS_INODES_PER_CHUNK);
if (xfs_sb_version_hasfinobt(&mp->m_sb))
inobt_sz *= 2;
if (xfs_sb_version_hasreflink(&mp->m_sb))
refcbt_sz = xfs_refcountbt_calc_size(mp, usedlen);
else
refcbt_sz = 0;
if (xfs_sb_version_hasrmapbt(&mp->m_sb)) {
/*
* Guess how many blocks we need to rebuild the rmapbt.
* For non-reflink filesystems we can't have more records than
* used blocks. However, with reflink it's possible to have
* more than one rmap record per AG block. We don't know how
* many rmaps there could be in the AG, so we start off with
* what we hope is an generous over-estimation.
*/
if (xfs_sb_version_hasreflink(&mp->m_sb))
rmapbt_sz = xfs_rmapbt_calc_size(mp,
(unsigned long long)aglen * 2);
else
rmapbt_sz = xfs_rmapbt_calc_size(mp, usedlen);
} else {
rmapbt_sz = 0;
}
trace_xrep_calc_ag_resblks_btsize(mp, sm->sm_agno, bnobt_sz,
inobt_sz, rmapbt_sz, refcbt_sz);
return max(max(bnobt_sz, inobt_sz), max(rmapbt_sz, refcbt_sz));
}
/*
* Allocate an inode.
*
* The caller selected an AG for us, and made sure that free inodes are
* available.
*/
STATIC int
xfs_dialloc_ag(
struct xfs_trans *tp,
struct xfs_buf *agbp,
xfs_ino_t parent,
xfs_ino_t *inop)
{
struct xfs_mount *mp = tp->t_mountp;
struct xfs_agi *agi = XFS_BUF_TO_AGI(agbp);
xfs_agnumber_t agno = be32_to_cpu(agi->agi_seqno);
xfs_agnumber_t pagno = XFS_INO_TO_AGNO(mp, parent);
xfs_agino_t pagino = XFS_INO_TO_AGINO(mp, parent);
struct xfs_perag *pag;
struct xfs_btree_cur *cur, *tcur;
struct xfs_inobt_rec_incore rec, trec;
xfs_ino_t ino;
int error;
int offset;
int i, j;
pag = xfs_perag_get(mp, agno);
ASSERT(pag->pagi_init);
ASSERT(pag->pagi_inodeok);
ASSERT(pag->pagi_freecount > 0);
restart_pagno:
cur = xfs_inobt_init_cursor(mp, tp, agbp, agno);
/*
* If pagino is 0 (this is the root inode allocation) use newino.
* This must work because we've just allocated some.
*/
if (!pagino)
pagino = be32_to_cpu(agi->agi_newino);
error = xfs_check_agi_freecount(cur, agi);
if (error)
goto error0;
/*
* If in the same AG as the parent, try to get near the parent.
*/
if (pagno == agno) {
int doneleft; /* done, to the left */
int doneright; /* done, to the right */
int searchdistance = 10;
error = xfs_inobt_lookup(cur, pagino, XFS_LOOKUP_LE, &i);
if (error)
goto error0;
XFS_WANT_CORRUPTED_GOTO(i == 1, error0);
error = xfs_inobt_get_rec(cur, &rec, &j);
if (error)
goto error0;
XFS_WANT_CORRUPTED_GOTO(i == 1, error0);
if (rec.ir_freecount > 0) {
/*
* Found a free inode in the same chunk
* as the parent, done.
*/
goto alloc_inode;
}
/*
* In the same AG as parent, but parent's chunk is full.
*/
/* duplicate the cursor, search left & right simultaneously */
error = xfs_btree_dup_cursor(cur, &tcur);
if (error)
goto error0;
/*
* Skip to last blocks looked up if same parent inode.
*/
if (pagino != NULLAGINO &&
pag->pagl_pagino == pagino &&
pag->pagl_leftrec != NULLAGINO &&
pag->pagl_rightrec != NULLAGINO) {
error = xfs_ialloc_get_rec(tcur, pag->pagl_leftrec,
&trec, &doneleft);
if (error)
goto error1;
error = xfs_ialloc_get_rec(cur, pag->pagl_rightrec,
&rec, &doneright);
if (error)
goto error1;
} else {
/* search left with tcur, back up 1 record */
error = xfs_ialloc_next_rec(tcur, &trec, &doneleft, 1);
if (error)
goto error1;
/* search right with cur, go forward 1 record. */
error = xfs_ialloc_next_rec(cur, &rec, &doneright, 0);
if (error)
goto error1;
}
/*
* Loop until we find an inode chunk with a free inode.
*/
while (!doneleft || !doneright) {
int useleft; /* using left inode chunk this time */
if (!--searchdistance) {
/*
* Not in range - save last search
* location and allocate a new inode
*/
xfs_btree_del_cursor(tcur, XFS_BTREE_NOERROR);
pag->pagl_leftrec = trec.ir_startino;
pag->pagl_rightrec = rec.ir_startino;
pag->pagl_pagino = pagino;
goto newino;
}
/* figure out the closer block if both are valid. */
if (!doneleft && !doneright) {
useleft = pagino -
(trec.ir_startino + XFS_INODES_PER_CHUNK - 1) <
rec.ir_startino - pagino;
} else {
useleft = !doneleft;
}
/* free inodes to the left? */
if (useleft && trec.ir_freecount) {
rec = trec;
xfs_btree_del_cursor(cur, XFS_BTREE_NOERROR);
cur = tcur;
pag->pagl_leftrec = trec.ir_startino;
pag->pagl_rightrec = rec.ir_startino;
pag->pagl_pagino = pagino;
goto alloc_inode;
}
/* free inodes to the right? */
if (!useleft && rec.ir_freecount) {
xfs_btree_del_cursor(tcur, XFS_BTREE_NOERROR);
pag->pagl_leftrec = trec.ir_startino;
pag->pagl_rightrec = rec.ir_startino;
pag->pagl_pagino = pagino;
goto alloc_inode;
}
/* get next record to check */
if (useleft) {
error = xfs_ialloc_next_rec(tcur, &trec,
&doneleft, 1);
} else {
error = xfs_ialloc_next_rec(cur, &rec,
&doneright, 0);
}
if (error)
goto error1;
}
/*
* We've reached the end of the btree. because
* we are only searching a small chunk of the
* btree each search, there is obviously free
* inodes closer to the parent inode than we
* are now. restart the search again.
*/
pag->pagl_pagino = NULLAGINO;
pag->pagl_leftrec = NULLAGINO;
pag->pagl_rightrec = NULLAGINO;
xfs_btree_del_cursor(tcur, XFS_BTREE_NOERROR);
xfs_btree_del_cursor(cur, XFS_BTREE_NOERROR);
goto restart_pagno;
}
/*
* In a different AG from the parent.
* See if the most recently allocated block has any free.
*/
newino:
if (agi->agi_newino != cpu_to_be32(NULLAGINO)) {
error = xfs_inobt_lookup(cur, be32_to_cpu(agi->agi_newino),
XFS_LOOKUP_EQ, &i);
if (error)
goto error0;
if (i == 1) {
error = xfs_inobt_get_rec(cur, &rec, &j);
if (error)
goto error0;
if (j == 1 && rec.ir_freecount > 0) {
/*
* The last chunk allocated in the group
* still has a free inode.
*/
goto alloc_inode;
}
}
}
/*
* None left in the last group, search the whole AG
*/
error = xfs_inobt_lookup(cur, 0, XFS_LOOKUP_GE, &i);
if (error)
goto error0;
XFS_WANT_CORRUPTED_GOTO(i == 1, error0);
for (;;) {
error = xfs_inobt_get_rec(cur, &rec, &i);
if (error)
goto error0;
XFS_WANT_CORRUPTED_GOTO(i == 1, error0);
if (rec.ir_freecount > 0)
break;
error = xfs_btree_increment(cur, 0, &i);
if (error)
goto error0;
XFS_WANT_CORRUPTED_GOTO(i == 1, error0);
}
alloc_inode:
offset = xfs_lowbit64(rec.ir_free);
ASSERT(offset >= 0);
ASSERT(offset < XFS_INODES_PER_CHUNK);
ASSERT((XFS_AGINO_TO_OFFSET(mp, rec.ir_startino) %
XFS_INODES_PER_CHUNK) == 0);
ino = XFS_AGINO_TO_INO(mp, agno, rec.ir_startino + offset);
rec.ir_free &= ~XFS_INOBT_MASK(offset);
rec.ir_freecount--;
error = xfs_inobt_update(cur, &rec);
if (error)
goto error0;
be32_add_cpu(&agi->agi_freecount, -1);
xfs_ialloc_log_agi(tp, agbp, XFS_AGI_FREECOUNT);
pag->pagi_freecount--;
error = xfs_check_agi_freecount(cur, agi);
if (error)
goto error0;
xfs_btree_del_cursor(cur, XFS_BTREE_NOERROR);
xfs_trans_mod_sb(tp, XFS_TRANS_SB_IFREE, -1);
xfs_perag_put(pag);
*inop = ino;
return 0;
error1:
xfs_btree_del_cursor(tcur, XFS_BTREE_ERROR);
error0:
xfs_btree_del_cursor(cur, XFS_BTREE_ERROR);
xfs_perag_put(pag);
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;
}
/*
* Allocate an inode on disk.
* Mode is used to tell whether the new inode will need space, and whether
* it is a directory.
*
* The arguments IO_agbp and alloc_done are defined to work within
* the constraint of one allocation per transaction.
* xfs_dialloc() is designed to be called twice if it has to do an
* allocation to make more free inodes. On the first call,
* IO_agbp should be set to NULL. If an inode is available,
* i.e., xfs_dialloc() did not need to do an allocation, an inode
* number is returned. In this case, IO_agbp would be set to the
* current ag_buf and alloc_done set to false.
* If an allocation needed to be done, xfs_dialloc would return
* the current ag_buf in IO_agbp and set alloc_done to true.
* The caller should then commit the current transaction, allocate a new
* transaction, and call xfs_dialloc() again, passing in the previous
* value of IO_agbp. IO_agbp should be held across the transactions.
* Since the agbp is locked across the two calls, the second call is
* guaranteed to have a free inode available.
*
* Once we successfully pick an inode its number is returned and the
* on-disk data structures are updated. The inode itself is not read
* in, since doing so would break ordering constraints with xfs_reclaim.
*/
int
xfs_dialloc(
xfs_trans_t *tp, /* transaction pointer */
xfs_ino_t parent, /* parent inode (directory) */
umode_t mode, /* mode bits for new inode */
int okalloc, /* ok to allocate more space */
xfs_buf_t **IO_agbp, /* in/out ag header's buffer */
boolean_t *alloc_done, /* true if we needed to replenish
inode freelist */
xfs_ino_t *inop) /* inode number allocated */
{
xfs_agnumber_t agcount; /* number of allocation groups */
xfs_buf_t *agbp; /* allocation group header's buffer */
xfs_agnumber_t agno; /* allocation group number */
xfs_agi_t *agi; /* allocation group header structure */
xfs_btree_cur_t *cur; /* inode allocation btree cursor */
int error; /* error return value */
int i; /* result code */
int ialloced; /* inode allocation status */
int noroom = 0; /* no space for inode blk allocation */
xfs_ino_t ino; /* fs-relative inode to be returned */
/* REFERENCED */
int j; /* result code */
xfs_mount_t *mp; /* file system mount structure */
int offset; /* index of inode in chunk */
xfs_agino_t pagino; /* parent's AG relative inode # */
xfs_agnumber_t pagno; /* parent's AG number */
xfs_inobt_rec_incore_t rec; /* inode allocation record */
xfs_agnumber_t tagno; /* testing allocation group number */
xfs_btree_cur_t *tcur; /* temp cursor */
xfs_inobt_rec_incore_t trec; /* temp inode allocation record */
struct xfs_perag *pag;
if (*IO_agbp == NULL) {
/*
* We do not have an agbp, so select an initial allocation
* group for inode allocation.
*/
agbp = xfs_ialloc_ag_select(tp, parent, mode, okalloc);
/*
* Couldn't find an allocation group satisfying the
* criteria, give up.
*/
if (!agbp) {
*inop = NULLFSINO;
return 0;
}
agi = XFS_BUF_TO_AGI(agbp);
ASSERT(agi->agi_magicnum == cpu_to_be32(XFS_AGI_MAGIC));
} else {
/*
* Continue where we left off before. In this case, we
* know that the allocation group has free inodes.
*/
agbp = *IO_agbp;
agi = XFS_BUF_TO_AGI(agbp);
ASSERT(agi->agi_magicnum == cpu_to_be32(XFS_AGI_MAGIC));
ASSERT(be32_to_cpu(agi->agi_freecount) > 0);
}
mp = tp->t_mountp;
agcount = mp->m_sb.sb_agcount;
agno = be32_to_cpu(agi->agi_seqno);
tagno = agno;
pagno = XFS_INO_TO_AGNO(mp, parent);
pagino = XFS_INO_TO_AGINO(mp, parent);
/*
* If we have already hit the ceiling of inode blocks then clear
* okalloc so we scan all available agi structures for a free
* inode.
*/
if (mp->m_maxicount &&
mp->m_sb.sb_icount + XFS_IALLOC_INODES(mp) > mp->m_maxicount) {
noroom = 1;
okalloc = 0;
}
/*
* Loop until we find an allocation group that either has free inodes
* or in which we can allocate some inodes. Iterate through the
* allocation groups upward, wrapping at the end.
*/
*alloc_done = B_FALSE;
while (!agi->agi_freecount) {
/*
* Don't do anything if we're not supposed to allocate
* any blocks, just go on to the next ag.
*/
if (okalloc) {
/*
* Try to allocate some new inodes in the allocation
* group.
*/
if ((error = xfs_ialloc_ag_alloc(tp, agbp, &ialloced))) {
xfs_trans_brelse(tp, agbp);
if (error == ENOSPC) {
*inop = NULLFSINO;
return 0;
} else
return error;
}
if (ialloced) {
/*
* We successfully allocated some inodes, return
* the current context to the caller so that it
* can commit the current transaction and call
* us again where we left off.
*/
ASSERT(be32_to_cpu(agi->agi_freecount) > 0);
*alloc_done = B_TRUE;
*IO_agbp = agbp;
*inop = NULLFSINO;
return 0;
}
}
/*
* If it failed, give up on this ag.
*/
xfs_trans_brelse(tp, agbp);
/*
* Go on to the next ag: get its ag header.
*/
nextag:
if (++tagno == agcount)
tagno = 0;
if (tagno == agno) {
*inop = NULLFSINO;
return noroom ? ENOSPC : 0;
}
pag = xfs_perag_get(mp, tagno);
if (pag->pagi_inodeok == 0) {
xfs_perag_put(pag);
goto nextag;
}
error = xfs_ialloc_read_agi(mp, tp, tagno, &agbp);
xfs_perag_put(pag);
if (error)
goto nextag;
agi = XFS_BUF_TO_AGI(agbp);
ASSERT(agi->agi_magicnum == cpu_to_be32(XFS_AGI_MAGIC));
}
/*
* Here with an allocation group that has a free inode.
* Reset agno since we may have chosen a new ag in the
* loop above.
*/
agno = tagno;
*IO_agbp = NULL;
pag = xfs_perag_get(mp, agno);
restart_pagno:
cur = xfs_inobt_init_cursor(mp, tp, agbp, be32_to_cpu(agi->agi_seqno));
/*
* If pagino is 0 (this is the root inode allocation) use newino.
* This must work because we've just allocated some.
*/
if (!pagino)
pagino = be32_to_cpu(agi->agi_newino);
error = xfs_check_agi_freecount(cur, agi);
if (error)
goto error0;
/*
* If in the same AG as the parent, try to get near the parent.
*/
if (pagno == agno) {
int doneleft; /* done, to the left */
int doneright; /* done, to the right */
int searchdistance = 10;
error = xfs_inobt_lookup(cur, pagino, XFS_LOOKUP_LE, &i);
if (error)
goto error0;
XFS_WANT_CORRUPTED_GOTO(i == 1, error0);
error = xfs_inobt_get_rec(cur, &rec, &j);
if (error)
goto error0;
XFS_WANT_CORRUPTED_GOTO(i == 1, error0);
if (rec.ir_freecount > 0) {
/*
* Found a free inode in the same chunk
* as the parent, done.
*/
goto alloc_inode;
}
/*
* In the same AG as parent, but parent's chunk is full.
*/
/* duplicate the cursor, search left & right simultaneously */
error = xfs_btree_dup_cursor(cur, &tcur);
if (error)
goto error0;
/*
* Skip to last blocks looked up if same parent inode.
*/
if (pagino != NULLAGINO &&
pag->pagl_pagino == pagino &&
pag->pagl_leftrec != NULLAGINO &&
pag->pagl_rightrec != NULLAGINO) {
error = xfs_ialloc_get_rec(tcur, pag->pagl_leftrec,
&trec, &doneleft, 1);
if (error)
goto error1;
error = xfs_ialloc_get_rec(cur, pag->pagl_rightrec,
&rec, &doneright, 0);
if (error)
goto error1;
} else {
/* search left with tcur, back up 1 record */
error = xfs_ialloc_next_rec(tcur, &trec, &doneleft, 1);
if (error)
goto error1;
/* search right with cur, go forward 1 record. */
error = xfs_ialloc_next_rec(cur, &rec, &doneright, 0);
if (error)
goto error1;
}
/*
* Loop until we find an inode chunk with a free inode.
*/
while (!doneleft || !doneright) {
int useleft; /* using left inode chunk this time */
if (!--searchdistance) {
/*
* Not in range - save last search
* location and allocate a new inode
*/
xfs_btree_del_cursor(tcur, XFS_BTREE_NOERROR);
pag->pagl_leftrec = trec.ir_startino;
pag->pagl_rightrec = rec.ir_startino;
pag->pagl_pagino = pagino;
goto newino;
}
/* figure out the closer block if both are valid. */
if (!doneleft && !doneright) {
useleft = pagino -
(trec.ir_startino + XFS_INODES_PER_CHUNK - 1) <
rec.ir_startino - pagino;
} else {
useleft = !doneleft;
}
/* free inodes to the left? */
if (useleft && trec.ir_freecount) {
rec = trec;
xfs_btree_del_cursor(cur, XFS_BTREE_NOERROR);
cur = tcur;
pag->pagl_leftrec = trec.ir_startino;
pag->pagl_rightrec = rec.ir_startino;
pag->pagl_pagino = pagino;
goto alloc_inode;
}
/* free inodes to the right? */
if (!useleft && rec.ir_freecount) {
xfs_btree_del_cursor(tcur, XFS_BTREE_NOERROR);
pag->pagl_leftrec = trec.ir_startino;
pag->pagl_rightrec = rec.ir_startino;
pag->pagl_pagino = pagino;
goto alloc_inode;
}
/* get next record to check */
if (useleft) {
error = xfs_ialloc_next_rec(tcur, &trec,
&doneleft, 1);
} else {
error = xfs_ialloc_next_rec(cur, &rec,
&doneright, 0);
}
if (error)
goto error1;
}
/*
* We've reached the end of the btree. because
* we are only searching a small chunk of the
* btree each search, there is obviously free
* inodes closer to the parent inode than we
* are now. restart the search again.
*/
pag->pagl_pagino = NULLAGINO;
pag->pagl_leftrec = NULLAGINO;
pag->pagl_rightrec = NULLAGINO;
xfs_btree_del_cursor(tcur, XFS_BTREE_NOERROR);
xfs_btree_del_cursor(cur, XFS_BTREE_NOERROR);
goto restart_pagno;
}
/*
* In a different AG from the parent.
* See if the most recently allocated block has any free.
*/
newino:
if (agi->agi_newino != cpu_to_be32(NULLAGINO)) {
error = xfs_inobt_lookup(cur, be32_to_cpu(agi->agi_newino),
XFS_LOOKUP_EQ, &i);
if (error)
goto error0;
if (i == 1) {
error = xfs_inobt_get_rec(cur, &rec, &j);
if (error)
goto error0;
if (j == 1 && rec.ir_freecount > 0) {
/*
* The last chunk allocated in the group
* still has a free inode.
*/
goto alloc_inode;
}
}
}
/*
* None left in the last group, search the whole AG
*/
error = xfs_inobt_lookup(cur, 0, XFS_LOOKUP_GE, &i);
if (error)
goto error0;
XFS_WANT_CORRUPTED_GOTO(i == 1, error0);
for (;;) {
error = xfs_inobt_get_rec(cur, &rec, &i);
if (error)
goto error0;
XFS_WANT_CORRUPTED_GOTO(i == 1, error0);
if (rec.ir_freecount > 0)
break;
error = xfs_btree_increment(cur, 0, &i);
if (error)
goto error0;
XFS_WANT_CORRUPTED_GOTO(i == 1, error0);
}
alloc_inode:
offset = xfs_ialloc_find_free(&rec.ir_free);
ASSERT(offset >= 0);
ASSERT(offset < XFS_INODES_PER_CHUNK);
ASSERT((XFS_AGINO_TO_OFFSET(mp, rec.ir_startino) %
XFS_INODES_PER_CHUNK) == 0);
ino = XFS_AGINO_TO_INO(mp, agno, rec.ir_startino + offset);
rec.ir_free &= ~XFS_INOBT_MASK(offset);
rec.ir_freecount--;
error = xfs_inobt_update(cur, &rec);
if (error)
goto error0;
be32_add_cpu(&agi->agi_freecount, -1);
xfs_ialloc_log_agi(tp, agbp, XFS_AGI_FREECOUNT);
pag->pagi_freecount--;
error = xfs_check_agi_freecount(cur, agi);
if (error)
goto error0;
xfs_btree_del_cursor(cur, XFS_BTREE_NOERROR);
xfs_trans_mod_sb(tp, XFS_TRANS_SB_IFREE, -1);
xfs_perag_put(pag);
*inop = ino;
return 0;
error1:
xfs_btree_del_cursor(tcur, XFS_BTREE_ERROR);
error0:
xfs_btree_del_cursor(cur, XFS_BTREE_ERROR);
xfs_perag_put(pag);
return error;
}
/*
* Select an allocation group to look for a free inode in, based on the parent
* inode and then mode. Return the allocation group buffer.
*/
STATIC xfs_buf_t * /* allocation group buffer */
xfs_ialloc_ag_select(
xfs_trans_t *tp, /* transaction pointer */
xfs_ino_t parent, /* parent directory inode number */
umode_t mode, /* bits set to indicate file type */
int okalloc) /* ok to allocate more space */
{
xfs_buf_t *agbp; /* allocation group header buffer */
xfs_agnumber_t agcount; /* number of ag's in the filesystem */
xfs_agnumber_t agno; /* current ag number */
int flags; /* alloc buffer locking flags */
xfs_extlen_t ineed; /* blocks needed for inode allocation */
xfs_extlen_t longest = 0; /* longest extent available */
xfs_mount_t *mp; /* mount point structure */
int needspace; /* file mode implies space allocated */
xfs_perag_t *pag; /* per allocation group data */
xfs_agnumber_t pagno; /* parent (starting) ag number */
/*
* Files of these types need at least one block if length > 0
* (and they won't fit in the inode, but that's hard to figure out).
*/
needspace = S_ISDIR(mode) || S_ISREG(mode) || S_ISLNK(mode);
mp = tp->t_mountp;
agcount = mp->m_maxagi;
if (S_ISDIR(mode))
pagno = xfs_ialloc_next_ag(mp);
else {
pagno = XFS_INO_TO_AGNO(mp, parent);
if (pagno >= agcount)
pagno = 0;
}
ASSERT(pagno < agcount);
/*
* Loop through allocation groups, looking for one with a little
* free space in it. Note we don't look for free inodes, exactly.
* Instead, we include whether there is a need to allocate inodes
* to mean that blocks must be allocated for them,
* if none are currently free.
*/
agno = pagno;
flags = XFS_ALLOC_FLAG_TRYLOCK;
for (;;) {
pag = xfs_perag_get(mp, agno);
if (!pag->pagi_init) {
if (xfs_ialloc_read_agi(mp, tp, agno, &agbp)) {
agbp = NULL;
goto nextag;
}
} else
agbp = NULL;
if (!pag->pagi_inodeok) {
xfs_ialloc_next_ag(mp);
goto unlock_nextag;
}
/*
* Is there enough free space for the file plus a block
* of inodes (if we need to allocate some)?
*/
ineed = pag->pagi_freecount ? 0 : XFS_IALLOC_BLOCKS(mp);
if (ineed && !pag->pagf_init) {
if (agbp == NULL &&
xfs_ialloc_read_agi(mp, tp, agno, &agbp)) {
agbp = NULL;
goto nextag;
}
(void)xfs_alloc_pagf_init(mp, tp, agno, flags);
}
if (!ineed || pag->pagf_init) {
if (ineed && !(longest = pag->pagf_longest))
longest = pag->pagf_flcount > 0;
if (!ineed ||
(pag->pagf_freeblks >= needspace + ineed &&
longest >= ineed &&
okalloc)) {
if (agbp == NULL &&
xfs_ialloc_read_agi(mp, tp, agno, &agbp)) {
agbp = NULL;
goto nextag;
}
xfs_perag_put(pag);
return agbp;
}
}
unlock_nextag:
if (agbp)
xfs_trans_brelse(tp, agbp);
nextag:
xfs_perag_put(pag);
/*
* No point in iterating over the rest, if we're shutting
* down.
*/
if (XFS_FORCED_SHUTDOWN(mp))
return NULL;
agno++;
if (agno >= agcount)
agno = 0;
if (agno == pagno) {
if (flags == 0)
return NULL;
flags = 0;
}
}
}
/*
* Allocate new inodes in the allocation group specified by agbp.
* Return 0 for success, else error code.
*/
STATIC int /* error code or 0 */
xfs_ialloc_ag_alloc(
xfs_trans_t *tp, /* transaction pointer */
xfs_buf_t *agbp, /* alloc group buffer */
int *alloc)
{
xfs_agi_t *agi; /* allocation group header */
xfs_alloc_arg_t args; /* allocation argument structure */
xfs_btree_cur_t *cur; /* inode btree cursor */
xfs_agnumber_t agno;
int error;
int i;
xfs_agino_t newino; /* new first inode's number */
xfs_agino_t newlen; /* new number of inodes */
xfs_agino_t thisino; /* current inode number, for loop */
int isaligned = 0; /* inode allocation at stripe unit */
/* boundary */
struct xfs_perag *pag;
args.tp = tp;
args.mp = tp->t_mountp;
/*
* Locking will ensure that we don't have two callers in here
* at one time.
*/
newlen = XFS_IALLOC_INODES(args.mp);
if (args.mp->m_maxicount &&
args.mp->m_sb.sb_icount + newlen > args.mp->m_maxicount)
return XFS_ERROR(ENOSPC);
args.minlen = args.maxlen = XFS_IALLOC_BLOCKS(args.mp);
/*
* First try to allocate inodes contiguous with the last-allocated
* chunk of inodes. If the filesystem is striped, this will fill
* an entire stripe unit with inodes.
*/
agi = XFS_BUF_TO_AGI(agbp);
newino = be32_to_cpu(agi->agi_newino);
agno = be32_to_cpu(agi->agi_seqno);
args.agbno = XFS_AGINO_TO_AGBNO(args.mp, newino) +
XFS_IALLOC_BLOCKS(args.mp);
if (likely(newino != NULLAGINO &&
(args.agbno < be32_to_cpu(agi->agi_length)))) {
args.fsbno = XFS_AGB_TO_FSB(args.mp, agno, args.agbno);
args.type = XFS_ALLOCTYPE_THIS_BNO;
args.mod = args.total = args.wasdel = args.isfl =
args.userdata = args.minalignslop = 0;
args.prod = 1;
/*
* We need to take into account alignment here to ensure that
* we don't modify the free list if we fail to have an exact
* block. If we don't have an exact match, and every oher
* attempt allocation attempt fails, we'll end up cancelling
* a dirty transaction and shutting down.
*
* For an exact allocation, alignment must be 1,
* however we need to take cluster alignment into account when
* fixing up the freelist. Use the minalignslop field to
* indicate that extra blocks might be required for alignment,
* but not to use them in the actual exact allocation.
*/
args.alignment = 1;
args.minalignslop = xfs_ialloc_cluster_alignment(&args) - 1;
/* Allow space for the inode btree to split. */
args.minleft = args.mp->m_in_maxlevels - 1;
if ((error = xfs_alloc_vextent(&args)))
return error;
} else
args.fsbno = NULLFSBLOCK;
if (unlikely(args.fsbno == NULLFSBLOCK)) {
/*
* Set the alignment for the allocation.
* If stripe alignment is turned on then align at stripe unit
* boundary.
* If the cluster size is smaller than a filesystem block
* then we're doing I/O for inodes in filesystem block size
* pieces, so don't need alignment anyway.
*/
isaligned = 0;
if (args.mp->m_sinoalign) {
ASSERT(!(args.mp->m_flags & XFS_MOUNT_NOALIGN));
args.alignment = args.mp->m_dalign;
isaligned = 1;
} else
args.alignment = xfs_ialloc_cluster_alignment(&args);
/*
* Need to figure out where to allocate the inode blocks.
* Ideally they should be spaced out through the a.g.
* For now, just allocate blocks up front.
*/
args.agbno = be32_to_cpu(agi->agi_root);
args.fsbno = XFS_AGB_TO_FSB(args.mp, agno, args.agbno);
/*
* Allocate a fixed-size extent of inodes.
*/
args.type = XFS_ALLOCTYPE_NEAR_BNO;
args.mod = args.total = args.wasdel = args.isfl =
args.userdata = args.minalignslop = 0;
args.prod = 1;
/*
* Allow space for the inode btree to split.
*/
args.minleft = args.mp->m_in_maxlevels - 1;
if ((error = xfs_alloc_vextent(&args)))
return error;
}
/*
* If stripe alignment is turned on, then try again with cluster
* alignment.
*/
if (isaligned && args.fsbno == NULLFSBLOCK) {
args.type = XFS_ALLOCTYPE_NEAR_BNO;
args.agbno = be32_to_cpu(agi->agi_root);
args.fsbno = XFS_AGB_TO_FSB(args.mp, agno, args.agbno);
args.alignment = xfs_ialloc_cluster_alignment(&args);
if ((error = xfs_alloc_vextent(&args)))
return error;
}
if (args.fsbno == NULLFSBLOCK) {
*alloc = 0;
return 0;
}
ASSERT(args.len == args.minlen);
/*
* Stamp and write the inode buffers.
*
* Seed the new inode cluster with a random generation number. This
* prevents short-term reuse of generation numbers if a chunk is
* freed and then immediately reallocated. We use random numbers
* rather than a linear progression to prevent the next generation
* number from being easily guessable.
*/
error = xfs_ialloc_inode_init(args.mp, tp, agno, args.agbno,
args.len, prandom_u32());
if (error)
return error;
/*
* Convert the results.
*/
newino = XFS_OFFBNO_TO_AGINO(args.mp, args.agbno, 0);
be32_add_cpu(&agi->agi_count, newlen);
be32_add_cpu(&agi->agi_freecount, newlen);
pag = xfs_perag_get(args.mp, agno);
pag->pagi_freecount += newlen;
xfs_perag_put(pag);
agi->agi_newino = cpu_to_be32(newino);
/*
* Insert records describing the new inode chunk into the btree.
*/
cur = xfs_inobt_init_cursor(args.mp, tp, agbp, agno);
for (thisino = newino;
thisino < newino + newlen;
thisino += XFS_INODES_PER_CHUNK) {
cur->bc_rec.i.ir_startino = thisino;
cur->bc_rec.i.ir_freecount = XFS_INODES_PER_CHUNK;
cur->bc_rec.i.ir_free = XFS_INOBT_ALL_FREE;
error = xfs_btree_lookup(cur, XFS_LOOKUP_EQ, &i);
if (error) {
xfs_btree_del_cursor(cur, XFS_BTREE_ERROR);
return error;
}
ASSERT(i == 0);
error = xfs_btree_insert(cur, &i);
if (error) {
xfs_btree_del_cursor(cur, XFS_BTREE_ERROR);
return error;
}
ASSERT(i == 1);
}
xfs_btree_del_cursor(cur, XFS_BTREE_NOERROR);
/*
* Log allocation group header fields
*/
xfs_ialloc_log_agi(tp, agbp,
XFS_AGI_COUNT | XFS_AGI_FREECOUNT | XFS_AGI_NEWINO);
/*
* Modify/log superblock values for inode count and inode free count.
*/
xfs_trans_mod_sb(tp, XFS_TRANS_SB_ICOUNT, (long)newlen);
xfs_trans_mod_sb(tp, XFS_TRANS_SB_IFREE, (long)newlen);
*alloc = 1;
return 0;
}
/*
* Allocate an inode on disk.
*
* Mode is used to tell whether the new inode will need space, and whether it
* is a directory.
*
* This function is designed to be called twice if it has to do an allocation
* to make more free inodes. On the first call, *IO_agbp should be set to NULL.
* If an inode is available without having to performn an allocation, an inode
* number is returned. In this case, *IO_agbp is set to NULL. If an allocation
* needs to be done, xfs_dialloc returns the current AGI buffer in *IO_agbp.
* The caller should then commit the current transaction, allocate a
* new transaction, and call xfs_dialloc() again, passing in the previous value
* of *IO_agbp. IO_agbp should be held across the transactions. Since the AGI
* buffer is locked across the two calls, the second call is guaranteed to have
* a free inode available.
*
* Once we successfully pick an inode its number is returned and the on-disk
* data structures are updated. The inode itself is not read in, since doing so
* would break ordering constraints with xfs_reclaim.
*/
int
xfs_dialloc(
struct xfs_trans *tp,
xfs_ino_t parent,
umode_t mode,
int okalloc,
struct xfs_buf **IO_agbp,
xfs_ino_t *inop)
{
struct xfs_mount *mp = tp->t_mountp;
struct xfs_buf *agbp;
xfs_agnumber_t agno;
int error;
int ialloced;
int noroom = 0;
xfs_agnumber_t start_agno;
struct xfs_perag *pag;
if (*IO_agbp) {
/*
* If the caller passes in a pointer to the AGI buffer,
* continue where we left off before. In this case, we
* know that the allocation group has free inodes.
*/
agbp = *IO_agbp;
goto out_alloc;
}
/*
* We do not have an agbp, so select an initial allocation
* group for inode allocation.
*/
start_agno = xfs_ialloc_ag_select(tp, parent, mode, okalloc);
if (start_agno == NULLAGNUMBER) {
*inop = NULLFSINO;
return 0;
}
/*
* If we have already hit the ceiling of inode blocks then clear
* okalloc so we scan all available agi structures for a free
* inode.
*/
if (mp->m_maxicount &&
mp->m_sb.sb_icount + XFS_IALLOC_INODES(mp) > mp->m_maxicount) {
noroom = 1;
okalloc = 0;
}
/*
* Loop until we find an allocation group that either has free inodes
* or in which we can allocate some inodes. Iterate through the
* allocation groups upward, wrapping at the end.
*/
agno = start_agno;
for (;;) {
pag = xfs_perag_get(mp, agno);
if (!pag->pagi_inodeok) {
xfs_ialloc_next_ag(mp);
goto nextag;
}
if (!pag->pagi_init) {
error = xfs_ialloc_pagi_init(mp, tp, agno);
if (error)
goto out_error;
}
/*
* Do a first racy fast path check if this AG is usable.
*/
if (!pag->pagi_freecount && !okalloc)
goto nextag;
/*
* Then read in the AGI buffer and recheck with the AGI buffer
* lock held.
*/
error = xfs_ialloc_read_agi(mp, tp, agno, &agbp);
if (error)
goto out_error;
if (pag->pagi_freecount) {
xfs_perag_put(pag);
goto out_alloc;
}
if (!okalloc)
goto nextag_relse_buffer;
error = xfs_ialloc_ag_alloc(tp, agbp, &ialloced);
if (error) {
xfs_trans_brelse(tp, agbp);
if (error != ENOSPC)
goto out_error;
xfs_perag_put(pag);
*inop = NULLFSINO;
return 0;
}
if (ialloced) {
/*
* We successfully allocated some inodes, return
* the current context to the caller so that it
* can commit the current transaction and call
* us again where we left off.
*/
ASSERT(pag->pagi_freecount > 0);
xfs_perag_put(pag);
*IO_agbp = agbp;
*inop = NULLFSINO;
return 0;
}
nextag_relse_buffer:
xfs_trans_brelse(tp, agbp);
nextag:
xfs_perag_put(pag);
if (++agno == mp->m_sb.sb_agcount)
agno = 0;
if (agno == start_agno) {
*inop = NULLFSINO;
return noroom ? ENOSPC : 0;
}
}
out_alloc:
*IO_agbp = NULL;
return xfs_dialloc_ag(tp, agbp, parent, inop);
out_error:
xfs_perag_put(pag);
return XFS_ERROR(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);
}
STATIC int
xfs_trim_extents(
struct xfs_mount *mp,
xfs_agnumber_t agno,
xfs_fsblock_t start,
xfs_fsblock_t len,
xfs_fsblock_t minlen,
__uint64_t *blocks_trimmed)
{
struct block_device *bdev = mp->m_ddev_targp->bt_bdev;
struct xfs_btree_cur *cur;
struct xfs_buf *agbp;
struct xfs_perag *pag;
int error;
int i;
pag = xfs_perag_get(mp, agno);
error = xfs_alloc_read_agf(mp, NULL, agno, 0, &agbp);
if (error || !agbp)
goto out_put_perag;
cur = xfs_allocbt_init_cursor(mp, NULL, agbp, agno, XFS_BTNUM_CNT);
/*
* Force out the log. This means any transactions that might have freed
* space before we took the AGF buffer lock are now on disk, and the
* volatile disk cache is flushed.
*/
xfs_log_force(mp, XFS_LOG_SYNC);
/*
* Look up the longest btree in the AGF and start with it.
*/
error = xfs_alloc_lookup_le(cur, 0,
XFS_BUF_TO_AGF(agbp)->agf_longest, &i);
if (error)
goto out_del_cursor;
/*
* Loop until we are done with all extents that are large
* enough to be worth discarding.
*/
while (i) {
xfs_agblock_t fbno;
xfs_extlen_t flen;
error = xfs_alloc_get_rec(cur, &fbno, &flen, &i);
if (error)
goto out_del_cursor;
XFS_WANT_CORRUPTED_GOTO(i == 1, out_del_cursor);
ASSERT(flen <= XFS_BUF_TO_AGF(agbp)->agf_longest);
/*
* Too small? Give up.
*/
if (flen < minlen) {
trace_xfs_discard_toosmall(mp, agno, fbno, flen);
goto out_del_cursor;
}
/*
* If the extent is entirely outside of the range we are
* supposed to discard skip it. Do not bother to trim
* down partially overlapping ranges for now.
*/
if (XFS_AGB_TO_FSB(mp, agno, fbno) + flen < start ||
XFS_AGB_TO_FSB(mp, agno, fbno) >= start + len) {
trace_xfs_discard_exclude(mp, agno, fbno, flen);
goto next_extent;
}
/*
* If any blocks in the range are still busy, skip the
* discard and try again the next time.
*/
if (xfs_alloc_busy_search(mp, agno, fbno, flen)) {
trace_xfs_discard_busy(mp, agno, fbno, flen);
goto next_extent;
}
trace_xfs_discard_extent(mp, agno, fbno, flen);
error = -blkdev_issue_discard(bdev,
XFS_AGB_TO_DADDR(mp, agno, fbno),
XFS_FSB_TO_BB(mp, flen),
GFP_NOFS, 0);
if (error)
goto out_del_cursor;
*blocks_trimmed += flen;
next_extent:
error = xfs_btree_decrement(cur, 0, &i);
if (error)
goto out_del_cursor;
}
out_del_cursor:
xfs_btree_del_cursor(cur, error ? XFS_BTREE_ERROR : XFS_BTREE_NOERROR);
xfs_buf_relse(agbp);
out_put_perag:
xfs_perag_put(pag);
return error;
}
static int
_xfs_filestream_pick_ag(
xfs_mount_t *mp,
xfs_agnumber_t startag,
xfs_agnumber_t *agp,
int flags,
xfs_extlen_t minlen)
{
int streams, max_streams;
int err, trylock, nscan;
xfs_extlen_t longest, free, minfree, maxfree = 0;
xfs_agnumber_t ag, max_ag = NULLAGNUMBER;
struct xfs_perag *pag;
/* 2% of an AG's blocks must be free for it to be chosen. */
minfree = mp->m_sb.sb_agblocks / 50;
ag = startag;
*agp = NULLAGNUMBER;
/* For the first pass, don't sleep trying to init the per-AG. */
trylock = XFS_ALLOC_FLAG_TRYLOCK;
for (nscan = 0; 1; nscan++) {
pag = xfs_perag_get(mp, ag);
TRACE_AG_SCAN(mp, ag, atomic_read(&pag->pagf_fstrms));
if (!pag->pagf_init) {
err = xfs_alloc_pagf_init(mp, NULL, ag, trylock);
if (err && !trylock) {
xfs_perag_put(pag);
return err;
}
}
/* Might fail sometimes during the 1st pass with trylock set. */
if (!pag->pagf_init)
goto next_ag;
/* Keep track of the AG with the most free blocks. */
if (pag->pagf_freeblks > maxfree) {
maxfree = pag->pagf_freeblks;
max_streams = atomic_read(&pag->pagf_fstrms);
max_ag = ag;
}
/*
* The AG reference count does two things: it enforces mutual
* exclusion when examining the suitability of an AG in this
* loop, and it guards against two filestreams being established
* in the same AG as each other.
*/
if (xfs_filestream_get_ag(mp, ag) > 1) {
xfs_filestream_put_ag(mp, ag);
goto next_ag;
}
longest = xfs_alloc_longest_free_extent(mp, pag);
if (((minlen && longest >= minlen) ||
(!minlen && pag->pagf_freeblks >= minfree)) &&
(!pag->pagf_metadata || !(flags & XFS_PICK_USERDATA) ||
(flags & XFS_PICK_LOWSPACE))) {
/* Break out, retaining the reference on the AG. */
free = pag->pagf_freeblks;
streams = atomic_read(&pag->pagf_fstrms);
xfs_perag_put(pag);
*agp = ag;
break;
}
/* Drop the reference on this AG, it's not usable. */
xfs_filestream_put_ag(mp, ag);
next_ag:
xfs_perag_put(pag);
/* Move to the next AG, wrapping to AG 0 if necessary. */
if (++ag >= mp->m_sb.sb_agcount)
ag = 0;
/* If a full pass of the AGs hasn't been done yet, continue. */
if (ag != startag)
continue;
/* Allow sleeping in xfs_alloc_pagf_init() on the 2nd pass. */
if (trylock != 0) {
trylock = 0;
continue;
}
/* Finally, if lowspace wasn't set, set it for the 3rd pass. */
if (!(flags & XFS_PICK_LOWSPACE)) {
flags |= XFS_PICK_LOWSPACE;
continue;
}
/*
* Take the AG with the most free space, regardless of whether
* it's already in use by another filestream.
*/
if (max_ag != NULLAGNUMBER) {
xfs_filestream_get_ag(mp, max_ag);
TRACE_AG_PICK1(mp, max_ag, maxfree);
streams = max_streams;
free = maxfree;
*agp = max_ag;
break;
}
/* take AG 0 if none matched */
TRACE_AG_PICK1(mp, max_ag, maxfree);
*agp = 0;
return 0;
}
TRACE_AG_PICK2(mp, startag, *agp, streams, free, nscan, flags);
return 0;
}
