int nfs_writepages(struct address_space *mapping, struct writeback_control *wbc)
{
struct inode *inode = mapping->host;
unsigned long *bitlock = &NFS_I(inode)->flags;
struct nfs_pageio_descriptor pgio;
int err;
/* Stop dirtying of new pages while we sync */
err = wait_on_bit_lock(bitlock, NFS_INO_FLUSHING,
nfs_wait_bit_killable, TASK_KILLABLE);
if (err)
goto out_err;
nfs_inc_stats(inode, NFSIOS_VFSWRITEPAGES);
nfs_pageio_init_write(&pgio, inode, wb_priority(wbc));
err = write_cache_pages(mapping, wbc, nfs_writepages_callback, &pgio);
nfs_pageio_complete(&pgio);
clear_bit_unlock(NFS_INO_FLUSHING, bitlock);
smp_mb__after_clear_bit();
wake_up_bit(bitlock, NFS_INO_FLUSHING);
if (err < 0)
goto out_err;
err = pgio.pg_error;
if (err < 0)
goto out_err;
return 0;
out_err:
return err;
}
static void gdlm_recover_done(void *arg, struct dlm_slot *slots, int num_slots,
int our_slot, uint32_t generation)
{
struct gfs2_sbd *sdp = arg;
struct lm_lockstruct *ls = &sdp->sd_lockstruct;
/* ensure the ls jid arrays are large enough */
set_recover_size(sdp, slots, num_slots);
spin_lock(&ls->ls_recover_spin);
ls->ls_recover_start = generation;
if (!ls->ls_recover_mount) {
ls->ls_recover_mount = generation;
ls->ls_jid = our_slot - 1;
}
if (!test_bit(DFL_UNMOUNT, &ls->ls_recover_flags))
queue_delayed_work(gfs2_control_wq, &sdp->sd_control_work, 0);
clear_bit(DFL_DLM_RECOVERY, &ls->ls_recover_flags);
smp_mb__after_atomic();
wake_up_bit(&ls->ls_recover_flags, DFL_DLM_RECOVERY);
spin_unlock(&ls->ls_recover_spin);
}
/**
* fscache_object_lookup_negative - Note negative cookie lookup
* @object: Object pointing to cookie to mark
*
* Note negative lookup, permitting those waiting to read data from an already
* existing backing object to continue as there's no data for them to read.
*/
void fscache_object_lookup_negative(struct fscache_object *object)
{
struct fscache_cookie *cookie = object->cookie;
_enter("{OBJ%x,%s}",
object->debug_id, fscache_object_states[object->state]);
spin_lock(&object->lock);
if (object->state == FSCACHE_OBJECT_LOOKING_UP) {
fscache_stat(&fscache_n_object_lookups_negative);
/* transit here to allow write requests to begin stacking up
* and read requests to begin returning ENODATA */
object->state = FSCACHE_OBJECT_CREATING;
spin_unlock(&object->lock);
set_bit(FSCACHE_COOKIE_PENDING_FILL, &cookie->flags);
set_bit(FSCACHE_COOKIE_NO_DATA_YET, &cookie->flags);
_debug("wake up lookup %p", &cookie->flags);
smp_mb__before_clear_bit();
clear_bit(FSCACHE_COOKIE_LOOKING_UP, &cookie->flags);
smp_mb__after_clear_bit();
wake_up_bit(&cookie->flags, FSCACHE_COOKIE_LOOKING_UP);
set_bit(FSCACHE_OBJECT_EV_REQUEUE, &object->events);
} else {
ASSERTCMP(object->state, ==, FSCACHE_OBJECT_CREATING);
spin_unlock(&object->lock);
}
_leave("");
}
/**
* fscache_obtained_object - Note successful object lookup or creation
* @object: Object pointing to cookie to mark
*
* Note successful lookup and/or creation, permitting those waiting to write
* data to a backing object to continue.
*
* Note that after calling this, an object's cookie may be relinquished by the
* netfs, and so must be accessed with object lock held.
*/
void fscache_obtained_object(struct fscache_object *object)
{
struct fscache_cookie *cookie = object->cookie;
_enter("{OBJ%x,%s}", object->debug_id, object->state->name);
/* if we were still looking up, then we must have a positive lookup
* result, in which case there may be data available */
if (!test_and_set_bit(FSCACHE_OBJECT_IS_LOOKED_UP, &object->flags)) {
fscache_stat(&fscache_n_object_lookups_positive);
/* We do (presumably) have data */
clear_bit_unlock(FSCACHE_COOKIE_NO_DATA_YET, &cookie->flags);
clear_bit(FSCACHE_COOKIE_UNAVAILABLE, &cookie->flags);
/* Allow write requests to begin stacking up and read requests
* to begin shovelling data.
*/
clear_bit_unlock(FSCACHE_COOKIE_LOOKING_UP, &cookie->flags);
wake_up_bit(&cookie->flags, FSCACHE_COOKIE_LOOKING_UP);
} else {
fscache_stat(&fscache_n_object_created);
}
set_bit(FSCACHE_OBJECT_IS_AVAILABLE, &object->flags);
_leave("");
}
static void gfs2_clear_glop_pending(struct gfs2_inode *ip)
{
if (!ip)
return;
clear_bit_unlock(GIF_GLOP_PENDING, &ip->i_flags);
wake_up_bit(&ip->i_flags, GIF_GLOP_PENDING);
}
static int dvb_usb_stop_feed(struct dvb_demux_feed *dvbdmxfeed)
{
struct dvb_usb_adapter *adap = dvbdmxfeed->demux->priv;
struct dvb_usb_device *d = adap_to_d(adap);
int ret = 0;
dev_dbg(&d->udev->dev,
"%s: adap=%d active_fe=%d feed_type=%d setting pid [%s]: %04x (%04d) at index %d\n",
__func__, adap->id, adap->active_fe, dvbdmxfeed->type,
adap->pid_filtering ? "yes" : "no", dvbdmxfeed->pid,
dvbdmxfeed->pid, dvbdmxfeed->index);
if (adap->active_fe == -1)
return -EINVAL;
/* remove PID from device HW PID filter */
if (adap->pid_filtering && adap->props->pid_filter) {
ret = adap->props->pid_filter(adap, dvbdmxfeed->index,
dvbdmxfeed->pid, 0);
if (ret)
dev_err(&d->udev->dev, "%s: pid_filter() failed=%d\n",
KBUILD_MODNAME, ret);
}
/* we cannot stop streaming until last PID is removed */
if (--adap->feed_count > 0)
goto skip_feed_stop;
/* ask device to stop streaming */
if (d->props->streaming_ctrl) {
ret = d->props->streaming_ctrl(adap->fe[adap->active_fe], 0);
if (ret)
dev_err(&d->udev->dev,
"%s: streaming_ctrl() failed=%d\n",
KBUILD_MODNAME, ret);
}
/* disable HW PID filter */
if (adap->pid_filtering && adap->props->pid_filter_ctrl) {
ret = adap->props->pid_filter_ctrl(adap, 0);
if (ret)
dev_err(&d->udev->dev,
"%s: pid_filter_ctrl() failed=%d\n",
KBUILD_MODNAME, ret);
}
/* kill USB streaming packets */
usb_urb_killv2(&adap->stream);
/* clear 'streaming' status bit */
clear_bit(ADAP_STREAMING, &adap->state_bits);
smp_mb__after_atomic();
wake_up_bit(&adap->state_bits, ADAP_STREAMING);
skip_feed_stop:
if (ret)
dev_dbg(&d->udev->dev, "%s: failed=%d\n", __func__, ret);
return ret;
}
/*
* Unlock cookie management lock
*/
static inline void nfs_fscache_inode_unlock(struct inode *inode)
{
struct nfs_inode *nfsi = NFS_I(inode);
smp_mb__before_clear_bit();
clear_bit(NFS_INO_FSCACHE_LOCK, &nfsi->flags);
smp_mb__after_clear_bit();
wake_up_bit(&nfsi->flags, NFS_INO_FSCACHE_LOCK);
}
static void
nfs_iocounter_dec(struct nfs_io_counter *c)
{
if (atomic_dec_and_test(&c->io_count)) {
clear_bit(NFS_IO_INPROGRESS, &c->flags);
smp_mb__after_clear_bit();
wake_up_bit(&c->flags, NFS_IO_INPROGRESS);
}
}
/*
* start an op running
*/
static void fscache_run_op(struct fscache_object *object,
struct fscache_operation *op)
{
object->n_in_progress++;
if (test_and_clear_bit(FSCACHE_OP_WAITING, &op->flags))
wake_up_bit(&op->flags, FSCACHE_OP_WAITING);
if (op->processor)
fscache_enqueue_operation(op);
fscache_stat(&fscache_n_op_run);
}
static bool afs_vl_probe_done(struct afs_vlserver *server)
{
if (!atomic_dec_and_test(&server->probe_outstanding))
return false;
wake_up_var(&server->probe_outstanding);
clear_bit_unlock(AFS_VLSERVER_FL_PROBING, &server->flags);
wake_up_bit(&server->flags, AFS_VLSERVER_FL_PROBING);
return true;
}
/**
* nfs_unlock_request - Unlock request and wake up sleepers.
* @req:
*/
void nfs_unlock_request(struct nfs_page *req)
{
if (!NFS_WBACK_BUSY(req)) {
printk(KERN_ERR "NFS: Invalid unlock attempted\n");
BUG();
}
smp_mb__before_clear_bit();
clear_bit(PG_BUSY, &req->wb_flags);
smp_mb__after_clear_bit();
wake_up_bit(&req->wb_flags, PG_BUSY);
}
/*
* nfs_page_group_unlock - unlock the head of the page group
* @req - request in group that is to be unlocked
*/
void
nfs_page_group_unlock(struct nfs_page *req)
{
struct nfs_page *head = req->wb_head;
WARN_ON_ONCE(head != head->wb_head);
smp_mb__before_atomic();
clear_bit(PG_HEADLOCK, &head->wb_flags);
smp_mb__after_atomic();
wake_up_bit(&head->wb_flags, PG_HEADLOCK);
}
STATIC void
xfs_inode_item_unpin(
struct xfs_log_item *lip,
int remove)
{
struct xfs_inode *ip = INODE_ITEM(lip)->ili_inode;
trace_xfs_inode_unpin(ip, _RET_IP_);
ASSERT(atomic_read(&ip->i_pincount) > 0);
if (atomic_dec_and_test(&ip->i_pincount))
wake_up_bit(&ip->i_flags, __XFS_IPINNED_BIT);
}
/**
* fscache_obtained_object - Note successful object lookup or creation
* @object: Object pointing to cookie to mark
*
* Note successful lookup and/or creation, permitting those waiting to write
* data to a backing object to continue.
*
* Note that after calling this, an object's cookie may be relinquished by the
* netfs, and so must be accessed with object lock held.
*/
void fscache_obtained_object(struct fscache_object *object)
{
struct fscache_cookie *cookie = object->cookie;
_enter("{OBJ%x,%s}",
object->debug_id, fscache_object_states[object->state]);
/* if we were still looking up, then we must have a positive lookup
* result, in which case there may be data available */
spin_lock(&object->lock);
if (object->state == FSCACHE_OBJECT_LOOKING_UP) {
fscache_stat(&fscache_n_object_lookups_positive);
clear_bit(FSCACHE_COOKIE_NO_DATA_YET, &cookie->flags);
object->state = FSCACHE_OBJECT_AVAILABLE;
spin_unlock(&object->lock);
smp_mb__before_clear_bit();
clear_bit(FSCACHE_COOKIE_LOOKING_UP, &cookie->flags);
smp_mb__after_clear_bit();
wake_up_bit(&cookie->flags, FSCACHE_COOKIE_LOOKING_UP);
set_bit(FSCACHE_OBJECT_EV_REQUEUE, &object->events);
} else {
ASSERTCMP(object->state, ==, FSCACHE_OBJECT_CREATING);
fscache_stat(&fscache_n_object_created);
object->state = FSCACHE_OBJECT_AVAILABLE;
spin_unlock(&object->lock);
set_bit(FSCACHE_OBJECT_EV_REQUEUE, &object->events);
smp_wmb();
}
if (test_and_clear_bit(FSCACHE_COOKIE_CREATING, &cookie->flags))
wake_up_bit(&cookie->flags, FSCACHE_COOKIE_CREATING);
_leave("");
}
/*
* handle an object that has just become available
*/
static void fscache_object_available(struct fscache_object *object)
{
_enter("{OBJ%x}", object->debug_id);
spin_lock(&object->lock);
if (object->cookie &&
test_and_clear_bit(FSCACHE_COOKIE_CREATING, &object->cookie->flags))
wake_up_bit(&object->cookie->flags, FSCACHE_COOKIE_CREATING);
fscache_done_parent_op(object);
if (object->n_in_progress == 0) {
if (object->n_ops > 0) {
ASSERTCMP(object->n_ops, >=, object->n_obj_ops);
fscache_start_operations(object);
} else {
/*
* Mark inode dirty to delete. (called from ->drop_inode()).
* Caller must hold inode->i_lock.
*/
void tux3_mark_inode_to_delete(struct inode *inode)
{
struct sb *sb = tux_sb(inode->i_sb);
struct tux3_inode *tuxnode = tux_inode(inode);
unsigned delta;
/* inode has dead mark already */
if (tux3_inode_is_dead(tuxnode))
return;
change_begin_atomic(sb);
delta = tux3_inode_delta(inode);
__tux3_mark_inode_to_delete(inode, delta);
/*
* Hack: this is called under inode->i_lock. So, we have to
* release inode->i_lock to call mark_inode_dirty_sync().
*
* FIXME: we want to set I_DIRTY_SYNC (I_DIRTY_SYNC will
* prevent the indo is freed) and wakeup flusher if need,
* while preventing inode is freed. Need better way to do.
*/
if (!(tux3_dirty_flags(inode, delta) & I_DIRTY_SYNC)) {
/* FIXME: I_REFERENCED can't prevent completely */
//inode->i_state |= I_REFERENCED;
/* FIXME: I_WILL_FREE will bother igrab() grabs reference */
inode->i_state |= I_WILL_FREE;
spin_unlock(&inode->i_lock);
/* Tell dead inode to backend by marking as dirty. */
tux3_mark_inode_dirty_sync(inode);
spin_lock(&inode->i_lock);
inode->i_state &= ~I_WILL_FREE;
#ifdef __KERNEL__
wake_up_bit(&inode->i_state, __I_NEW);
#endif
}
change_end_atomic(sb);
}
/**
* fscache_object_lookup_negative - Note negative cookie lookup
* @object: Object pointing to cookie to mark
*
* Note negative lookup, permitting those waiting to read data from an already
* existing backing object to continue as there's no data for them to read.
*/
void fscache_object_lookup_negative(struct fscache_object *object)
{
struct fscache_cookie *cookie = object->cookie;
_enter("{OBJ%x,%s}", object->debug_id, object->state->name);
if (!test_and_set_bit(FSCACHE_OBJECT_IS_LOOKED_UP, &object->flags)) {
fscache_stat(&fscache_n_object_lookups_negative);
/* Allow write requests to begin stacking up and read requests to begin
* returning ENODATA.
*/
set_bit(FSCACHE_COOKIE_NO_DATA_YET, &cookie->flags);
clear_bit(FSCACHE_COOKIE_UNAVAILABLE, &cookie->flags);
_debug("wake up lookup %p", &cookie->flags);
clear_bit_unlock(FSCACHE_COOKIE_LOOKING_UP, &cookie->flags);
wake_up_bit(&cookie->flags, FSCACHE_COOKIE_LOOKING_UP);
}
_leave("");
}
static int dvb_usb_fe_sleep(struct dvb_frontend *fe)
{
int ret;
struct dvb_usb_adapter *adap = fe->dvb->priv;
struct dvb_usb_device *d = adap_to_d(adap);
dev_dbg(&d->udev->dev, "%s: adap=%d fe=%d\n", __func__, adap->id,
fe->id);
if (!adap->suspend_resume_active) {
set_bit(ADAP_SLEEP, &adap->state_bits);
wait_on_bit(&adap->state_bits, ADAP_STREAMING,
TASK_UNINTERRUPTIBLE);
}
if (adap->fe_sleep[fe->id]) {
ret = adap->fe_sleep[fe->id](fe);
if (ret < 0)
goto err;
}
if (d->props->frontend_ctrl) {
ret = d->props->frontend_ctrl(fe, 0);
if (ret < 0)
goto err;
}
ret = dvb_usbv2_device_power_ctrl(d, 0);
if (ret < 0)
goto err;
err:
if (!adap->suspend_resume_active) {
adap->active_fe = -1;
clear_bit(ADAP_SLEEP, &adap->state_bits);
smp_mb__after_atomic();
wake_up_bit(&adap->state_bits, ADAP_SLEEP);
}
dev_dbg(&d->udev->dev, "%s: ret=%d\n", __func__, ret);
return ret;
}
static int dvb_usb_fe_init(struct dvb_frontend *fe)
{
int ret;
struct dvb_usb_adapter *adap = fe->dvb->priv;
struct dvb_usb_device *d = adap_to_d(adap);
dev_dbg(&d->udev->dev, "%s: adap=%d fe=%d\n", __func__, adap->id,
fe->id);
if (!adap->suspend_resume_active) {
adap->active_fe = fe->id;
set_bit(ADAP_INIT, &adap->state_bits);
}
ret = dvb_usbv2_device_power_ctrl(d, 1);
if (ret < 0)
goto err;
if (d->props->frontend_ctrl) {
ret = d->props->frontend_ctrl(fe, 1);
if (ret < 0)
goto err;
}
if (adap->fe_init[fe->id]) {
ret = adap->fe_init[fe->id](fe);
if (ret < 0)
goto err;
}
err:
if (!adap->suspend_resume_active) {
clear_bit(ADAP_INIT, &adap->state_bits);
smp_mb__after_atomic();
wake_up_bit(&adap->state_bits, ADAP_INIT);
}
dev_dbg(&d->udev->dev, "%s: ret=%d\n", __func__, ret);
return ret;
}
static int
id_to_sid(unsigned long cid, uint sidtype, struct cifs_sid *ssid)
{
int rc = 0;
struct key *sidkey;
const struct cred *saved_cred;
struct cifs_sid *lsid;
struct cifs_sid_id *psidid, *npsidid;
struct rb_root *cidtree;
spinlock_t *cidlock;
if (sidtype == SIDOWNER) {
cidlock = &siduidlock;
cidtree = &uidtree;
} else if (sidtype == SIDGROUP) {
cidlock = &sidgidlock;
cidtree = &gidtree;
} else
return -EINVAL;
spin_lock(cidlock);
psidid = sid_rb_search(cidtree, cid);
if (!psidid) {
spin_unlock(cidlock);
npsidid = kzalloc(sizeof(struct cifs_sid_id), GFP_KERNEL);
if (!npsidid)
return -ENOMEM;
npsidid->sidstr = kmalloc(SIDLEN, GFP_KERNEL);
if (!npsidid->sidstr) {
kfree(npsidid);
return -ENOMEM;
}
spin_lock(cidlock);
psidid = sid_rb_search(cidtree, cid);
if (psidid) {
++psidid->refcount;
spin_unlock(cidlock);
kfree(npsidid->sidstr);
kfree(npsidid);
} else {
psidid = npsidid;
sid_rb_insert(cidtree, cid, &psidid,
sidtype == SIDOWNER ? "oi:" : "gi:");
++psidid->refcount;
spin_unlock(cidlock);
}
} else {
++psidid->refcount;
spin_unlock(cidlock);
}
if (test_bit(SID_ID_MAPPED, &psidid->state)) {
memcpy(ssid, &psidid->sid, sizeof(struct cifs_sid));
psidid->time = jiffies;
goto id_sid_out;
}
if (time_after(psidid->time + SID_MAP_RETRY, jiffies)) {
rc = -EINVAL;
goto id_sid_out;
}
if (!test_and_set_bit(SID_ID_PENDING, &psidid->state)) {
saved_cred = override_creds(root_cred);
sidkey = request_key(&cifs_idmap_key_type, psidid->sidstr, "");
if (IS_ERR(sidkey)) {
rc = -EINVAL;
cFYI(1, "%s: Can't map and id to a SID", __func__);
} else {
lsid = (struct cifs_sid *)sidkey->payload.data;
memcpy(&psidid->sid, lsid,
sidkey->datalen < sizeof(struct cifs_sid) ?
sidkey->datalen : sizeof(struct cifs_sid));
memcpy(ssid, &psidid->sid,
sidkey->datalen < sizeof(struct cifs_sid) ?
sidkey->datalen : sizeof(struct cifs_sid));
set_bit(SID_ID_MAPPED, &psidid->state);
key_put(sidkey);
kfree(psidid->sidstr);
}
psidid->time = jiffies;
revert_creds(saved_cred);
clear_bit(SID_ID_PENDING, &psidid->state);
wake_up_bit(&psidid->state, SID_ID_PENDING);
} else {
rc = wait_on_bit(&psidid->state, SID_ID_PENDING,
sidid_pending_wait, TASK_INTERRUPTIBLE);
if (rc) {
cFYI(1, "%s: sidid_pending_wait interrupted %d",
__func__, rc);
--psidid->refcount;
return rc;
}
if (test_bit(SID_ID_MAPPED, &psidid->state))
memcpy(ssid, &psidid->sid, sizeof(struct cifs_sid));
else
rc = -EINVAL;
}
id_sid_out:
--psidid->refcount;
return rc;
}
/*
* Update a cell's VL server address list from the DNS.
*/
static void afs_update_cell(struct afs_cell *cell)
{
struct afs_vlserver_list *vllist, *old;
unsigned int min_ttl = READ_ONCE(afs_cell_min_ttl);
unsigned int max_ttl = READ_ONCE(afs_cell_max_ttl);
time64_t now, expiry = 0;
_enter("%s", cell->name);
vllist = afs_dns_query(cell, &expiry);
now = ktime_get_real_seconds();
if (min_ttl > max_ttl)
max_ttl = min_ttl;
if (expiry < now + min_ttl)
expiry = now + min_ttl;
else if (expiry > now + max_ttl)
expiry = now + max_ttl;
if (IS_ERR(vllist)) {
switch (PTR_ERR(vllist)) {
case -ENODATA:
case -EDESTADDRREQ:
/* The DNS said that the cell does not exist or there
* weren't any addresses to be had.
*/
set_bit(AFS_CELL_FL_NOT_FOUND, &cell->flags);
clear_bit(AFS_CELL_FL_DNS_FAIL, &cell->flags);
cell->dns_expiry = expiry;
break;
case -EAGAIN:
case -ECONNREFUSED:
default:
set_bit(AFS_CELL_FL_DNS_FAIL, &cell->flags);
cell->dns_expiry = now + 10;
break;
}
cell->error = -EDESTADDRREQ;
} else {
clear_bit(AFS_CELL_FL_DNS_FAIL, &cell->flags);
clear_bit(AFS_CELL_FL_NOT_FOUND, &cell->flags);
/* Exclusion on changing vl_addrs is achieved by a
* non-reentrant work item.
*/
old = rcu_dereference_protected(cell->vl_servers, true);
rcu_assign_pointer(cell->vl_servers, vllist);
cell->dns_expiry = expiry;
if (old)
afs_put_vlserverlist(cell->net, old);
}
if (test_and_clear_bit(AFS_CELL_FL_NO_LOOKUP_YET, &cell->flags))
wake_up_bit(&cell->flags, AFS_CELL_FL_NO_LOOKUP_YET);
now = ktime_get_real_seconds();
afs_set_cell_timer(cell->net, cell->dns_expiry - now);
_leave("");
}
/*
* process events that have been sent to an object's state machine
* - initiates parent lookup
* - does object lookup
* - does object creation
* - does object recycling and retirement
* - does object withdrawal
*/
static void fscache_object_state_machine(struct fscache_object *object)
{
enum fscache_object_state new_state;
struct fscache_cookie *cookie;
ASSERT(object != NULL);
_enter("{OBJ%x,%s,%lx}",
object->debug_id, fscache_object_states[object->state],
object->events);
switch (object->state) {
/* wait for the parent object to become ready */
case FSCACHE_OBJECT_INIT:
object->event_mask =
ULONG_MAX & ~(1 << FSCACHE_OBJECT_EV_CLEARED);
fscache_initialise_object(object);
goto done;
/* look up the object metadata on disk */
case FSCACHE_OBJECT_LOOKING_UP:
fscache_lookup_object(object);
goto lookup_transit;
/* create the object metadata on disk */
case FSCACHE_OBJECT_CREATING:
fscache_lookup_object(object);
goto lookup_transit;
/* handle an object becoming available; start pending
* operations and queue dependent operations for processing */
case FSCACHE_OBJECT_AVAILABLE:
fscache_object_available(object);
goto active_transit;
/* normal running state */
case FSCACHE_OBJECT_ACTIVE:
goto active_transit;
/* Invalidate an object on disk */
case FSCACHE_OBJECT_INVALIDATING:
clear_bit(FSCACHE_OBJECT_EV_INVALIDATE, &object->events);
fscache_stat(&fscache_n_invalidates_run);
fscache_stat(&fscache_n_cop_invalidate_object);
fscache_invalidate_object(object);
fscache_stat_d(&fscache_n_cop_invalidate_object);
fscache_raise_event(object, FSCACHE_OBJECT_EV_UPDATE);
goto active_transit;
/* update the object metadata on disk */
case FSCACHE_OBJECT_UPDATING:
clear_bit(FSCACHE_OBJECT_EV_UPDATE, &object->events);
fscache_stat(&fscache_n_updates_run);
fscache_stat(&fscache_n_cop_update_object);
object->cache->ops->update_object(object);
fscache_stat_d(&fscache_n_cop_update_object);
goto active_transit;
/* handle an object dying during lookup or creation */
case FSCACHE_OBJECT_LC_DYING:
object->event_mask &= ~(1 << FSCACHE_OBJECT_EV_UPDATE);
fscache_stat(&fscache_n_cop_lookup_complete);
object->cache->ops->lookup_complete(object);
fscache_stat_d(&fscache_n_cop_lookup_complete);
spin_lock(&object->lock);
object->state = FSCACHE_OBJECT_DYING;
cookie = object->cookie;
if (cookie) {
if (test_and_clear_bit(FSCACHE_COOKIE_LOOKING_UP,
&cookie->flags))
wake_up_bit(&cookie->flags,
FSCACHE_COOKIE_LOOKING_UP);
if (test_and_clear_bit(FSCACHE_COOKIE_CREATING,
&cookie->flags))
wake_up_bit(&cookie->flags,
FSCACHE_COOKIE_CREATING);
}
spin_unlock(&object->lock);
fscache_done_parent_op(object);
/* wait for completion of all active operations on this object
* and the death of all child objects of this object */
case FSCACHE_OBJECT_DYING:
dying:
clear_bit(FSCACHE_OBJECT_EV_CLEARED, &object->events);
spin_lock(&object->lock);
_debug("dying OBJ%x {%d,%d}",
object->debug_id, object->n_ops, object->n_children);
if (object->n_ops == 0 && object->n_children == 0) {
object->event_mask &=
~(1 << FSCACHE_OBJECT_EV_CLEARED);
object->event_mask |=
(1 << FSCACHE_OBJECT_EV_WITHDRAW) |
(1 << FSCACHE_OBJECT_EV_RETIRE) |
(1 << FSCACHE_OBJECT_EV_RELEASE) |
(1 << FSCACHE_OBJECT_EV_ERROR);
} else {
object->event_mask &=
~((1 << FSCACHE_OBJECT_EV_WITHDRAW) |
(1 << FSCACHE_OBJECT_EV_RETIRE) |
(1 << FSCACHE_OBJECT_EV_RELEASE) |
(1 << FSCACHE_OBJECT_EV_ERROR));
object->event_mask |=
1 << FSCACHE_OBJECT_EV_CLEARED;
}
spin_unlock(&object->lock);
fscache_enqueue_dependents(object);
fscache_start_operations(object);
goto terminal_transit;
/* handle an abort during initialisation */
case FSCACHE_OBJECT_ABORT_INIT:
_debug("handle abort init %lx", object->events);
object->event_mask &= ~(1 << FSCACHE_OBJECT_EV_UPDATE);
spin_lock(&object->lock);
fscache_dequeue_object(object);
object->state = FSCACHE_OBJECT_DYING;
if (test_and_clear_bit(FSCACHE_COOKIE_CREATING,
&object->cookie->flags))
wake_up_bit(&object->cookie->flags,
FSCACHE_COOKIE_CREATING);
spin_unlock(&object->lock);
goto dying;
/* handle the netfs releasing an object and possibly marking it
* obsolete too */
case FSCACHE_OBJECT_RELEASING:
case FSCACHE_OBJECT_RECYCLING:
object->event_mask &=
~((1 << FSCACHE_OBJECT_EV_WITHDRAW) |
(1 << FSCACHE_OBJECT_EV_RETIRE) |
(1 << FSCACHE_OBJECT_EV_RELEASE) |
(1 << FSCACHE_OBJECT_EV_ERROR));
fscache_release_object(object);
spin_lock(&object->lock);
object->state = FSCACHE_OBJECT_DEAD;
spin_unlock(&object->lock);
fscache_stat(&fscache_n_object_dead);
goto terminal_transit;
/* handle the parent cache of this object being withdrawn from
* active service */
case FSCACHE_OBJECT_WITHDRAWING:
object->event_mask &=
~((1 << FSCACHE_OBJECT_EV_WITHDRAW) |
(1 << FSCACHE_OBJECT_EV_RETIRE) |
(1 << FSCACHE_OBJECT_EV_RELEASE) |
(1 << FSCACHE_OBJECT_EV_ERROR));
fscache_withdraw_object(object);
spin_lock(&object->lock);
object->state = FSCACHE_OBJECT_DEAD;
spin_unlock(&object->lock);
fscache_stat(&fscache_n_object_dead);
goto terminal_transit;
/* complain about the object being woken up once it is
* deceased */
case FSCACHE_OBJECT_DEAD:
printk(KERN_ERR "FS-Cache:"
" Unexpected event in dead state %lx\n",
object->events & object->event_mask);
BUG();
default:
printk(KERN_ERR "FS-Cache: Unknown object state %u\n",
object->state);
BUG();
}
/* determine the transition from a lookup state */
lookup_transit:
switch (fls(object->events & object->event_mask) - 1) {
case FSCACHE_OBJECT_EV_WITHDRAW:
case FSCACHE_OBJECT_EV_RETIRE:
case FSCACHE_OBJECT_EV_RELEASE:
case FSCACHE_OBJECT_EV_ERROR:
new_state = FSCACHE_OBJECT_LC_DYING;
goto change_state;
case FSCACHE_OBJECT_EV_REQUEUE:
goto done;
case -1:
goto done; /* sleep until event */
default:
goto unsupported_event;
}
/* determine the transition from an active state */
active_transit:
switch (fls(object->events & object->event_mask) - 1) {
case FSCACHE_OBJECT_EV_WITHDRAW:
case FSCACHE_OBJECT_EV_RETIRE:
case FSCACHE_OBJECT_EV_RELEASE:
case FSCACHE_OBJECT_EV_ERROR:
new_state = FSCACHE_OBJECT_DYING;
goto change_state;
case FSCACHE_OBJECT_EV_INVALIDATE:
new_state = FSCACHE_OBJECT_INVALIDATING;
goto change_state;
case FSCACHE_OBJECT_EV_UPDATE:
new_state = FSCACHE_OBJECT_UPDATING;
goto change_state;
case -1:
new_state = FSCACHE_OBJECT_ACTIVE;
goto change_state; /* sleep until event */
default:
goto unsupported_event;
}
/* determine the transition from a terminal state */
terminal_transit:
switch (fls(object->events & object->event_mask) - 1) {
case FSCACHE_OBJECT_EV_WITHDRAW:
new_state = FSCACHE_OBJECT_WITHDRAWING;
goto change_state;
case FSCACHE_OBJECT_EV_RETIRE:
new_state = FSCACHE_OBJECT_RECYCLING;
goto change_state;
case FSCACHE_OBJECT_EV_RELEASE:
new_state = FSCACHE_OBJECT_RELEASING;
goto change_state;
case FSCACHE_OBJECT_EV_ERROR:
new_state = FSCACHE_OBJECT_WITHDRAWING;
goto change_state;
case FSCACHE_OBJECT_EV_CLEARED:
new_state = FSCACHE_OBJECT_DYING;
goto change_state;
case -1:
goto done; /* sleep until event */
default:
goto unsupported_event;
}
change_state:
spin_lock(&object->lock);
object->state = new_state;
spin_unlock(&object->lock);
done:
_leave(" [->%s]", fscache_object_states[object->state]);
return;
unsupported_event:
printk(KERN_ERR "FS-Cache:"
" Unsupported event %lx [mask %lx] in state %s\n",
object->events, object->event_mask,
fscache_object_states[object->state]);
BUG();
}
/*
* Notify netfs of invalidation completion.
*/
static inline void fscache_invalidation_complete(struct fscache_cookie *cookie)
{
if (test_and_clear_bit(FSCACHE_COOKIE_INVALIDATING, &cookie->flags))
wake_up_bit(&cookie->flags, FSCACHE_COOKIE_INVALIDATING);
}
/*
* Manage a cell record, initialising and destroying it, maintaining its DNS
* records.
*/
static void afs_manage_cell(struct work_struct *work)
{
struct afs_cell *cell = container_of(work, struct afs_cell, manager);
struct afs_net *net = cell->net;
bool deleted;
int ret, usage;
_enter("%s", cell->name);
again:
_debug("state %u", cell->state);
switch (cell->state) {
case AFS_CELL_INACTIVE:
case AFS_CELL_FAILED:
write_seqlock(&net->cells_lock);
usage = 1;
deleted = atomic_try_cmpxchg_relaxed(&cell->usage, &usage, 0);
if (deleted)
rb_erase(&cell->net_node, &net->cells);
write_sequnlock(&net->cells_lock);
if (deleted)
goto final_destruction;
if (cell->state == AFS_CELL_FAILED)
goto done;
cell->state = AFS_CELL_UNSET;
goto again;
case AFS_CELL_UNSET:
cell->state = AFS_CELL_ACTIVATING;
goto again;
case AFS_CELL_ACTIVATING:
ret = afs_activate_cell(net, cell);
if (ret < 0)
goto activation_failed;
cell->state = AFS_CELL_ACTIVE;
smp_wmb();
clear_bit(AFS_CELL_FL_NOT_READY, &cell->flags);
wake_up_bit(&cell->flags, AFS_CELL_FL_NOT_READY);
goto again;
case AFS_CELL_ACTIVE:
if (atomic_read(&cell->usage) > 1) {
time64_t now = ktime_get_real_seconds();
if (cell->dns_expiry <= now && net->live)
afs_update_cell(cell);
goto done;
}
cell->state = AFS_CELL_DEACTIVATING;
goto again;
case AFS_CELL_DEACTIVATING:
set_bit(AFS_CELL_FL_NOT_READY, &cell->flags);
if (atomic_read(&cell->usage) > 1)
goto reverse_deactivation;
afs_deactivate_cell(net, cell);
cell->state = AFS_CELL_INACTIVE;
goto again;
default:
break;
}
_debug("bad state %u", cell->state);
BUG(); /* Unhandled state */
activation_failed:
cell->error = ret;
afs_deactivate_cell(net, cell);
cell->state = AFS_CELL_FAILED;
smp_wmb();
if (test_and_clear_bit(AFS_CELL_FL_NOT_READY, &cell->flags))
wake_up_bit(&cell->flags, AFS_CELL_FL_NOT_READY);
goto again;
reverse_deactivation:
cell->state = AFS_CELL_ACTIVE;
smp_wmb();
clear_bit(AFS_CELL_FL_NOT_READY, &cell->flags);
wake_up_bit(&cell->flags, AFS_CELL_FL_NOT_READY);
_leave(" [deact->act]");
return;
done:
_leave(" [done %u]", cell->state);
return;
final_destruction:
call_rcu(&cell->rcu, afs_cell_destroy);
afs_dec_cells_outstanding(net);
_leave(" [destruct %d]", atomic_read(&net->cells_outstanding));
}
static void wake_up_ast(struct gdlm_lock *lp)
{
clear_bit(LFL_AST_WAIT, &lp->flags);
smp_mb__after_clear_bit();
wake_up_bit(&lp->flags, LFL_AST_WAIT);
}
static void fscache_object_state_machine(struct fscache_object *object)
{
enum fscache_object_state new_state;
struct fscache_cookie *cookie;
ASSERT(object != NULL);
_enter("{OBJ%x,%s,%lx}",
object->debug_id, fscache_object_states[object->state],
object->events);
switch (object->state) {
case FSCACHE_OBJECT_INIT:
object->event_mask =
ULONG_MAX & ~(1 << FSCACHE_OBJECT_EV_CLEARED);
fscache_initialise_object(object);
goto done;
case FSCACHE_OBJECT_LOOKING_UP:
fscache_lookup_object(object);
goto lookup_transit;
case FSCACHE_OBJECT_CREATING:
fscache_lookup_object(object);
goto lookup_transit;
case FSCACHE_OBJECT_AVAILABLE:
fscache_object_available(object);
goto active_transit;
case FSCACHE_OBJECT_ACTIVE:
goto active_transit;
case FSCACHE_OBJECT_UPDATING:
clear_bit(FSCACHE_OBJECT_EV_UPDATE, &object->events);
fscache_stat(&fscache_n_updates_run);
fscache_stat(&fscache_n_cop_update_object);
object->cache->ops->update_object(object);
fscache_stat_d(&fscache_n_cop_update_object);
goto active_transit;
case FSCACHE_OBJECT_LC_DYING:
object->event_mask &= ~(1 << FSCACHE_OBJECT_EV_UPDATE);
fscache_stat(&fscache_n_cop_lookup_complete);
object->cache->ops->lookup_complete(object);
fscache_stat_d(&fscache_n_cop_lookup_complete);
spin_lock(&object->lock);
object->state = FSCACHE_OBJECT_DYING;
cookie = object->cookie;
if (cookie) {
if (test_and_clear_bit(FSCACHE_COOKIE_LOOKING_UP,
&cookie->flags))
wake_up_bit(&cookie->flags,
FSCACHE_COOKIE_LOOKING_UP);
if (test_and_clear_bit(FSCACHE_COOKIE_CREATING,
&cookie->flags))
wake_up_bit(&cookie->flags,
FSCACHE_COOKIE_CREATING);
}
spin_unlock(&object->lock);
fscache_done_parent_op(object);
case FSCACHE_OBJECT_DYING:
dying:
clear_bit(FSCACHE_OBJECT_EV_CLEARED, &object->events);
spin_lock(&object->lock);
_debug("dying OBJ%x {%d,%d}",
object->debug_id, object->n_ops, object->n_children);
if (object->n_ops == 0 && object->n_children == 0) {
object->event_mask &=
~(1 << FSCACHE_OBJECT_EV_CLEARED);
object->event_mask |=
(1 << FSCACHE_OBJECT_EV_WITHDRAW) |
(1 << FSCACHE_OBJECT_EV_RETIRE) |
(1 << FSCACHE_OBJECT_EV_RELEASE) |
(1 << FSCACHE_OBJECT_EV_ERROR);
} else {
object->event_mask &=
~((1 << FSCACHE_OBJECT_EV_WITHDRAW) |
(1 << FSCACHE_OBJECT_EV_RETIRE) |
(1 << FSCACHE_OBJECT_EV_RELEASE) |
(1 << FSCACHE_OBJECT_EV_ERROR));
object->event_mask |=
1 << FSCACHE_OBJECT_EV_CLEARED;
}
spin_unlock(&object->lock);
fscache_enqueue_dependents(object);
fscache_start_operations(object);
goto terminal_transit;
case FSCACHE_OBJECT_ABORT_INIT:
_debug("handle abort init %lx", object->events);
object->event_mask &= ~(1 << FSCACHE_OBJECT_EV_UPDATE);
spin_lock(&object->lock);
fscache_dequeue_object(object);
object->state = FSCACHE_OBJECT_DYING;
if (test_and_clear_bit(FSCACHE_COOKIE_CREATING,
&object->cookie->flags))
wake_up_bit(&object->cookie->flags,
FSCACHE_COOKIE_CREATING);
spin_unlock(&object->lock);
goto dying;
case FSCACHE_OBJECT_RELEASING:
case FSCACHE_OBJECT_RECYCLING:
object->event_mask &=
~((1 << FSCACHE_OBJECT_EV_WITHDRAW) |
(1 << FSCACHE_OBJECT_EV_RETIRE) |
(1 << FSCACHE_OBJECT_EV_RELEASE) |
(1 << FSCACHE_OBJECT_EV_ERROR));
fscache_release_object(object);
spin_lock(&object->lock);
object->state = FSCACHE_OBJECT_DEAD;
spin_unlock(&object->lock);
fscache_stat(&fscache_n_object_dead);
goto terminal_transit;
case FSCACHE_OBJECT_WITHDRAWING:
object->event_mask &=
~((1 << FSCACHE_OBJECT_EV_WITHDRAW) |
(1 << FSCACHE_OBJECT_EV_RETIRE) |
(1 << FSCACHE_OBJECT_EV_RELEASE) |
(1 << FSCACHE_OBJECT_EV_ERROR));
fscache_withdraw_object(object);
spin_lock(&object->lock);
object->state = FSCACHE_OBJECT_DEAD;
spin_unlock(&object->lock);
fscache_stat(&fscache_n_object_dead);
goto terminal_transit;
case FSCACHE_OBJECT_DEAD:
printk(KERN_ERR "FS-Cache:"
" Unexpected event in dead state %lx\n",
object->events & object->event_mask);
BUG();
default:
printk(KERN_ERR "FS-Cache: Unknown object state %u\n",
object->state);
BUG();
}
lookup_transit:
switch (fls(object->events & object->event_mask) - 1) {
case FSCACHE_OBJECT_EV_WITHDRAW:
case FSCACHE_OBJECT_EV_RETIRE:
case FSCACHE_OBJECT_EV_RELEASE:
case FSCACHE_OBJECT_EV_ERROR:
new_state = FSCACHE_OBJECT_LC_DYING;
goto change_state;
case FSCACHE_OBJECT_EV_REQUEUE:
goto done;
case -1:
goto done;
default:
goto unsupported_event;
}
active_transit:
switch (fls(object->events & object->event_mask) - 1) {
case FSCACHE_OBJECT_EV_WITHDRAW:
case FSCACHE_OBJECT_EV_RETIRE:
case FSCACHE_OBJECT_EV_RELEASE:
case FSCACHE_OBJECT_EV_ERROR:
new_state = FSCACHE_OBJECT_DYING;
goto change_state;
case FSCACHE_OBJECT_EV_UPDATE:
new_state = FSCACHE_OBJECT_UPDATING;
goto change_state;
case -1:
new_state = FSCACHE_OBJECT_ACTIVE;
goto change_state;
default:
goto unsupported_event;
}
terminal_transit:
switch (fls(object->events & object->event_mask) - 1) {
case FSCACHE_OBJECT_EV_WITHDRAW:
new_state = FSCACHE_OBJECT_WITHDRAWING;
goto change_state;
case FSCACHE_OBJECT_EV_RETIRE:
new_state = FSCACHE_OBJECT_RECYCLING;
goto change_state;
case FSCACHE_OBJECT_EV_RELEASE:
new_state = FSCACHE_OBJECT_RELEASING;
goto change_state;
case FSCACHE_OBJECT_EV_ERROR:
new_state = FSCACHE_OBJECT_WITHDRAWING;
goto change_state;
case FSCACHE_OBJECT_EV_CLEARED:
new_state = FSCACHE_OBJECT_DYING;
goto change_state;
case -1:
goto done;
default:
goto unsupported_event;
}
change_state:
spin_lock(&object->lock);
object->state = new_state;
spin_unlock(&object->lock);
done:
_leave(" [->%s]", fscache_object_states[object->state]);
return;
unsupported_event:
printk(KERN_ERR "FS-Cache:"
" Unsupported event %lx [mask %lx] in state %s\n",
object->events, object->event_mask,
fscache_object_states[object->state]);
BUG();
}
/*
* journal_commit_transaction
*
* The primary function for committing a transaction to the log. This
* function is called by the journal thread to begin a complete commit.
*/
void journal_commit_transaction(journal_t *journal)
{
transaction_t *commit_transaction;
struct journal_head *jh, *new_jh, *descriptor;
struct buffer_head **wbuf = journal->j_wbuf;
int bufs;
int flags;
int err;
unsigned int blocknr;
ktime_t start_time;
u64 commit_time;
char *tagp = NULL;
journal_header_t *header;
journal_block_tag_t *tag = NULL;
int space_left = 0;
int first_tag = 0;
int tag_flag;
int i;
struct blk_plug plug;
/*
* First job: lock down the current transaction and wait for
* all outstanding updates to complete.
*/
/* Do we need to erase the effects of a prior journal_flush? */
if (journal->j_flags & JFS_FLUSHED) {
jbd_debug(3, "super block updated\n");
journal_update_superblock(journal, 1);
} else {
jbd_debug(3, "superblock not updated\n");
}
J_ASSERT(journal->j_running_transaction != NULL);
J_ASSERT(journal->j_committing_transaction == NULL);
commit_transaction = journal->j_running_transaction;
J_ASSERT(commit_transaction->t_state == T_RUNNING);
trace_jbd_start_commit(journal, commit_transaction);
jbd_debug(1, "JBD: starting commit of transaction %d\n",
commit_transaction->t_tid);
spin_lock(&journal->j_state_lock);
commit_transaction->t_state = T_LOCKED;
trace_jbd_commit_locking(journal, commit_transaction);
spin_lock(&commit_transaction->t_handle_lock);
while (commit_transaction->t_updates) {
DEFINE_WAIT(wait);
prepare_to_wait(&journal->j_wait_updates, &wait,
TASK_UNINTERRUPTIBLE);
if (commit_transaction->t_updates) {
spin_unlock(&commit_transaction->t_handle_lock);
spin_unlock(&journal->j_state_lock);
schedule();
spin_lock(&journal->j_state_lock);
spin_lock(&commit_transaction->t_handle_lock);
}
finish_wait(&journal->j_wait_updates, &wait);
}
spin_unlock(&commit_transaction->t_handle_lock);
J_ASSERT (commit_transaction->t_outstanding_credits <=
journal->j_max_transaction_buffers);
/*
* First thing we are allowed to do is to discard any remaining
* BJ_Reserved buffers. Note, it is _not_ permissible to assume
* that there are no such buffers: if a large filesystem
* operation like a truncate needs to split itself over multiple
* transactions, then it may try to do a journal_restart() while
* there are still BJ_Reserved buffers outstanding. These must
* be released cleanly from the current transaction.
*
* In this case, the filesystem must still reserve write access
* again before modifying the buffer in the new transaction, but
* we do not require it to remember exactly which old buffers it
* has reserved. This is consistent with the existing behaviour
* that multiple journal_get_write_access() calls to the same
* buffer are perfectly permissible.
*/
while (commit_transaction->t_reserved_list) {
jh = commit_transaction->t_reserved_list;
JBUFFER_TRACE(jh, "reserved, unused: refile");
/*
* A journal_get_undo_access()+journal_release_buffer() may
* leave undo-committed data.
*/
if (jh->b_committed_data) {
struct buffer_head *bh = jh2bh(jh);
jbd_lock_bh_state(bh);
jbd_free(jh->b_committed_data, bh->b_size);
jh->b_committed_data = NULL;
jbd_unlock_bh_state(bh);
}
journal_refile_buffer(journal, jh);
}
/*
* Now try to drop any written-back buffers from the journal's
* checkpoint lists. We do this *before* commit because it potentially
* frees some memory
*/
spin_lock(&journal->j_list_lock);
__journal_clean_checkpoint_list(journal);
spin_unlock(&journal->j_list_lock);
jbd_debug (3, "JBD: commit phase 1\n");
/*
* Clear revoked flag to reflect there is no revoked buffers
* in the next transaction which is going to be started.
*/
journal_clear_buffer_revoked_flags(journal);
/*
* Switch to a new revoke table.
*/
journal_switch_revoke_table(journal);
trace_jbd_commit_flushing(journal, commit_transaction);
commit_transaction->t_state = T_FLUSH;
journal->j_committing_transaction = commit_transaction;
journal->j_running_transaction = NULL;
start_time = ktime_get();
commit_transaction->t_log_start = journal->j_head;
wake_up(&journal->j_wait_transaction_locked);
spin_unlock(&journal->j_state_lock);
jbd_debug (3, "JBD: commit phase 2\n");
/*
* Now start flushing things to disk, in the order they appear
* on the transaction lists. Data blocks go first.
*/
blk_start_plug(&plug);
err = journal_submit_data_buffers(journal, commit_transaction,
WRITE_SYNC);
blk_finish_plug(&plug);
/*
* Wait for all previously submitted IO to complete.
*/
spin_lock(&journal->j_list_lock);
while (commit_transaction->t_locked_list) {
struct buffer_head *bh;
jh = commit_transaction->t_locked_list->b_tprev;
bh = jh2bh(jh);
get_bh(bh);
if (buffer_locked(bh)) {
spin_unlock(&journal->j_list_lock);
wait_on_buffer(bh);
spin_lock(&journal->j_list_lock);
}
if (unlikely(!buffer_uptodate(bh))) {
if (!trylock_page(bh->b_page)) {
spin_unlock(&journal->j_list_lock);
lock_page(bh->b_page);
spin_lock(&journal->j_list_lock);
}
if (bh->b_page->mapping)
set_bit(AS_EIO, &bh->b_page->mapping->flags);
unlock_page(bh->b_page);
SetPageError(bh->b_page);
err = -EIO;
}
if (!inverted_lock(journal, bh)) {
put_bh(bh);
spin_lock(&journal->j_list_lock);
continue;
}
if (buffer_jbd(bh) && bh2jh(bh) == jh &&
jh->b_transaction == commit_transaction &&
jh->b_jlist == BJ_Locked)
__journal_unfile_buffer(jh);
jbd_unlock_bh_state(bh);
release_data_buffer(bh);
cond_resched_lock(&journal->j_list_lock);
}
spin_unlock(&journal->j_list_lock);
if (err) {
char b[BDEVNAME_SIZE];
printk(KERN_WARNING
"JBD: Detected IO errors while flushing file data "
"on %s\n", bdevname(journal->j_fs_dev, b));
if (journal->j_flags & JFS_ABORT_ON_SYNCDATA_ERR)
journal_abort(journal, err);
err = 0;
}
blk_start_plug(&plug);
journal_write_revoke_records(journal, commit_transaction, WRITE_SYNC);
/*
* If we found any dirty or locked buffers, then we should have
* looped back up to the write_out_data label. If there weren't
* any then journal_clean_data_list should have wiped the list
* clean by now, so check that it is in fact empty.
*/
J_ASSERT (commit_transaction->t_sync_datalist == NULL);
jbd_debug (3, "JBD: commit phase 3\n");
/*
* Way to go: we have now written out all of the data for a
* transaction! Now comes the tricky part: we need to write out
* metadata. Loop over the transaction's entire buffer list:
*/
spin_lock(&journal->j_state_lock);
commit_transaction->t_state = T_COMMIT;
spin_unlock(&journal->j_state_lock);
trace_jbd_commit_logging(journal, commit_transaction);
J_ASSERT(commit_transaction->t_nr_buffers <=
commit_transaction->t_outstanding_credits);
descriptor = NULL;
bufs = 0;
while (commit_transaction->t_buffers) {
/* Find the next buffer to be journaled... */
jh = commit_transaction->t_buffers;
/* If we're in abort mode, we just un-journal the buffer and
release it. */
if (is_journal_aborted(journal)) {
clear_buffer_jbddirty(jh2bh(jh));
JBUFFER_TRACE(jh, "journal is aborting: refile");
journal_refile_buffer(journal, jh);
/* If that was the last one, we need to clean up
* any descriptor buffers which may have been
* already allocated, even if we are now
* aborting. */
if (!commit_transaction->t_buffers)
goto start_journal_io;
continue;
}
/* Make sure we have a descriptor block in which to
record the metadata buffer. */
if (!descriptor) {
struct buffer_head *bh;
J_ASSERT (bufs == 0);
jbd_debug(4, "JBD: get descriptor\n");
descriptor = journal_get_descriptor_buffer(journal);
if (!descriptor) {
journal_abort(journal, -EIO);
continue;
}
bh = jh2bh(descriptor);
jbd_debug(4, "JBD: got buffer %llu (%p)\n",
(unsigned long long)bh->b_blocknr, bh->b_data);
header = (journal_header_t *)&bh->b_data[0];
header->h_magic = cpu_to_be32(JFS_MAGIC_NUMBER);
header->h_blocktype = cpu_to_be32(JFS_DESCRIPTOR_BLOCK);
header->h_sequence = cpu_to_be32(commit_transaction->t_tid);
tagp = &bh->b_data[sizeof(journal_header_t)];
space_left = bh->b_size - sizeof(journal_header_t);
first_tag = 1;
set_buffer_jwrite(bh);
set_buffer_dirty(bh);
wbuf[bufs++] = bh;
/* Record it so that we can wait for IO
completion later */
BUFFER_TRACE(bh, "ph3: file as descriptor");
journal_file_buffer(descriptor, commit_transaction,
BJ_LogCtl);
}
/* Where is the buffer to be written? */
err = journal_next_log_block(journal, &blocknr);
/* If the block mapping failed, just abandon the buffer
and repeat this loop: we'll fall into the
refile-on-abort condition above. */
if (err) {
journal_abort(journal, err);
continue;
}
/*
* start_this_handle() uses t_outstanding_credits to determine
* the free space in the log, but this counter is changed
* by journal_next_log_block() also.
*/
commit_transaction->t_outstanding_credits--;
/* Bump b_count to prevent truncate from stumbling over
the shadowed buffer! @@@ This can go if we ever get
rid of the BJ_IO/BJ_Shadow pairing of buffers. */
get_bh(jh2bh(jh));
/* Make a temporary IO buffer with which to write it out
(this will requeue both the metadata buffer and the
temporary IO buffer). new_bh goes on BJ_IO*/
set_buffer_jwrite(jh2bh(jh));
/*
* akpm: journal_write_metadata_buffer() sets
* new_bh->b_transaction to commit_transaction.
* We need to clean this up before we release new_bh
* (which is of type BJ_IO)
*/
JBUFFER_TRACE(jh, "ph3: write metadata");
flags = journal_write_metadata_buffer(commit_transaction,
jh, &new_jh, blocknr);
set_buffer_jwrite(jh2bh(new_jh));
wbuf[bufs++] = jh2bh(new_jh);
/* Record the new block's tag in the current descriptor
buffer */
tag_flag = 0;
if (flags & 1)
tag_flag |= JFS_FLAG_ESCAPE;
if (!first_tag)
tag_flag |= JFS_FLAG_SAME_UUID;
tag = (journal_block_tag_t *) tagp;
tag->t_blocknr = cpu_to_be32(jh2bh(jh)->b_blocknr);
tag->t_flags = cpu_to_be32(tag_flag);
tagp += sizeof(journal_block_tag_t);
space_left -= sizeof(journal_block_tag_t);
if (first_tag) {
memcpy (tagp, journal->j_uuid, 16);
tagp += 16;
space_left -= 16;
first_tag = 0;
}
/* If there's no more to do, or if the descriptor is full,
let the IO rip! */
if (bufs == journal->j_wbufsize ||
commit_transaction->t_buffers == NULL ||
space_left < sizeof(journal_block_tag_t) + 16) {
jbd_debug(4, "JBD: Submit %d IOs\n", bufs);
/* Write an end-of-descriptor marker before
submitting the IOs. "tag" still points to
the last tag we set up. */
tag->t_flags |= cpu_to_be32(JFS_FLAG_LAST_TAG);
start_journal_io:
for (i = 0; i < bufs; i++) {
struct buffer_head *bh = wbuf[i];
lock_buffer(bh);
clear_buffer_dirty(bh);
set_buffer_uptodate(bh);
bh->b_end_io = journal_end_buffer_io_sync;
submit_bh(WRITE_SYNC, bh);
}
cond_resched();
/* Force a new descriptor to be generated next
time round the loop. */
descriptor = NULL;
bufs = 0;
}
}
blk_finish_plug(&plug);
/* Lo and behold: we have just managed to send a transaction to
the log. Before we can commit it, wait for the IO so far to
complete. Control buffers being written are on the
transaction's t_log_list queue, and metadata buffers are on
the t_iobuf_list queue.
Wait for the buffers in reverse order. That way we are
less likely to be woken up until all IOs have completed, and
so we incur less scheduling load.
*/
jbd_debug(3, "JBD: commit phase 4\n");
/*
* akpm: these are BJ_IO, and j_list_lock is not needed.
* See __journal_try_to_free_buffer.
*/
wait_for_iobuf:
while (commit_transaction->t_iobuf_list != NULL) {
struct buffer_head *bh;
jh = commit_transaction->t_iobuf_list->b_tprev;
bh = jh2bh(jh);
if (buffer_locked(bh)) {
wait_on_buffer(bh);
goto wait_for_iobuf;
}
if (cond_resched())
goto wait_for_iobuf;
if (unlikely(!buffer_uptodate(bh)))
err = -EIO;
clear_buffer_jwrite(bh);
JBUFFER_TRACE(jh, "ph4: unfile after journal write");
journal_unfile_buffer(journal, jh);
/*
* ->t_iobuf_list should contain only dummy buffer_heads
* which were created by journal_write_metadata_buffer().
*/
BUFFER_TRACE(bh, "dumping temporary bh");
journal_put_journal_head(jh);
__brelse(bh);
J_ASSERT_BH(bh, atomic_read(&bh->b_count) == 0);
free_buffer_head(bh);
/* We also have to unlock and free the corresponding
shadowed buffer */
jh = commit_transaction->t_shadow_list->b_tprev;
bh = jh2bh(jh);
clear_buffer_jwrite(bh);
J_ASSERT_BH(bh, buffer_jbddirty(bh));
/* The metadata is now released for reuse, but we need
to remember it against this transaction so that when
we finally commit, we can do any checkpointing
required. */
JBUFFER_TRACE(jh, "file as BJ_Forget");
journal_file_buffer(jh, commit_transaction, BJ_Forget);
/*
* Wake up any transactions which were waiting for this
* IO to complete. The barrier must be here so that changes
* by journal_file_buffer() take effect before wake_up_bit()
* does the waitqueue check.
*/
smp_mb();
wake_up_bit(&bh->b_state, BH_Unshadow);
JBUFFER_TRACE(jh, "brelse shadowed buffer");
__brelse(bh);
}
J_ASSERT (commit_transaction->t_shadow_list == NULL);
jbd_debug(3, "JBD: commit phase 5\n");
/* Here we wait for the revoke record and descriptor record buffers */
wait_for_ctlbuf:
while (commit_transaction->t_log_list != NULL) {
struct buffer_head *bh;
jh = commit_transaction->t_log_list->b_tprev;
bh = jh2bh(jh);
if (buffer_locked(bh)) {
wait_on_buffer(bh);
goto wait_for_ctlbuf;
}
if (cond_resched())
goto wait_for_ctlbuf;
if (unlikely(!buffer_uptodate(bh)))
err = -EIO;
BUFFER_TRACE(bh, "ph5: control buffer writeout done: unfile");
clear_buffer_jwrite(bh);
journal_unfile_buffer(journal, jh);
journal_put_journal_head(jh);
__brelse(bh); /* One for getblk */
/* AKPM: bforget here */
}
if (err)
journal_abort(journal, err);
jbd_debug(3, "JBD: commit phase 6\n");
/* All metadata is written, now write commit record and do cleanup */
spin_lock(&journal->j_state_lock);
J_ASSERT(commit_transaction->t_state == T_COMMIT);
commit_transaction->t_state = T_COMMIT_RECORD;
spin_unlock(&journal->j_state_lock);
if (journal_write_commit_record(journal, commit_transaction))
err = -EIO;
if (err)
journal_abort(journal, err);
/* End of a transaction! Finally, we can do checkpoint
processing: any buffers committed as a result of this
transaction can be removed from any checkpoint list it was on
before. */
jbd_debug(3, "JBD: commit phase 7\n");
J_ASSERT(commit_transaction->t_sync_datalist == NULL);
J_ASSERT(commit_transaction->t_buffers == NULL);
J_ASSERT(commit_transaction->t_checkpoint_list == NULL);
J_ASSERT(commit_transaction->t_iobuf_list == NULL);
J_ASSERT(commit_transaction->t_shadow_list == NULL);
J_ASSERT(commit_transaction->t_log_list == NULL);
restart_loop:
/*
* As there are other places (journal_unmap_buffer()) adding buffers
* to this list we have to be careful and hold the j_list_lock.
*/
spin_lock(&journal->j_list_lock);
while (commit_transaction->t_forget) {
transaction_t *cp_transaction;
struct buffer_head *bh;
int try_to_free = 0;
jh = commit_transaction->t_forget;
spin_unlock(&journal->j_list_lock);
bh = jh2bh(jh);
/*
* Get a reference so that bh cannot be freed before we are
* done with it.
*/
get_bh(bh);
jbd_lock_bh_state(bh);
J_ASSERT_JH(jh, jh->b_transaction == commit_transaction ||
jh->b_transaction == journal->j_running_transaction);
/*
* If there is undo-protected committed data against
* this buffer, then we can remove it now. If it is a
* buffer needing such protection, the old frozen_data
* field now points to a committed version of the
* buffer, so rotate that field to the new committed
* data.
*
* Otherwise, we can just throw away the frozen data now.
*/
if (jh->b_committed_data) {
jbd_free(jh->b_committed_data, bh->b_size);
jh->b_committed_data = NULL;
if (jh->b_frozen_data) {
jh->b_committed_data = jh->b_frozen_data;
jh->b_frozen_data = NULL;
}
} else if (jh->b_frozen_data) {
jbd_free(jh->b_frozen_data, bh->b_size);
jh->b_frozen_data = NULL;
}
spin_lock(&journal->j_list_lock);
cp_transaction = jh->b_cp_transaction;
if (cp_transaction) {
JBUFFER_TRACE(jh, "remove from old cp transaction");
__journal_remove_checkpoint(jh);
}
/* Only re-checkpoint the buffer_head if it is marked
* dirty. If the buffer was added to the BJ_Forget list
* by journal_forget, it may no longer be dirty and
* there's no point in keeping a checkpoint record for
* it. */
/* A buffer which has been freed while still being
* journaled by a previous transaction may end up still
* being dirty here, but we want to avoid writing back
* that buffer in the future after the "add to orphan"
* operation been committed, That's not only a performance
* gain, it also stops aliasing problems if the buffer is
* left behind for writeback and gets reallocated for another
* use in a different page. */
if (buffer_freed(bh) && !jh->b_next_transaction) {
clear_buffer_freed(bh);
clear_buffer_jbddirty(bh);
}
if (buffer_jbddirty(bh)) {
JBUFFER_TRACE(jh, "add to new checkpointing trans");
__journal_insert_checkpoint(jh, commit_transaction);
if (is_journal_aborted(journal))
clear_buffer_jbddirty(bh);
} else {
J_ASSERT_BH(bh, !buffer_dirty(bh));
/*
* The buffer on BJ_Forget list and not jbddirty means
* it has been freed by this transaction and hence it
* could not have been reallocated until this
* transaction has committed. *BUT* it could be
* reallocated once we have written all the data to
* disk and before we process the buffer on BJ_Forget
* list.
*/
if (!jh->b_next_transaction)
try_to_free = 1;
}
JBUFFER_TRACE(jh, "refile or unfile freed buffer");
__journal_refile_buffer(jh);
jbd_unlock_bh_state(bh);
if (try_to_free)
release_buffer_page(bh);
else
__brelse(bh);
cond_resched_lock(&journal->j_list_lock);
}
spin_unlock(&journal->j_list_lock);
/*
* This is a bit sleazy. We use j_list_lock to protect transition
* of a transaction into T_FINISHED state and calling
* __journal_drop_transaction(). Otherwise we could race with
* other checkpointing code processing the transaction...
*/
spin_lock(&journal->j_state_lock);
spin_lock(&journal->j_list_lock);
/*
* Now recheck if some buffers did not get attached to the transaction
* while the lock was dropped...
*/
if (commit_transaction->t_forget) {
spin_unlock(&journal->j_list_lock);
spin_unlock(&journal->j_state_lock);
goto restart_loop;
}
/* Done with this transaction! */
jbd_debug(3, "JBD: commit phase 8\n");
J_ASSERT(commit_transaction->t_state == T_COMMIT_RECORD);
commit_transaction->t_state = T_FINISHED;
J_ASSERT(commit_transaction == journal->j_committing_transaction);
journal->j_commit_sequence = commit_transaction->t_tid;
journal->j_committing_transaction = NULL;
commit_time = ktime_to_ns(ktime_sub(ktime_get(), start_time));
/*
* weight the commit time higher than the average time so we don't
* react too strongly to vast changes in commit time
*/
if (likely(journal->j_average_commit_time))
journal->j_average_commit_time = (commit_time*3 +
journal->j_average_commit_time) / 4;
else
journal->j_average_commit_time = commit_time;
spin_unlock(&journal->j_state_lock);
if (commit_transaction->t_checkpoint_list == NULL &&
commit_transaction->t_checkpoint_io_list == NULL) {
__journal_drop_transaction(journal, commit_transaction);
} else {
if (journal->j_checkpoint_transactions == NULL) {
journal->j_checkpoint_transactions = commit_transaction;
commit_transaction->t_cpnext = commit_transaction;
commit_transaction->t_cpprev = commit_transaction;
} else {
commit_transaction->t_cpnext =
journal->j_checkpoint_transactions;
commit_transaction->t_cpprev =
commit_transaction->t_cpnext->t_cpprev;
commit_transaction->t_cpnext->t_cpprev =
commit_transaction;
commit_transaction->t_cpprev->t_cpnext =
commit_transaction;
}
}
spin_unlock(&journal->j_list_lock);
trace_jbd_end_commit(journal, commit_transaction);
jbd_debug(1, "JBD: commit %d complete, head %d\n",
journal->j_commit_sequence, journal->j_tail_sequence);
wake_up(&journal->j_wait_done_commit);
}
/*
* Garbage collector for unused keys.
*
* This is done in process context so that we don't have to disable interrupts
* all over the place. key_put() schedules this rather than trying to do the
* cleanup itself, which means key_put() doesn't have to sleep.
*/
static void key_garbage_collector(struct work_struct *work)
{
static LIST_HEAD(graveyard);
static u8 gc_state; /* Internal persistent state */
#define KEY_GC_REAP_AGAIN 0x01 /* - Need another cycle */
#define KEY_GC_REAPING_LINKS 0x02 /* - We need to reap links */
#define KEY_GC_SET_TIMER 0x04 /* - We need to restart the timer */
#define KEY_GC_REAPING_DEAD_1 0x10 /* - We need to mark dead keys */
#define KEY_GC_REAPING_DEAD_2 0x20 /* - We need to reap dead key links */
#define KEY_GC_REAPING_DEAD_3 0x40 /* - We need to reap dead keys */
#define KEY_GC_FOUND_DEAD_KEY 0x80 /* - We found at least one dead key */
struct rb_node *cursor;
struct key *key;
time_t new_timer, limit;
kenter("[%lx,%x]", key_gc_flags, gc_state);
limit = current_kernel_time().tv_sec;
if (limit > key_gc_delay)
limit -= key_gc_delay;
else
limit = key_gc_delay;
/* Work out what we're going to be doing in this pass */
gc_state &= KEY_GC_REAPING_DEAD_1 | KEY_GC_REAPING_DEAD_2;
gc_state <<= 1;
if (test_and_clear_bit(KEY_GC_KEY_EXPIRED, &key_gc_flags))
gc_state |= KEY_GC_REAPING_LINKS | KEY_GC_SET_TIMER;
if (test_and_clear_bit(KEY_GC_REAP_KEYTYPE, &key_gc_flags))
gc_state |= KEY_GC_REAPING_DEAD_1;
kdebug("new pass %x", gc_state);
new_timer = LONG_MAX;
/* As only this function is permitted to remove things from the key
* serial tree, if cursor is non-NULL then it will always point to a
* valid node in the tree - even if lock got dropped.
*/
spin_lock(&key_serial_lock);
cursor = rb_first(&key_serial_tree);
continue_scanning:
while (cursor) {
key = rb_entry(cursor, struct key, serial_node);
cursor = rb_next(cursor);
if (atomic_read(&key->usage) == 0)
goto found_unreferenced_key;
if (unlikely(gc_state & KEY_GC_REAPING_DEAD_1)) {
if (key->type == key_gc_dead_keytype) {
gc_state |= KEY_GC_FOUND_DEAD_KEY;
set_bit(KEY_FLAG_DEAD, &key->flags);
key->perm = 0;
goto skip_dead_key;
}
}
if (gc_state & KEY_GC_SET_TIMER) {
if (key->expiry > limit && key->expiry < new_timer) {
kdebug("will expire %x in %ld",
key_serial(key), key->expiry - limit);
new_timer = key->expiry;
}
}
if (unlikely(gc_state & KEY_GC_REAPING_DEAD_2))
if (key->type == key_gc_dead_keytype)
gc_state |= KEY_GC_FOUND_DEAD_KEY;
if ((gc_state & KEY_GC_REAPING_LINKS) ||
unlikely(gc_state & KEY_GC_REAPING_DEAD_2)) {
if (key->type == &key_type_keyring)
goto found_keyring;
}
if (unlikely(gc_state & KEY_GC_REAPING_DEAD_3))
if (key->type == key_gc_dead_keytype)
goto destroy_dead_key;
skip_dead_key:
if (spin_is_contended(&key_serial_lock) || need_resched())
goto contended;
}
contended:
spin_unlock(&key_serial_lock);
maybe_resched:
if (cursor) {
cond_resched();
spin_lock(&key_serial_lock);
goto continue_scanning;
}
/* We've completed the pass. Set the timer if we need to and queue a
* new cycle if necessary. We keep executing cycles until we find one
* where we didn't reap any keys.
*/
kdebug("pass complete");
if (gc_state & KEY_GC_SET_TIMER && new_timer != (time_t)LONG_MAX) {
new_timer += key_gc_delay;
key_schedule_gc(new_timer);
}
if (unlikely(gc_state & KEY_GC_REAPING_DEAD_2) ||
!list_empty(&graveyard)) {
/* Make sure that all pending keyring payload destructions are
* fulfilled and that people aren't now looking at dead or
* dying keys that they don't have a reference upon or a link
* to.
*/
kdebug("gc sync");
synchronize_rcu();
}
if (!list_empty(&graveyard)) {
kdebug("gc keys");
key_gc_unused_keys(&graveyard);
}
if (unlikely(gc_state & (KEY_GC_REAPING_DEAD_1 |
KEY_GC_REAPING_DEAD_2))) {
if (!(gc_state & KEY_GC_FOUND_DEAD_KEY)) {
/* No remaining dead keys: short circuit the remaining
* keytype reap cycles.
*/
kdebug("dead short");
gc_state &= ~(KEY_GC_REAPING_DEAD_1 | KEY_GC_REAPING_DEAD_2);
gc_state |= KEY_GC_REAPING_DEAD_3;
} else {
gc_state |= KEY_GC_REAP_AGAIN;
}
}
if (unlikely(gc_state & KEY_GC_REAPING_DEAD_3)) {
kdebug("dead wake");
smp_mb();
clear_bit(KEY_GC_REAPING_KEYTYPE, &key_gc_flags);
wake_up_bit(&key_gc_flags, KEY_GC_REAPING_KEYTYPE);
}
if (gc_state & KEY_GC_REAP_AGAIN)
schedule_work(&key_gc_work);
kleave(" [end %x]", gc_state);
return;
/* We found an unreferenced key - once we've removed it from the tree,
* we can safely drop the lock.
*/
found_unreferenced_key:
kdebug("unrefd key %d", key->serial);
rb_erase(&key->serial_node, &key_serial_tree);
spin_unlock(&key_serial_lock);
list_add_tail(&key->graveyard_link, &graveyard);
gc_state |= KEY_GC_REAP_AGAIN;
goto maybe_resched;
/* We found a keyring and we need to check the payload for links to
* dead or expired keys. We don't flag another reap immediately as we
* have to wait for the old payload to be destroyed by RCU before we
* can reap the keys to which it refers.
*/
found_keyring:
spin_unlock(&key_serial_lock);
kdebug("scan keyring %d", key->serial);
key_gc_keyring(key, limit);
goto maybe_resched;
/* We found a dead key that is still referenced. Reset its type and
* destroy its payload with its semaphore held.
*/
destroy_dead_key:
spin_unlock(&key_serial_lock);
kdebug("destroy key %d", key->serial);
down_write(&key->sem);
key->type = &key_type_dead;
if (key_gc_dead_keytype->destroy)
key_gc_dead_keytype->destroy(key);
memset(&key->payload, KEY_DESTROY, sizeof(key->payload));
up_write(&key->sem);
goto maybe_resched;
}
static int gdlm_mount(struct gfs2_sbd *sdp, const char *table)
{
struct lm_lockstruct *ls = &sdp->sd_lockstruct;
char cluster[GFS2_LOCKNAME_LEN];
const char *fsname;
uint32_t flags;
int error, ops_result;
/*
* initialize everything
*/
INIT_DELAYED_WORK(&sdp->sd_control_work, gfs2_control_func);
spin_lock_init(&ls->ls_recover_spin);
ls->ls_recover_flags = 0;
ls->ls_recover_mount = 0;
ls->ls_recover_start = 0;
ls->ls_recover_block = 0;
ls->ls_recover_size = 0;
ls->ls_recover_submit = NULL;
ls->ls_recover_result = NULL;
ls->ls_lvb_bits = NULL;
error = set_recover_size(sdp, NULL, 0);
if (error)
goto fail;
/*
* prepare dlm_new_lockspace args
*/
fsname = strchr(table, ':');
if (!fsname) {
fs_info(sdp, "no fsname found\n");
error = -EINVAL;
goto fail_free;
}
memset(cluster, 0, sizeof(cluster));
memcpy(cluster, table, strlen(table) - strlen(fsname));
fsname++;
flags = DLM_LSFL_FS | DLM_LSFL_NEWEXCL;
/*
* create/join lockspace
*/
error = dlm_new_lockspace(fsname, cluster, flags, GDLM_LVB_SIZE,
&gdlm_lockspace_ops, sdp, &ops_result,
&ls->ls_dlm);
if (error) {
fs_err(sdp, "dlm_new_lockspace error %d\n", error);
goto fail_free;
}
if (ops_result < 0) {
/*
* dlm does not support ops callbacks,
* old dlm_controld/gfs_controld are used, try without ops.
*/
fs_info(sdp, "dlm lockspace ops not used\n");
free_recover_size(ls);
set_bit(DFL_NO_DLM_OPS, &ls->ls_recover_flags);
return 0;
}
if (!test_bit(SDF_NOJOURNALID, &sdp->sd_flags)) {
fs_err(sdp, "dlm lockspace ops disallow jid preset\n");
error = -EINVAL;
goto fail_release;
}
/*
* control_mount() uses control_lock to determine first mounter,
* and for later mounts, waits for any recoveries to be cleared.
*/
error = control_mount(sdp);
if (error) {
fs_err(sdp, "mount control error %d\n", error);
goto fail_release;
}
ls->ls_first = !!test_bit(DFL_FIRST_MOUNT, &ls->ls_recover_flags);
clear_bit(SDF_NOJOURNALID, &sdp->sd_flags);
smp_mb__after_atomic();
wake_up_bit(&sdp->sd_flags, SDF_NOJOURNALID);
return 0;
fail_release:
dlm_release_lockspace(ls->ls_dlm, 2);
fail_free:
free_recover_size(ls);
fail:
return error;
}
static int
sid_to_id(struct cifs_sb_info *cifs_sb, struct cifs_sid *psid,
struct cifs_fattr *fattr, uint sidtype)
{
int rc;
unsigned long cid;
struct key *idkey;
const struct cred *saved_cred;
struct cifs_sid_id *psidid, *npsidid;
struct rb_root *cidtree;
spinlock_t *cidlock;
if (sidtype == SIDOWNER) {
cid = cifs_sb->mnt_uid;
cidlock = &siduidlock;
cidtree = &uidtree;
} else if (sidtype == SIDGROUP) {
cid = cifs_sb->mnt_gid;
cidlock = &sidgidlock;
cidtree = &gidtree;
} else
return -ENOENT;
spin_lock(cidlock);
psidid = id_rb_search(cidtree, psid);
if (!psidid) {
spin_unlock(cidlock);
npsidid = kzalloc(sizeof(struct cifs_sid_id), GFP_KERNEL);
if (!npsidid)
return -ENOMEM;
npsidid->sidstr = kmalloc(SIDLEN, GFP_KERNEL);
if (!npsidid->sidstr) {
kfree(npsidid);
return -ENOMEM;
}
spin_lock(cidlock);
psidid = id_rb_search(cidtree, psid);
if (psidid) {
++psidid->refcount;
spin_unlock(cidlock);
kfree(npsidid->sidstr);
kfree(npsidid);
} else {
psidid = npsidid;
id_rb_insert(cidtree, psid, &psidid,
sidtype == SIDOWNER ? "os:" : "gs:");
++psidid->refcount;
spin_unlock(cidlock);
}
} else {
++psidid->refcount;
spin_unlock(cidlock);
}
if (test_bit(SID_ID_MAPPED, &psidid->state)) {
cid = psidid->id;
psidid->time = jiffies;
goto sid_to_id_out;
}
if (time_after(psidid->time + SID_MAP_RETRY, jiffies))
goto sid_to_id_out;
if (!test_and_set_bit(SID_ID_PENDING, &psidid->state)) {
saved_cred = override_creds(root_cred);
idkey = request_key(&cifs_idmap_key_type, psidid->sidstr, "");
if (IS_ERR(idkey))
cFYI(1, "%s: Can't map SID to an id", __func__);
else {
cid = *(unsigned long *)idkey->payload.value;
psidid->id = cid;
set_bit(SID_ID_MAPPED, &psidid->state);
key_put(idkey);
kfree(psidid->sidstr);
}
revert_creds(saved_cred);
psidid->time = jiffies;
clear_bit(SID_ID_PENDING, &psidid->state);
wake_up_bit(&psidid->state, SID_ID_PENDING);
} else {
rc = wait_on_bit(&psidid->state, SID_ID_PENDING,
sidid_pending_wait, TASK_INTERRUPTIBLE);
if (rc) {
cFYI(1, "%s: sidid_pending_wait interrupted %d",
__func__, rc);
--psidid->refcount;
return rc;
}
if (test_bit(SID_ID_MAPPED, &psidid->state))
cid = psidid->id;
}
sid_to_id_out:
--psidid->refcount;
if (sidtype == SIDOWNER)
fattr->cf_uid = cid;
else
fattr->cf_gid = cid;
return 0;
}
