put_net_conf(mdev);
}
+ /* The helper may take some time.
+ * write out any unsynced meta data changes now */
+ drbd_md_sync(mdev);
+
dev_info(DEV, "helper command: %s %s %s\n", usermode_helper, cmd, mb);
drbd_bcast_ev_helper(mdev, cmd);
put_ldev(mdev);
} else {
dev_warn(DEV, "Not fencing peer, I'm not even Consistent myself.\n");
- return mdev->state.pdsk;
+ nps = mdev->state.pdsk;
+ goto out;
}
r = drbd_khelper(mdev, "fence-peer");
dev_info(DEV, "fence-peer helper returned %d (%s)\n",
(r>>8) & 0xff, ex_to_string);
+
+out:
+ if (mdev->state.susp_fen && nps >= D_UNKNOWN) {
+ /* The handler was not successful... unfreeze here, the
+ state engine can not unfreeze... */
+ _drbd_request_state(mdev, NS(susp_fen, 0), CS_VERBOSE);
+ }
+
return nps;
}
return r;
}
+static struct drbd_conf *ensure_mdev(int minor, int create)
+{
+ struct drbd_conf *mdev;
+
+ if (minor >= minor_count)
+ return NULL;
+
+ mdev = minor_to_mdev(minor);
+
+ if (!mdev && create) {
+ struct gendisk *disk = NULL;
+ mdev = drbd_new_device(minor);
+
+ spin_lock_irq(&drbd_pp_lock);
+ if (minor_table[minor] == NULL) {
+ minor_table[minor] = mdev;
+ disk = mdev->vdisk;
+ mdev = NULL;
+ } /* else: we lost the race */
+ spin_unlock_irq(&drbd_pp_lock);
+
+ if (disk) /* we won the race above */
+ /* in case we ever add a drbd_delete_device(),
+ * don't forget the del_gendisk! */
+ add_disk(disk);
+ else /* we lost the race above */
+ drbd_free_mdev(mdev);
+
+ mdev = minor_to_mdev(minor);
+ }
+
+ return mdev;
+}
static int drbd_nl_primary(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp,
struct drbd_nl_cfg_reply *reply)
void drbd_suspend_io(struct drbd_conf *mdev)
{
set_bit(SUSPEND_IO, &mdev->flags);
- if (mdev->state.susp)
+ if (is_susp(mdev->state))
return;
wait_event(mdev->misc_wait, !atomic_read(&mdev->ap_bio_cnt));
}
blk_queue_segment_boundary(q, PAGE_SIZE-1);
blk_stack_limits(&q->limits, &b->limits, 0);
- if (b->merge_bvec_fn)
- dev_warn(DEV, "Backing device's merge_bvec_fn() = %p\n",
- b->merge_bvec_fn);
dev_info(DEV, "max_segment_size ( = BIO size ) = %u\n", queue_max_segment_size(q));
if (q->backing_dev_info.ra_pages != b->backing_dev_info.ra_pages) {
/* serialize deconfig (worker exiting, doing cleanup)
* and reconfig (drbdsetup disk, drbdsetup net)
*
- * wait for a potentially exiting worker, then restart it,
- * or start a new one.
+ * Wait for a potentially exiting worker, then restart it,
+ * or start a new one. Flush any pending work, there may still be an
+ * after_state_change queued.
*/
static void drbd_reconfig_start(struct drbd_conf *mdev)
{
wait_event(mdev->state_wait, !test_and_set_bit(CONFIG_PENDING, &mdev->flags));
wait_event(mdev->state_wait, !test_bit(DEVICE_DYING, &mdev->flags));
drbd_thread_start(&mdev->worker);
+ drbd_flush_workqueue(mdev);
}
/* if still unconfigured, stops worker again.
wake_up(&mdev->state_wait);
}
+/* Make sure IO is suspended before calling this function(). */
+static void drbd_suspend_al(struct drbd_conf *mdev)
+{
+ int s = 0;
+
+ if (lc_try_lock(mdev->act_log)) {
+ drbd_al_shrink(mdev);
+ lc_unlock(mdev->act_log);
+ } else {
+ dev_warn(DEV, "Failed to lock al in drbd_suspend_al()\n");
+ return;
+ }
+
+ spin_lock_irq(&mdev->req_lock);
+ if (mdev->state.conn < C_CONNECTED)
+ s = !test_and_set_bit(AL_SUSPENDED, &mdev->flags);
+
+ spin_unlock_irq(&mdev->req_lock);
+
+ if (s)
+ dev_info(DEV, "Suspended AL updates\n");
+}
+
/* does always return 0;
* interesting return code is in reply->ret_code */
static int drbd_nl_disk_conf(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp,
struct inode *inode, *inode2;
struct lru_cache *resync_lru = NULL;
union drbd_state ns, os;
+ unsigned int max_seg_s;
int rv;
int cp_discovered = 0;
int logical_block_size;
retcode = ERR_DISK_CONFIGURED;
goto fail;
}
+ /* It may just now have detached because of IO error. Make sure
+ * drbd_ldev_destroy is done already, we may end up here very fast,
+ * e.g. if someone calls attach from the on-io-error handler,
+ * to realize a "hot spare" feature (not that I'd recommend that) */
+ wait_event(mdev->misc_wait, !atomic_read(&mdev->local_cnt));
/* allocation not in the IO path, cqueue thread context */
nbc = kzalloc(sizeof(struct drbd_backing_dev), GFP_KERNEL);
drbd_suspend_io(mdev);
/* also wait for the last barrier ack. */
- wait_event(mdev->misc_wait, !atomic_read(&mdev->ap_pending_cnt) || mdev->state.susp);
+ wait_event(mdev->misc_wait, !atomic_read(&mdev->ap_pending_cnt) || is_susp(mdev->state));
/* and for any other previously queued work */
drbd_flush_workqueue(mdev);
clear_bit(CRASHED_PRIMARY, &mdev->flags);
if (drbd_md_test_flag(mdev->ldev, MDF_PRIMARY_IND) &&
- !(mdev->state.role == R_PRIMARY && mdev->state.susp &&
- mdev->sync_conf.on_no_data == OND_SUSPEND_IO)) {
+ !(mdev->state.role == R_PRIMARY && mdev->state.susp_nod)) {
set_bit(CRASHED_PRIMARY, &mdev->flags);
cp_discovered = 1;
}
mdev->read_cnt = 0;
mdev->writ_cnt = 0;
- drbd_setup_queue_param(mdev, DRBD_MAX_SEGMENT_SIZE);
+ max_seg_s = DRBD_MAX_SEGMENT_SIZE;
+ if (mdev->state.conn == C_CONNECTED) {
+ /* We are Primary, Connected, and now attach a new local
+ * backing store. We must not increase the user visible maximum
+ * bio size on this device to something the peer may not be
+ * able to handle. */
+ if (mdev->agreed_pro_version < 94)
+ max_seg_s = queue_max_segment_size(mdev->rq_queue);
+ else if (mdev->agreed_pro_version == 94)
+ max_seg_s = DRBD_MAX_SIZE_H80_PACKET;
+ /* else: drbd 8.3.9 and later, stay with default */
+ }
+
+ drbd_setup_queue_param(mdev, max_seg_s);
/* If I am currently not R_PRIMARY,
* but meta data primary indicator is set,
drbd_al_to_on_disk_bm(mdev);
}
+ if (_drbd_bm_total_weight(mdev) == drbd_bm_bits(mdev))
+ drbd_suspend_al(mdev); /* IO is still suspended here... */
+
spin_lock_irq(&mdev->req_lock);
os = mdev->state;
ns.i = os.i;
force_diskless_dec:
put_ldev(mdev);
force_diskless:
- drbd_force_state(mdev, NS(disk, D_DISKLESS));
+ drbd_force_state(mdev, NS(disk, D_FAILED));
drbd_md_sync(mdev);
release_bdev2_fail:
if (nbc)
return 0;
}
+/* Detaching the disk is a process in multiple stages. First we need to lock
+ * out application IO, in-flight IO, IO stuck in drbd_al_begin_io.
+ * Then we transition to D_DISKLESS, and wait for put_ldev() to return all
+ * internal references as well.
+ * Only then we have finally detached. */
static int drbd_nl_detach(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp,
struct drbd_nl_cfg_reply *reply)
{
+ drbd_suspend_io(mdev); /* so no-one is stuck in drbd_al_begin_io */
reply->ret_code = drbd_request_state(mdev, NS(disk, D_DISKLESS));
+ if (mdev->state.disk == D_DISKLESS)
+ wait_event(mdev->misc_wait, !atomic_read(&mdev->local_cnt));
+ drbd_resume_io(mdev);
return 0;
}
}
#undef AL_MAX
+ /* to avoid spurious errors when configuring minors before configuring
+ * the minors they depend on: if necessary, first create the minor we
+ * depend on */
+ if (sc.after >= 0)
+ ensure_mdev(sc.after, 1);
+
/* most sanity checks done, try to assign the new sync-after
* dependency. need to hold the global lock in there,
* to avoid a race in the dependency loop check. */
return 0;
}
+static int drbd_bmio_set_susp_al(struct drbd_conf *mdev)
+{
+ int rv;
+
+ rv = drbd_bmio_set_n_write(mdev);
+ drbd_suspend_al(mdev);
+ return rv;
+}
+
static int drbd_nl_invalidate_peer(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp,
struct drbd_nl_cfg_reply *reply)
{
+ int retcode;
- reply->ret_code = drbd_request_state(mdev, NS(conn, C_STARTING_SYNC_S));
+ retcode = _drbd_request_state(mdev, NS(conn, C_STARTING_SYNC_S), CS_ORDERED);
+
+ if (retcode < SS_SUCCESS) {
+ if (retcode == SS_NEED_CONNECTION && mdev->state.role == R_PRIMARY) {
+ /* The peer will get a resync upon connect anyways. Just make that
+ into a full resync. */
+ retcode = drbd_request_state(mdev, NS(pdsk, D_INCONSISTENT));
+ if (retcode >= SS_SUCCESS) {
+ /* open coded drbd_bitmap_io() */
+ if (drbd_bitmap_io(mdev, &drbd_bmio_set_susp_al,
+ "set_n_write from invalidate_peer"))
+ retcode = ERR_IO_MD_DISK;
+ }
+ } else
+ retcode = drbd_request_state(mdev, NS(conn, C_STARTING_SYNC_S));
+ }
+ reply->ret_code = retcode;
return 0;
}
if (test_bit(NEW_CUR_UUID, &mdev->flags)) {
drbd_uuid_new_current(mdev);
clear_bit(NEW_CUR_UUID, &mdev->flags);
- drbd_md_sync(mdev);
}
drbd_suspend_io(mdev);
- reply->ret_code = drbd_request_state(mdev, NS(susp, 0));
+ reply->ret_code = drbd_request_state(mdev, NS3(susp, 0, susp_nod, 0, susp_fen, 0));
if (reply->ret_code == SS_SUCCESS) {
if (mdev->state.conn < C_CONNECTED)
tl_clear(mdev);
return 0;
}
-static struct drbd_conf *ensure_mdev(struct drbd_nl_cfg_req *nlp)
-{
- struct drbd_conf *mdev;
-
- if (nlp->drbd_minor >= minor_count)
- return NULL;
-
- mdev = minor_to_mdev(nlp->drbd_minor);
-
- if (!mdev && (nlp->flags & DRBD_NL_CREATE_DEVICE)) {
- struct gendisk *disk = NULL;
- mdev = drbd_new_device(nlp->drbd_minor);
-
- spin_lock_irq(&drbd_pp_lock);
- if (minor_table[nlp->drbd_minor] == NULL) {
- minor_table[nlp->drbd_minor] = mdev;
- disk = mdev->vdisk;
- mdev = NULL;
- } /* else: we lost the race */
- spin_unlock_irq(&drbd_pp_lock);
-
- if (disk) /* we won the race above */
- /* in case we ever add a drbd_delete_device(),
- * don't forget the del_gendisk! */
- add_disk(disk);
- else /* we lost the race above */
- drbd_free_mdev(mdev);
-
- mdev = minor_to_mdev(nlp->drbd_minor);
- }
-
- return mdev;
-}
-
struct cn_handler_struct {
int (*function)(struct drbd_conf *,
struct drbd_nl_cfg_req *,
goto fail;
}
- mdev = ensure_mdev(nlp);
+ mdev = ensure_mdev(nlp->drbd_minor,
+ (nlp->flags & DRBD_NL_CREATE_DEVICE));
if (!mdev) {
retcode = ERR_MINOR_INVALID;
goto fail;
projects / deliverable / linux.git / blobdiff