struct completion completion; /* completion for synchronized locking */
void (*bast)(void *arg, int mode); /* blocking AST function pointer*/
struct mddev *mddev; /* pointing back to mddev. */
+ int mode;
};
struct suspend_info {
dlm_lockspace_t *lockspace;
int slot_number;
struct completion completion;
- struct mutex sb_mutex;
struct dlm_lock_resource *bitmap_lockres;
struct dlm_lock_resource *resync_lockres;
struct list_head suspend_list;
};
struct cluster_msg {
- int type;
- int slot;
+ __le32 type;
+ __le32 slot;
/* TODO: Unionize this for smaller footprint */
- sector_t low;
- sector_t high;
+ __le64 low;
+ __le64 high;
char uuid[16];
- int raid_slot;
+ __le32 raid_slot;
};
static void sync_ast(void *arg)
{
struct dlm_lock_resource *res;
- res = (struct dlm_lock_resource *) arg;
+ res = arg;
complete(&res->completion);
}
if (ret)
return ret;
wait_for_completion(&res->completion);
+ if (res->lksb.sb_status == 0)
+ res->mode = mode;
return res->lksb.sb_status;
}
init_completion(&res->completion);
res->ls = cinfo->lockspace;
res->mddev = mddev;
+ res->mode = DLM_LOCK_IV;
namelen = strlen(name);
res->name = kzalloc(namelen + 1, GFP_KERNEL);
if (!res->name) {
kfree(res);
}
-static void add_resync_info(struct mddev *mddev, struct dlm_lock_resource *lockres,
- sector_t lo, sector_t hi)
+static void add_resync_info(struct dlm_lock_resource *lockres,
+ sector_t lo, sector_t hi)
{
struct resync_info *ri;
dlm_lock_sync(lockres, DLM_LOCK_CR);
memcpy(&ri, lockres->lksb.sb_lvbptr, sizeof(struct resync_info));
hi = le64_to_cpu(ri.hi);
- if (ri.hi > 0) {
+ if (hi > 0) {
s = kzalloc(sizeof(struct suspend_info), GFP_KERNEL);
if (!s)
goto out;
*/
static void ack_bast(void *arg, int mode)
{
- struct dlm_lock_resource *res = (struct dlm_lock_resource *)arg;
+ struct dlm_lock_resource *res = arg;
struct md_cluster_info *cinfo = res->mddev->cluster_info;
if (mode == DLM_LOCK_EX)
list_for_each_entry_safe(s, tmp, &cinfo->suspend_list, list)
if (slot == s->slot) {
- pr_info("%s:%d Deleting suspend_info: %d\n",
- __func__, __LINE__, slot);
list_del(&s->list);
kfree(s);
break;
len = snprintf(disk_uuid, 64, "DEVICE_UUID=");
sprintf(disk_uuid + len, "%pU", cmsg->uuid);
- snprintf(raid_slot, 16, "RAID_DISK=%d", cmsg->raid_slot);
+ snprintf(raid_slot, 16, "RAID_DISK=%d", le32_to_cpu(cmsg->raid_slot));
pr_info("%s:%d Sending kobject change with %s and %s\n", __func__, __LINE__, disk_uuid, raid_slot);
init_completion(&cinfo->newdisk_completion);
set_bit(MD_CLUSTER_WAITING_FOR_NEWDISK, &cinfo->state);
static void process_remove_disk(struct mddev *mddev, struct cluster_msg *msg)
{
- struct md_rdev *rdev = md_find_rdev_nr_rcu(mddev, msg->raid_slot);
+ struct md_rdev *rdev = md_find_rdev_nr_rcu(mddev,
+ le32_to_cpu(msg->raid_slot));
if (rdev)
md_kick_rdev_from_array(rdev);
else
- pr_warn("%s: %d Could not find disk(%d) to REMOVE\n", __func__, __LINE__, msg->raid_slot);
+ pr_warn("%s: %d Could not find disk(%d) to REMOVE\n",
+ __func__, __LINE__, le32_to_cpu(msg->raid_slot));
}
static void process_readd_disk(struct mddev *mddev, struct cluster_msg *msg)
{
- struct md_rdev *rdev = md_find_rdev_nr_rcu(mddev, msg->raid_slot);
+ struct md_rdev *rdev = md_find_rdev_nr_rcu(mddev,
+ le32_to_cpu(msg->raid_slot));
if (rdev && test_bit(Faulty, &rdev->flags))
clear_bit(Faulty, &rdev->flags);
else
- pr_warn("%s: %d Could not find disk(%d) which is faulty", __func__, __LINE__, msg->raid_slot);
+ pr_warn("%s: %d Could not find disk(%d) which is faulty",
+ __func__, __LINE__, le32_to_cpu(msg->raid_slot));
}
static void process_recvd_msg(struct mddev *mddev, struct cluster_msg *msg)
{
- switch (msg->type) {
+ if (WARN(mddev->cluster_info->slot_number - 1 == le32_to_cpu(msg->slot),
+ "node %d received it's own msg\n", le32_to_cpu(msg->slot)))
+ return;
+ switch (le32_to_cpu(msg->type)) {
case METADATA_UPDATED:
- pr_info("%s: %d Received message: METADATA_UPDATE from %d\n",
- __func__, __LINE__, msg->slot);
process_metadata_update(mddev, msg);
break;
case RESYNCING:
- pr_info("%s: %d Received message: RESYNCING from %d\n",
- __func__, __LINE__, msg->slot);
- process_suspend_info(mddev, msg->slot,
- msg->low, msg->high);
+ process_suspend_info(mddev, le32_to_cpu(msg->slot),
+ le64_to_cpu(msg->low),
+ le64_to_cpu(msg->high));
break;
case NEWDISK:
- pr_info("%s: %d Received message: NEWDISK from %d\n",
- __func__, __LINE__, msg->slot);
process_add_new_disk(mddev, msg);
break;
case REMOVE:
- pr_info("%s: %d Received REMOVE from %d\n",
- __func__, __LINE__, msg->slot);
process_remove_disk(mddev, msg);
break;
case RE_ADD:
- pr_info("%s: %d Received RE_ADD from %d\n",
- __func__, __LINE__, msg->slot);
process_readd_disk(mddev, msg);
break;
case BITMAP_NEEDS_SYNC:
- pr_info("%s: %d Received BITMAP_NEEDS_SYNC from %d\n",
- __func__, __LINE__, msg->slot);
- __recover_slot(mddev, msg->slot);
+ __recover_slot(mddev, le32_to_cpu(msg->slot));
break;
default:
pr_warn("%s:%d Received unknown message from %d\n",
/* lock_comm()
* Takes the lock on the TOKEN lock resource so no other
* node can communicate while the operation is underway.
+ * If called again, and the TOKEN lock is alread in EX mode
+ * return success. However, care must be taken that unlock_comm()
+ * is called only once.
*/
static int lock_comm(struct md_cluster_info *cinfo)
{
int error;
+ if (cinfo->token_lockres->mode == DLM_LOCK_EX)
+ return 0;
+
error = dlm_lock_sync(cinfo->token_lockres, DLM_LOCK_EX);
if (error)
pr_err("md-cluster(%s:%d): failed to get EX on TOKEN (%d)\n",
static void unlock_comm(struct md_cluster_info *cinfo)
{
+ WARN_ON(cinfo->token_lockres->mode != DLM_LOCK_EX);
dlm_unlock_sync(cinfo->token_lockres);
}
init_completion(&cinfo->completion);
set_bit(MD_CLUSTER_BEGIN_JOIN_CLUSTER, &cinfo->state);
- mutex_init(&cinfo->sb_mutex);
mddev->cluster_info = cinfo;
memset(str, 0, 64);
struct cluster_msg cmsg;
struct md_rdev *rdev;
int ret = 0;
+ int raid_slot = -1;
memset(&cmsg, 0, sizeof(cmsg));
cmsg.type = cpu_to_le32(METADATA_UPDATED);
- cmsg.raid_slot = -1;
/* Pick up a good active device number to send.
*/
rdev_for_each(rdev, mddev)
if (rdev->raid_disk > -1 && !test_bit(Faulty, &rdev->flags)) {
- cmsg.raid_slot = cpu_to_le32(rdev->desc_nr);
+ raid_slot = rdev->desc_nr;
break;
}
- if (cmsg.raid_slot >= 0)
+ if (raid_slot >= 0) {
+ cmsg.raid_slot = cpu_to_le32(raid_slot);
ret = __sendmsg(cinfo, &cmsg);
- else
+ } else
pr_warn("md-cluster: No good device id found to send\n");
unlock_comm(cinfo);
return ret;
}
-static int metadata_update_cancel(struct mddev *mddev)
+static void metadata_update_cancel(struct mddev *mddev)
{
struct md_cluster_info *cinfo = mddev->cluster_info;
-
- return dlm_unlock_sync(cinfo->token_lockres);
+ unlock_comm(cinfo);
}
static int resync_start(struct mddev *mddev)
static int resync_info_update(struct mddev *mddev, sector_t lo, sector_t hi)
{
struct md_cluster_info *cinfo = mddev->cluster_info;
- struct cluster_msg cmsg;
- int slot = cinfo->slot_number - 1;
+ struct cluster_msg cmsg = {0};
- add_resync_info(mddev, cinfo->bitmap_lockres, lo, hi);
+ add_resync_info(cinfo->bitmap_lockres, lo, hi);
/* Re-acquire the lock to refresh LVB */
dlm_lock_sync(cinfo->bitmap_lockres, DLM_LOCK_PW);
cmsg.type = cpu_to_le32(RESYNCING);
- cmsg.slot = cpu_to_le32(slot);
cmsg.low = cpu_to_le64(lo);
cmsg.high = cpu_to_le64(hi);
return ret;
}
-static int add_new_disk_start(struct mddev *mddev, struct md_rdev *rdev)
+/* add_new_disk() - initiates a disk add
+ * However, if this fails before writing md_update_sb(),
+ * add_new_disk_cancel() must be called to release token lock
+ */
+static int add_new_disk(struct mddev *mddev, struct md_rdev *rdev)
{
struct md_cluster_info *cinfo = mddev->cluster_info;
struct cluster_msg cmsg;
memset(&cmsg, 0, sizeof(cmsg));
cmsg.type = cpu_to_le32(NEWDISK);
memcpy(cmsg.uuid, uuid, 16);
- cmsg.raid_slot = rdev->desc_nr;
+ cmsg.raid_slot = cpu_to_le32(rdev->desc_nr);
lock_comm(cinfo);
ret = __sendmsg(cinfo, &cmsg);
if (ret)
/* Some node does not "see" the device */
if (ret == -EAGAIN)
ret = -ENOENT;
+ if (ret)
+ unlock_comm(cinfo);
else
dlm_lock_sync(cinfo->no_new_dev_lockres, DLM_LOCK_CR);
return ret;
}
-static int add_new_disk_finish(struct mddev *mddev)
+static void add_new_disk_cancel(struct mddev *mddev)
{
- /* Write sb and inform others */
- md_update_sb(mddev, 1);
- return metadata_update_finish(mddev);
+ struct md_cluster_info *cinfo = mddev->cluster_info;
+ unlock_comm(cinfo);
}
static int new_disk_ack(struct mddev *mddev, bool ack)
static int remove_disk(struct mddev *mddev, struct md_rdev *rdev)
{
- struct cluster_msg cmsg;
+ struct cluster_msg cmsg = {0};
struct md_cluster_info *cinfo = mddev->cluster_info;
- cmsg.type = REMOVE;
- cmsg.raid_slot = rdev->desc_nr;
+ cmsg.type = cpu_to_le32(REMOVE);
+ cmsg.raid_slot = cpu_to_le32(rdev->desc_nr);
return __sendmsg(cinfo, &cmsg);
}
{
int sn, err;
sector_t lo, hi;
- struct cluster_msg cmsg;
+ struct cluster_msg cmsg = {0};
struct mddev *mddev = rdev->mddev;
struct md_cluster_info *cinfo = mddev->cluster_info;
- cmsg.type = RE_ADD;
- cmsg.raid_slot = rdev->desc_nr;
+ cmsg.type = cpu_to_le32(RE_ADD);
+ cmsg.raid_slot = cpu_to_le32(rdev->desc_nr);
err = sendmsg(cinfo, &cmsg);
if (err)
goto out;
.metadata_update_finish = metadata_update_finish,
.metadata_update_cancel = metadata_update_cancel,
.area_resyncing = area_resyncing,
- .add_new_disk_start = add_new_disk_start,
- .add_new_disk_finish = add_new_disk_finish,
+ .add_new_disk = add_new_disk,
+ .add_new_disk_cancel = add_new_disk_cancel,
.new_disk_ack = new_disk_ack,
.remove_disk = remove_disk,
.gather_bitmaps = gather_bitmaps,
module_init(cluster_init);
module_exit(cluster_exit);
+MODULE_AUTHOR("SUSE");
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("Clustering support for MD");
projects / firefly-linux-kernel-4.4.55.git / blobdiff