#include <linux/module.h>
#include <linux/dlm.h>
#include <linux/sched.h>
+#include <linux/raid/md_p.h>
#include "md.h"
#include "bitmap.h"
#include "md-cluster.h"
#define LVB_SIZE 64
+#define NEW_DEV_TIMEOUT 5000
struct dlm_lock_resource {
dlm_lockspace_t *ls;
__le64 hi;
};
+/* md_cluster_info flags */
+#define MD_CLUSTER_WAITING_FOR_NEWDISK 1
+
+
struct md_cluster_info {
/* dlm lock space and resources for clustered raid. */
dlm_lockspace_t *lockspace;
spinlock_t suspend_lock;
struct md_thread *recovery_thread;
unsigned long recovery_map;
+ /* communication loc resources */
+ struct dlm_lock_resource *ack_lockres;
+ struct dlm_lock_resource *message_lockres;
+ struct dlm_lock_resource *token_lockres;
+ struct dlm_lock_resource *no_new_dev_lockres;
+ struct md_thread *recv_thread;
+ struct completion newdisk_completion;
+ unsigned long state;
+};
+
+enum msg_type {
+ METADATA_UPDATED = 0,
+ RESYNCING,
+ NEWDISK,
+ REMOVE,
+ RE_ADD,
+};
+
+struct cluster_msg {
+ int type;
+ int slot;
+ /* TODO: Unionize this for smaller footprint */
+ sector_t low;
+ sector_t high;
+ char uuid[16];
+ int raid_slot;
};
static void sync_ast(void *arg)
return s;
}
-void recover_bitmaps(struct md_thread *thread)
+static void recover_bitmaps(struct md_thread *thread)
{
struct mddev *mddev = thread->mddev;
struct md_cluster_info *cinfo = mddev->cluster_info;
str, ret);
goto clear_bit;
}
- ret = bitmap_copy_from_slot(mddev, slot, &lo, &hi);
+ ret = bitmap_copy_from_slot(mddev, slot, &lo, &hi, true);
if (ret) {
pr_err("md-cluster: Could not copy data from bitmap %d\n", slot);
goto dlm_unlock;
.recover_done = recover_done,
};
+/*
+ * The BAST function for the ack lock resource
+ * This function wakes up the receive thread in
+ * order to receive and process the message.
+ */
+static void ack_bast(void *arg, int mode)
+{
+ struct dlm_lock_resource *res = (struct dlm_lock_resource *)arg;
+ struct md_cluster_info *cinfo = res->mddev->cluster_info;
+
+ if (mode == DLM_LOCK_EX)
+ md_wakeup_thread(cinfo->recv_thread);
+}
+
+static void __remove_suspend_info(struct md_cluster_info *cinfo, int slot)
+{
+ struct suspend_info *s, *tmp;
+
+ 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;
+ }
+}
+
+static void remove_suspend_info(struct md_cluster_info *cinfo, int slot)
+{
+ spin_lock_irq(&cinfo->suspend_lock);
+ __remove_suspend_info(cinfo, slot);
+ spin_unlock_irq(&cinfo->suspend_lock);
+}
+
+
+static void process_suspend_info(struct md_cluster_info *cinfo,
+ int slot, sector_t lo, sector_t hi)
+{
+ struct suspend_info *s;
+
+ if (!hi) {
+ remove_suspend_info(cinfo, slot);
+ return;
+ }
+ s = kzalloc(sizeof(struct suspend_info), GFP_KERNEL);
+ if (!s)
+ return;
+ s->slot = slot;
+ s->lo = lo;
+ s->hi = hi;
+ spin_lock_irq(&cinfo->suspend_lock);
+ /* Remove existing entry (if exists) before adding */
+ __remove_suspend_info(cinfo, slot);
+ list_add(&s->list, &cinfo->suspend_list);
+ spin_unlock_irq(&cinfo->suspend_lock);
+}
+
+static void process_add_new_disk(struct mddev *mddev, struct cluster_msg *cmsg)
+{
+ char disk_uuid[64];
+ struct md_cluster_info *cinfo = mddev->cluster_info;
+ char event_name[] = "EVENT=ADD_DEVICE";
+ char raid_slot[16];
+ char *envp[] = {event_name, disk_uuid, raid_slot, NULL};
+ int len;
+
+ len = snprintf(disk_uuid, 64, "DEVICE_UUID=");
+ pretty_uuid(disk_uuid + len, cmsg->uuid);
+ snprintf(raid_slot, 16, "RAID_DISK=%d", 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);
+ kobject_uevent_env(&disk_to_dev(mddev->gendisk)->kobj, KOBJ_CHANGE, envp);
+ wait_for_completion_timeout(&cinfo->newdisk_completion,
+ NEW_DEV_TIMEOUT);
+ clear_bit(MD_CLUSTER_WAITING_FOR_NEWDISK, &cinfo->state);
+}
+
+
+static void process_metadata_update(struct mddev *mddev, struct cluster_msg *msg)
+{
+ struct md_cluster_info *cinfo = mddev->cluster_info;
+
+ md_reload_sb(mddev);
+ dlm_lock_sync(cinfo->no_new_dev_lockres, DLM_LOCK_CR);
+}
+
+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);
+
+ 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);
+}
+
+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);
+
+ 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);
+}
+
+static void process_recvd_msg(struct mddev *mddev, struct cluster_msg *msg)
+{
+ switch (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->cluster_info, msg->slot,
+ msg->low, 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;
+ default:
+ pr_warn("%s:%d Received unknown message from %d\n",
+ __func__, __LINE__, msg->slot);
+ }
+}
+
+/*
+ * thread for receiving message
+ */
+static void recv_daemon(struct md_thread *thread)
+{
+ struct md_cluster_info *cinfo = thread->mddev->cluster_info;
+ struct dlm_lock_resource *ack_lockres = cinfo->ack_lockres;
+ struct dlm_lock_resource *message_lockres = cinfo->message_lockres;
+ struct cluster_msg msg;
+
+ /*get CR on Message*/
+ if (dlm_lock_sync(message_lockres, DLM_LOCK_CR)) {
+ pr_err("md/raid1:failed to get CR on MESSAGE\n");
+ return;
+ }
+
+ /* read lvb and wake up thread to process this message_lockres */
+ memcpy(&msg, message_lockres->lksb.sb_lvbptr, sizeof(struct cluster_msg));
+ process_recvd_msg(thread->mddev, &msg);
+
+ /*release CR on ack_lockres*/
+ dlm_unlock_sync(ack_lockres);
+ /*up-convert to EX on message_lockres*/
+ dlm_lock_sync(message_lockres, DLM_LOCK_EX);
+ /*get CR on ack_lockres again*/
+ dlm_lock_sync(ack_lockres, DLM_LOCK_CR);
+ /*release CR on message_lockres*/
+ dlm_unlock_sync(message_lockres);
+}
+
+/* lock_comm()
+ * Takes the lock on the TOKEN lock resource so no other
+ * node can communicate while the operation is underway.
+ */
+static int lock_comm(struct md_cluster_info *cinfo)
+{
+ int error;
+
+ 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",
+ __func__, __LINE__, error);
+ return error;
+}
+
+static void unlock_comm(struct md_cluster_info *cinfo)
+{
+ dlm_unlock_sync(cinfo->token_lockres);
+}
+
+/* __sendmsg()
+ * This function performs the actual sending of the message. This function is
+ * usually called after performing the encompassing operation
+ * The function:
+ * 1. Grabs the message lockresource in EX mode
+ * 2. Copies the message to the message LVB
+ * 3. Downconverts message lockresource to CR
+ * 4. Upconverts ack lock resource from CR to EX. This forces the BAST on other nodes
+ * and the other nodes read the message. The thread will wait here until all other
+ * nodes have released ack lock resource.
+ * 5. Downconvert ack lockresource to CR
+ */
+static int __sendmsg(struct md_cluster_info *cinfo, struct cluster_msg *cmsg)
+{
+ int error;
+ int slot = cinfo->slot_number - 1;
+
+ cmsg->slot = cpu_to_le32(slot);
+ /*get EX on Message*/
+ error = dlm_lock_sync(cinfo->message_lockres, DLM_LOCK_EX);
+ if (error) {
+ pr_err("md-cluster: failed to get EX on MESSAGE (%d)\n", error);
+ goto failed_message;
+ }
+
+ memcpy(cinfo->message_lockres->lksb.sb_lvbptr, (void *)cmsg,
+ sizeof(struct cluster_msg));
+ /*down-convert EX to CR on Message*/
+ error = dlm_lock_sync(cinfo->message_lockres, DLM_LOCK_CR);
+ if (error) {
+ pr_err("md-cluster: failed to convert EX to CR on MESSAGE(%d)\n",
+ error);
+ goto failed_message;
+ }
+
+ /*up-convert CR to EX on Ack*/
+ error = dlm_lock_sync(cinfo->ack_lockres, DLM_LOCK_EX);
+ if (error) {
+ pr_err("md-cluster: failed to convert CR to EX on ACK(%d)\n",
+ error);
+ goto failed_ack;
+ }
+
+ /*down-convert EX to CR on Ack*/
+ error = dlm_lock_sync(cinfo->ack_lockres, DLM_LOCK_CR);
+ if (error) {
+ pr_err("md-cluster: failed to convert EX to CR on ACK(%d)\n",
+ error);
+ goto failed_ack;
+ }
+
+failed_ack:
+ dlm_unlock_sync(cinfo->message_lockres);
+failed_message:
+ return error;
+}
+
+static int sendmsg(struct md_cluster_info *cinfo, struct cluster_msg *cmsg)
+{
+ int ret;
+
+ lock_comm(cinfo);
+ ret = __sendmsg(cinfo, cmsg);
+ unlock_comm(cinfo);
+ return ret;
+}
+
static int gather_all_resync_info(struct mddev *mddev, int total_slots)
{
struct md_cluster_info *cinfo = mddev->cluster_info;
if (ret)
goto err;
wait_for_completion(&cinfo->completion);
- if (nodes <= cinfo->slot_number) {
- pr_err("md-cluster: Slot allotted(%d) greater than available slots(%d)", cinfo->slot_number - 1,
- nodes);
+ if (nodes < cinfo->slot_number) {
+ pr_err("md-cluster: Slot allotted(%d) is greater than available slots(%d).",
+ cinfo->slot_number, nodes);
ret = -ERANGE;
goto err;
}
ret = -ENOMEM;
goto err;
}
+ /* Initiate the communication resources */
+ ret = -ENOMEM;
+ cinfo->recv_thread = md_register_thread(recv_daemon, mddev, "cluster_recv");
+ if (!cinfo->recv_thread) {
+ pr_err("md-cluster: cannot allocate memory for recv_thread!\n");
+ goto err;
+ }
+ cinfo->message_lockres = lockres_init(mddev, "message", NULL, 1);
+ if (!cinfo->message_lockres)
+ goto err;
+ cinfo->token_lockres = lockres_init(mddev, "token", NULL, 0);
+ if (!cinfo->token_lockres)
+ goto err;
+ cinfo->ack_lockres = lockres_init(mddev, "ack", ack_bast, 0);
+ if (!cinfo->ack_lockres)
+ goto err;
+ cinfo->no_new_dev_lockres = lockres_init(mddev, "no-new-dev", NULL, 0);
+ if (!cinfo->no_new_dev_lockres)
+ goto err;
+
+ /* get sync CR lock on ACK. */
+ if (dlm_lock_sync(cinfo->ack_lockres, DLM_LOCK_CR))
+ pr_err("md-cluster: failed to get a sync CR lock on ACK!(%d)\n",
+ ret);
+ /* get sync CR lock on no-new-dev. */
+ if (dlm_lock_sync(cinfo->no_new_dev_lockres, DLM_LOCK_CR))
+ pr_err("md-cluster: failed to get a sync CR lock on no-new-dev!(%d)\n", ret);
+
pr_info("md-cluster: Joined cluster %s slot %d\n", str, cinfo->slot_number);
snprintf(str, 64, "bitmap%04d", cinfo->slot_number - 1);
return 0;
err:
+ lockres_free(cinfo->message_lockres);
+ lockres_free(cinfo->token_lockres);
+ lockres_free(cinfo->ack_lockres);
+ lockres_free(cinfo->no_new_dev_lockres);
lockres_free(cinfo->bitmap_lockres);
lockres_free(cinfo->sb_lock);
if (cinfo->lockspace)
if (!cinfo)
return 0;
md_unregister_thread(&cinfo->recovery_thread);
+ md_unregister_thread(&cinfo->recv_thread);
+ lockres_free(cinfo->message_lockres);
+ lockres_free(cinfo->token_lockres);
+ lockres_free(cinfo->ack_lockres);
+ lockres_free(cinfo->no_new_dev_lockres);
lockres_free(cinfo->sb_lock);
lockres_free(cinfo->bitmap_lockres);
dlm_release_lockspace(cinfo->lockspace, 2);
dlm_lock_sync(cinfo->bitmap_lockres, DLM_LOCK_PW);
}
+static int metadata_update_start(struct mddev *mddev)
+{
+ return lock_comm(mddev->cluster_info);
+}
+
+static int metadata_update_finish(struct mddev *mddev)
+{
+ struct md_cluster_info *cinfo = mddev->cluster_info;
+ struct cluster_msg cmsg;
+ int ret;
+
+ memset(&cmsg, 0, sizeof(cmsg));
+ cmsg.type = cpu_to_le32(METADATA_UPDATED);
+ ret = __sendmsg(cinfo, &cmsg);
+ unlock_comm(cinfo);
+ return ret;
+}
+
+static int metadata_update_cancel(struct mddev *mddev)
+{
+ struct md_cluster_info *cinfo = mddev->cluster_info;
+
+ return dlm_unlock_sync(cinfo->token_lockres);
+}
+
+static int resync_send(struct mddev *mddev, enum msg_type type,
+ sector_t lo, sector_t hi)
+{
+ struct md_cluster_info *cinfo = mddev->cluster_info;
+ struct cluster_msg cmsg;
+ int slot = cinfo->slot_number - 1;
+
+ pr_info("%s:%d lo: %llu hi: %llu\n", __func__, __LINE__,
+ (unsigned long long)lo,
+ (unsigned long long)hi);
+ resync_info_update(mddev, lo, hi);
+ cmsg.type = cpu_to_le32(type);
+ cmsg.slot = cpu_to_le32(slot);
+ cmsg.low = cpu_to_le64(lo);
+ cmsg.high = cpu_to_le64(hi);
+ return sendmsg(cinfo, &cmsg);
+}
+
+static int resync_start(struct mddev *mddev, sector_t lo, sector_t hi)
+{
+ pr_info("%s:%d\n", __func__, __LINE__);
+ return resync_send(mddev, RESYNCING, lo, hi);
+}
+
+static void resync_finish(struct mddev *mddev)
+{
+ pr_info("%s:%d\n", __func__, __LINE__);
+ resync_send(mddev, RESYNCING, 0, 0);
+}
+
+static int area_resyncing(struct mddev *mddev, sector_t lo, sector_t hi)
+{
+ struct md_cluster_info *cinfo = mddev->cluster_info;
+ int ret = 0;
+ struct suspend_info *s;
+
+ spin_lock_irq(&cinfo->suspend_lock);
+ if (list_empty(&cinfo->suspend_list))
+ goto out;
+ list_for_each_entry(s, &cinfo->suspend_list, list)
+ if (hi > s->lo && lo < s->hi) {
+ ret = 1;
+ break;
+ }
+out:
+ spin_unlock_irq(&cinfo->suspend_lock);
+ return ret;
+}
+
+static int add_new_disk_start(struct mddev *mddev, struct md_rdev *rdev)
+{
+ struct md_cluster_info *cinfo = mddev->cluster_info;
+ struct cluster_msg cmsg;
+ int ret = 0;
+ struct mdp_superblock_1 *sb = page_address(rdev->sb_page);
+ char *uuid = sb->device_uuid;
+
+ memset(&cmsg, 0, sizeof(cmsg));
+ cmsg.type = cpu_to_le32(NEWDISK);
+ memcpy(cmsg.uuid, uuid, 16);
+ cmsg.raid_slot = rdev->desc_nr;
+ lock_comm(cinfo);
+ ret = __sendmsg(cinfo, &cmsg);
+ if (ret)
+ return ret;
+ cinfo->no_new_dev_lockres->flags |= DLM_LKF_NOQUEUE;
+ ret = dlm_lock_sync(cinfo->no_new_dev_lockres, DLM_LOCK_EX);
+ cinfo->no_new_dev_lockres->flags &= ~DLM_LKF_NOQUEUE;
+ /* Some node does not "see" the device */
+ if (ret == -EAGAIN)
+ ret = -ENOENT;
+ else
+ dlm_lock_sync(cinfo->no_new_dev_lockres, DLM_LOCK_CR);
+ return ret;
+}
+
+static int add_new_disk_finish(struct mddev *mddev)
+{
+ struct cluster_msg cmsg;
+ struct md_cluster_info *cinfo = mddev->cluster_info;
+ int ret;
+ /* Write sb and inform others */
+ md_update_sb(mddev, 1);
+ cmsg.type = METADATA_UPDATED;
+ ret = __sendmsg(cinfo, &cmsg);
+ unlock_comm(cinfo);
+ return ret;
+}
+
+static int new_disk_ack(struct mddev *mddev, bool ack)
+{
+ struct md_cluster_info *cinfo = mddev->cluster_info;
+
+ if (!test_bit(MD_CLUSTER_WAITING_FOR_NEWDISK, &cinfo->state)) {
+ pr_warn("md-cluster(%s): Spurious cluster confirmation\n", mdname(mddev));
+ return -EINVAL;
+ }
+
+ if (ack)
+ dlm_unlock_sync(cinfo->no_new_dev_lockres);
+ complete(&cinfo->newdisk_completion);
+ return 0;
+}
+
+static int remove_disk(struct mddev *mddev, struct md_rdev *rdev)
+{
+ struct cluster_msg cmsg;
+ struct md_cluster_info *cinfo = mddev->cluster_info;
+ cmsg.type = REMOVE;
+ cmsg.raid_slot = rdev->desc_nr;
+ return __sendmsg(cinfo, &cmsg);
+}
+
+static int gather_bitmaps(struct md_rdev *rdev)
+{
+ int sn, err;
+ sector_t lo, hi;
+ struct cluster_msg cmsg;
+ struct mddev *mddev = rdev->mddev;
+ struct md_cluster_info *cinfo = mddev->cluster_info;
+
+ cmsg.type = RE_ADD;
+ cmsg.raid_slot = rdev->desc_nr;
+ err = sendmsg(cinfo, &cmsg);
+ if (err)
+ goto out;
+
+ for (sn = 0; sn < mddev->bitmap_info.nodes; sn++) {
+ if (sn == (cinfo->slot_number - 1))
+ continue;
+ err = bitmap_copy_from_slot(mddev, sn, &lo, &hi, false);
+ if (err) {
+ pr_warn("md-cluster: Could not gather bitmaps from slot %d", sn);
+ goto out;
+ }
+ if ((hi > 0) && (lo < mddev->recovery_cp))
+ mddev->recovery_cp = lo;
+ }
+out:
+ return err;
+}
+
static struct md_cluster_operations cluster_ops = {
.join = join,
.leave = leave,
.slot_number = slot_number,
.resync_info_update = resync_info_update,
+ .resync_start = resync_start,
+ .resync_finish = resync_finish,
+ .metadata_update_start = metadata_update_start,
+ .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,
+ .new_disk_ack = new_disk_ack,
+ .remove_disk = remove_disk,
+ .gather_bitmaps = gather_bitmaps,
};
static int __init cluster_init(void)
projects / cascardo / linux.git / blobdiff