md-cluster.c 22.5 KB
Newer Older
1 2 3 4 5 6 7 8 9 10 11 12
/*
 * Copyright (C) 2015, SUSE
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License as published by
 * the Free Software Foundation; either version 2, or (at your option)
 * any later version.
 *
 */


#include <linux/module.h>
13 14
#include <linux/dlm.h>
#include <linux/sched.h>
15
#include <linux/raid/md_p.h>
16
#include "md.h"
17
#include "bitmap.h"
18
#include "md-cluster.h"
19 20

#define LVB_SIZE	64
21
#define NEW_DEV_TIMEOUT 5000
22 23 24 25 26 27 28

struct dlm_lock_resource {
	dlm_lockspace_t *ls;
	struct dlm_lksb lksb;
	char *name; /* lock name. */
	uint32_t flags; /* flags to pass to dlm_lock() */
	struct completion completion; /* completion for synchronized locking */
G
Goldwyn Rodrigues 已提交
29 30 31 32
	void (*bast)(void *arg, int mode); /* blocking AST function pointer*/
	struct mddev *mddev; /* pointing back to mddev. */
};

33 34 35 36 37 38 39 40 41 42 43 44
struct suspend_info {
	int slot;
	sector_t lo;
	sector_t hi;
	struct list_head list;
};

struct resync_info {
	__le64 lo;
	__le64 hi;
};

G
Goldwyn Rodrigues 已提交
45 46 47
struct md_cluster_info {
	/* dlm lock space and resources for clustered raid. */
	dlm_lockspace_t *lockspace;
G
Goldwyn Rodrigues 已提交
48 49
	int slot_number;
	struct completion completion;
G
Goldwyn Rodrigues 已提交
50 51
	struct dlm_lock_resource *sb_lock;
	struct mutex sb_mutex;
52
	struct dlm_lock_resource *bitmap_lockres;
53 54
	struct list_head suspend_list;
	spinlock_t suspend_lock;
55 56
	struct md_thread *recovery_thread;
	unsigned long recovery_map;
57 58 59 60
	/* communication loc resources */
	struct dlm_lock_resource *ack_lockres;
	struct dlm_lock_resource *message_lockres;
	struct dlm_lock_resource *token_lockres;
61
	struct dlm_lock_resource *no_new_dev_lockres;
62
	struct md_thread *recv_thread;
63
	struct completion newdisk_completion;
64 65 66 67 68
};

enum msg_type {
	METADATA_UPDATED = 0,
	RESYNCING,
69
	NEWDISK,
70 71 72 73 74
};

struct cluster_msg {
	int type;
	int slot;
75
	/* TODO: Unionize this for smaller footprint */
76 77
	sector_t low;
	sector_t high;
78 79
	char uuid[16];
	int raid_slot;
80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108
};

static void sync_ast(void *arg)
{
	struct dlm_lock_resource *res;

	res = (struct dlm_lock_resource *) arg;
	complete(&res->completion);
}

static int dlm_lock_sync(struct dlm_lock_resource *res, int mode)
{
	int ret = 0;

	init_completion(&res->completion);
	ret = dlm_lock(res->ls, mode, &res->lksb,
			res->flags, res->name, strlen(res->name),
			0, sync_ast, res, res->bast);
	if (ret)
		return ret;
	wait_for_completion(&res->completion);
	return res->lksb.sb_status;
}

static int dlm_unlock_sync(struct dlm_lock_resource *res)
{
	return dlm_lock_sync(res, DLM_LOCK_NL);
}

G
Goldwyn Rodrigues 已提交
109
static struct dlm_lock_resource *lockres_init(struct mddev *mddev,
110 111 112 113
		char *name, void (*bastfn)(void *arg, int mode), int with_lvb)
{
	struct dlm_lock_resource *res = NULL;
	int ret, namelen;
G
Goldwyn Rodrigues 已提交
114
	struct md_cluster_info *cinfo = mddev->cluster_info;
115 116 117 118

	res = kzalloc(sizeof(struct dlm_lock_resource), GFP_KERNEL);
	if (!res)
		return NULL;
G
Goldwyn Rodrigues 已提交
119 120
	res->ls = cinfo->lockspace;
	res->mddev = mddev;
121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170
	namelen = strlen(name);
	res->name = kzalloc(namelen + 1, GFP_KERNEL);
	if (!res->name) {
		pr_err("md-cluster: Unable to allocate resource name for resource %s\n", name);
		goto out_err;
	}
	strlcpy(res->name, name, namelen + 1);
	if (with_lvb) {
		res->lksb.sb_lvbptr = kzalloc(LVB_SIZE, GFP_KERNEL);
		if (!res->lksb.sb_lvbptr) {
			pr_err("md-cluster: Unable to allocate LVB for resource %s\n", name);
			goto out_err;
		}
		res->flags = DLM_LKF_VALBLK;
	}

	if (bastfn)
		res->bast = bastfn;

	res->flags |= DLM_LKF_EXPEDITE;

	ret = dlm_lock_sync(res, DLM_LOCK_NL);
	if (ret) {
		pr_err("md-cluster: Unable to lock NL on new lock resource %s\n", name);
		goto out_err;
	}
	res->flags &= ~DLM_LKF_EXPEDITE;
	res->flags |= DLM_LKF_CONVERT;

	return res;
out_err:
	kfree(res->lksb.sb_lvbptr);
	kfree(res->name);
	kfree(res);
	return NULL;
}

static void lockres_free(struct dlm_lock_resource *res)
{
	if (!res)
		return;

	init_completion(&res->completion);
	dlm_unlock(res->ls, res->lksb.sb_lkid, 0, &res->lksb, res);
	wait_for_completion(&res->completion);

	kfree(res->name);
	kfree(res->lksb.sb_lvbptr);
	kfree(res);
}
171

G
Goldwyn Rodrigues 已提交
172 173 174 175 176 177 178 179 180 181 182 183
static char *pretty_uuid(char *dest, char *src)
{
	int i, len = 0;

	for (i = 0; i < 16; i++) {
		if (i == 4 || i == 6 || i == 8 || i == 10)
			len += sprintf(dest + len, "-");
		len += sprintf(dest + len, "%02x", (__u8)src[i]);
	}
	return dest;
}

184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214
static void add_resync_info(struct mddev *mddev, struct dlm_lock_resource *lockres,
		sector_t lo, sector_t hi)
{
	struct resync_info *ri;

	ri = (struct resync_info *)lockres->lksb.sb_lvbptr;
	ri->lo = cpu_to_le64(lo);
	ri->hi = cpu_to_le64(hi);
}

static struct suspend_info *read_resync_info(struct mddev *mddev, struct dlm_lock_resource *lockres)
{
	struct resync_info ri;
	struct suspend_info *s = NULL;
	sector_t hi = 0;

	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) {
		s = kzalloc(sizeof(struct suspend_info), GFP_KERNEL);
		if (!s)
			goto out;
		s->hi = hi;
		s->lo = le64_to_cpu(ri.lo);
	}
	dlm_unlock_sync(lockres);
out:
	return s;
}

215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250
void recover_bitmaps(struct md_thread *thread)
{
	struct mddev *mddev = thread->mddev;
	struct md_cluster_info *cinfo = mddev->cluster_info;
	struct dlm_lock_resource *bm_lockres;
	char str[64];
	int slot, ret;
	struct suspend_info *s, *tmp;
	sector_t lo, hi;

	while (cinfo->recovery_map) {
		slot = fls64((u64)cinfo->recovery_map) - 1;

		/* Clear suspend_area associated with the bitmap */
		spin_lock_irq(&cinfo->suspend_lock);
		list_for_each_entry_safe(s, tmp, &cinfo->suspend_list, list)
			if (slot == s->slot) {
				list_del(&s->list);
				kfree(s);
			}
		spin_unlock_irq(&cinfo->suspend_lock);

		snprintf(str, 64, "bitmap%04d", slot);
		bm_lockres = lockres_init(mddev, str, NULL, 1);
		if (!bm_lockres) {
			pr_err("md-cluster: Cannot initialize bitmaps\n");
			goto clear_bit;
		}

		ret = dlm_lock_sync(bm_lockres, DLM_LOCK_PW);
		if (ret) {
			pr_err("md-cluster: Could not DLM lock %s: %d\n",
					str, ret);
			goto clear_bit;
		}
		ret = bitmap_copy_from_slot(mddev, slot, &lo, &hi);
251
		if (ret) {
252
			pr_err("md-cluster: Could not copy data from bitmap %d\n", slot);
253 254 255 256 257 258 259 260 261 262
			goto dlm_unlock;
		}
		if (hi > 0) {
			/* TODO:Wait for current resync to get over */
			set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
			if (lo < mddev->recovery_cp)
				mddev->recovery_cp = lo;
			md_check_recovery(mddev);
		}
dlm_unlock:
263 264 265 266 267 268
		dlm_unlock_sync(bm_lockres);
clear_bit:
		clear_bit(slot, &cinfo->recovery_map);
	}
}

G
Goldwyn Rodrigues 已提交
269 270 271 272 273 274 275 276 277 278 279 280 281
static void recover_prep(void *arg)
{
}

static void recover_slot(void *arg, struct dlm_slot *slot)
{
	struct mddev *mddev = arg;
	struct md_cluster_info *cinfo = mddev->cluster_info;

	pr_info("md-cluster: %s Node %d/%d down. My slot: %d. Initiating recovery.\n",
			mddev->bitmap_info.cluster_name,
			slot->nodeid, slot->slot,
			cinfo->slot_number);
282 283 284 285 286 287 288 289 290 291
	set_bit(slot->slot - 1, &cinfo->recovery_map);
	if (!cinfo->recovery_thread) {
		cinfo->recovery_thread = md_register_thread(recover_bitmaps,
				mddev, "recover");
		if (!cinfo->recovery_thread) {
			pr_warn("md-cluster: Could not create recovery thread\n");
			return;
		}
	}
	md_wakeup_thread(cinfo->recovery_thread);
G
Goldwyn Rodrigues 已提交
292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310
}

static void recover_done(void *arg, struct dlm_slot *slots,
		int num_slots, int our_slot,
		uint32_t generation)
{
	struct mddev *mddev = arg;
	struct md_cluster_info *cinfo = mddev->cluster_info;

	cinfo->slot_number = our_slot;
	complete(&cinfo->completion);
}

static const struct dlm_lockspace_ops md_ls_ops = {
	.recover_prep = recover_prep,
	.recover_slot = recover_slot,
	.recover_done = recover_done,
};

311 312 313 314 315 316 317 318 319 320 321 322 323 324
/*
 * 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);
}

G
Goldwyn Rodrigues 已提交
325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368
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);
}

369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396
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);
	kobject_uevent_env(&disk_to_dev(mddev->gendisk)->kobj, KOBJ_CHANGE, envp);
	wait_for_completion_timeout(&cinfo->newdisk_completion,
			NEW_DEV_TIMEOUT);
}


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);
}

397 398 399 400 401 402
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);
403
		process_metadata_update(mddev, msg);
404 405 406 407
		break;
	case RESYNCING:
		pr_info("%s: %d Received message: RESYNCING from %d\n",
			__func__, __LINE__, msg->slot);
G
Goldwyn Rodrigues 已提交
408 409
		process_suspend_info(mddev->cluster_info, msg->slot,
				msg->low, msg->high);
410
		break;
411 412 413 414
	case NEWDISK:
		pr_info("%s: %d Received message: NEWDISK from %d\n",
			__func__, __LINE__, msg->slot);
		process_add_new_disk(mddev, msg);
415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447
	};
}

/*
 * 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);
}

448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534
/* 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;
}

535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581
static int gather_all_resync_info(struct mddev *mddev, int total_slots)
{
	struct md_cluster_info *cinfo = mddev->cluster_info;
	int i, ret = 0;
	struct dlm_lock_resource *bm_lockres;
	struct suspend_info *s;
	char str[64];


	for (i = 0; i < total_slots; i++) {
		memset(str, '\0', 64);
		snprintf(str, 64, "bitmap%04d", i);
		bm_lockres = lockres_init(mddev, str, NULL, 1);
		if (!bm_lockres)
			return -ENOMEM;
		if (i == (cinfo->slot_number - 1))
			continue;

		bm_lockres->flags |= DLM_LKF_NOQUEUE;
		ret = dlm_lock_sync(bm_lockres, DLM_LOCK_PW);
		if (ret == -EAGAIN) {
			memset(bm_lockres->lksb.sb_lvbptr, '\0', LVB_SIZE);
			s = read_resync_info(mddev, bm_lockres);
			if (s) {
				pr_info("%s:%d Resync[%llu..%llu] in progress on %d\n",
						__func__, __LINE__,
						(unsigned long long) s->lo,
						(unsigned long long) s->hi, i);
				spin_lock_irq(&cinfo->suspend_lock);
				s->slot = i;
				list_add(&s->list, &cinfo->suspend_list);
				spin_unlock_irq(&cinfo->suspend_lock);
			}
			ret = 0;
			lockres_free(bm_lockres);
			continue;
		}
		if (ret)
			goto out;
		/* TODO: Read the disk bitmap sb and check if it needs recovery */
		dlm_unlock_sync(bm_lockres);
		lockres_free(bm_lockres);
	}
out:
	return ret;
}

582 583
static int join(struct mddev *mddev, int nodes)
{
G
Goldwyn Rodrigues 已提交
584
	struct md_cluster_info *cinfo;
G
Goldwyn Rodrigues 已提交
585
	int ret, ops_rv;
G
Goldwyn Rodrigues 已提交
586 587 588 589 590 591 592 593 594
	char str[64];

	if (!try_module_get(THIS_MODULE))
		return -ENOENT;

	cinfo = kzalloc(sizeof(struct md_cluster_info), GFP_KERNEL);
	if (!cinfo)
		return -ENOMEM;

G
Goldwyn Rodrigues 已提交
595 596 597 598 599
	init_completion(&cinfo->completion);

	mutex_init(&cinfo->sb_mutex);
	mddev->cluster_info = cinfo;

G
Goldwyn Rodrigues 已提交
600 601
	memset(str, 0, 64);
	pretty_uuid(str, mddev->uuid);
G
Goldwyn Rodrigues 已提交
602 603 604
	ret = dlm_new_lockspace(str, mddev->bitmap_info.cluster_name,
				DLM_LSFL_FS, LVB_SIZE,
				&md_ls_ops, mddev, &ops_rv, &cinfo->lockspace);
G
Goldwyn Rodrigues 已提交
605 606
	if (ret)
		goto err;
G
Goldwyn Rodrigues 已提交
607
	wait_for_completion(&cinfo->completion);
608 609 610 611 612 613
	if (nodes <= cinfo->slot_number) {
		pr_err("md-cluster: Slot allotted(%d) greater than available slots(%d)", cinfo->slot_number - 1,
			nodes);
		ret = -ERANGE;
		goto err;
	}
G
Goldwyn Rodrigues 已提交
614 615 616 617 618 619
	cinfo->sb_lock = lockres_init(mddev, "cmd-super",
					NULL, 0);
	if (!cinfo->sb_lock) {
		ret = -ENOMEM;
		goto err;
	}
620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635
	/* 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;
636 637 638 639
	cinfo->no_new_dev_lockres = lockres_init(mddev, "no-new-dev", NULL, 0);
	if (!cinfo->no_new_dev_lockres)
		goto err;

640 641 642 643
	/* 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);
644 645 646 647
	/* 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);

648 649 650 651 652 653 654 655 656 657 658 659

	pr_info("md-cluster: Joined cluster %s slot %d\n", str, cinfo->slot_number);
	snprintf(str, 64, "bitmap%04d", cinfo->slot_number - 1);
	cinfo->bitmap_lockres = lockres_init(mddev, str, NULL, 1);
	if (!cinfo->bitmap_lockres)
		goto err;
	if (dlm_lock_sync(cinfo->bitmap_lockres, DLM_LOCK_PW)) {
		pr_err("Failed to get bitmap lock\n");
		ret = -EINVAL;
		goto err;
	}

660 661 662 663 664 665 666
	INIT_LIST_HEAD(&cinfo->suspend_list);
	spin_lock_init(&cinfo->suspend_lock);

	ret = gather_all_resync_info(mddev, nodes);
	if (ret)
		goto err;

667
	return 0;
G
Goldwyn Rodrigues 已提交
668
err:
669 670 671
	lockres_free(cinfo->message_lockres);
	lockres_free(cinfo->token_lockres);
	lockres_free(cinfo->ack_lockres);
672
	lockres_free(cinfo->no_new_dev_lockres);
673 674
	lockres_free(cinfo->bitmap_lockres);
	lockres_free(cinfo->sb_lock);
G
Goldwyn Rodrigues 已提交
675 676
	if (cinfo->lockspace)
		dlm_release_lockspace(cinfo->lockspace, 2);
G
Goldwyn Rodrigues 已提交
677
	mddev->cluster_info = NULL;
G
Goldwyn Rodrigues 已提交
678 679 680
	kfree(cinfo);
	module_put(THIS_MODULE);
	return ret;
681 682 683 684
}

static int leave(struct mddev *mddev)
{
G
Goldwyn Rodrigues 已提交
685 686 687 688
	struct md_cluster_info *cinfo = mddev->cluster_info;

	if (!cinfo)
		return 0;
689
	md_unregister_thread(&cinfo->recovery_thread);
690 691 692 693
	md_unregister_thread(&cinfo->recv_thread);
	lockres_free(cinfo->message_lockres);
	lockres_free(cinfo->token_lockres);
	lockres_free(cinfo->ack_lockres);
694
	lockres_free(cinfo->no_new_dev_lockres);
G
Goldwyn Rodrigues 已提交
695
	lockres_free(cinfo->sb_lock);
696
	lockres_free(cinfo->bitmap_lockres);
G
Goldwyn Rodrigues 已提交
697
	dlm_release_lockspace(cinfo->lockspace, 2);
698 699 700
	return 0;
}

G
Goldwyn Rodrigues 已提交
701 702 703 704 705 706 707 708 709 710 711
/* slot_number(): Returns the MD slot number to use
 * DLM starts the slot numbers from 1, wheras cluster-md
 * wants the number to be from zero, so we deduct one
 */
static int slot_number(struct mddev *mddev)
{
	struct md_cluster_info *cinfo = mddev->cluster_info;

	return cinfo->slot_number - 1;
}

712 713 714 715 716 717 718 719 720
static void resync_info_update(struct mddev *mddev, sector_t lo, sector_t hi)
{
	struct md_cluster_info *cinfo = mddev->cluster_info;

	add_resync_info(mddev, cinfo->bitmap_lockres, lo, hi);
	/* Re-acquire the lock to refresh LVB */
	dlm_lock_sync(cinfo->bitmap_lockres, DLM_LOCK_PW);
}

721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745
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);
}

746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775
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);
}

776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794
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;
}

795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843
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 void new_disk_ack(struct mddev *mddev, bool ack)
{
	struct md_cluster_info *cinfo = mddev->cluster_info;

	if (ack)
		dlm_unlock_sync(cinfo->no_new_dev_lockres);
	complete(&cinfo->newdisk_completion);
}

844 845 846
static struct md_cluster_operations cluster_ops = {
	.join   = join,
	.leave  = leave,
G
Goldwyn Rodrigues 已提交
847
	.slot_number = slot_number,
848
	.resync_info_update = resync_info_update,
849 850
	.resync_start = resync_start,
	.resync_finish = resync_finish,
851 852 853
	.metadata_update_start = metadata_update_start,
	.metadata_update_finish = metadata_update_finish,
	.metadata_update_cancel = metadata_update_cancel,
854
	.area_resyncing = area_resyncing,
855 856 857
	.add_new_disk_start = add_new_disk_start,
	.add_new_disk_finish = add_new_disk_finish,
	.new_disk_ack = new_disk_ack,
858 859
};

860 861 862 863
static int __init cluster_init(void)
{
	pr_warn("md-cluster: EXPERIMENTAL. Use with caution\n");
	pr_info("Registering Cluster MD functions\n");
864
	register_md_cluster_operations(&cluster_ops, THIS_MODULE);
865 866 867 868 869
	return 0;
}

static void cluster_exit(void)
{
870
	unregister_md_cluster_operations();
871 872 873 874 875 876
}

module_init(cluster_init);
module_exit(cluster_exit);
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("Clustering support for MD");