drbd_main.c 117.1 KB
Newer Older
P
Philipp Reisner 已提交
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34
/*
   drbd.c

   This file is part of DRBD by Philipp Reisner and Lars Ellenberg.

   Copyright (C) 2001-2008, LINBIT Information Technologies GmbH.
   Copyright (C) 1999-2008, Philipp Reisner <philipp.reisner@linbit.com>.
   Copyright (C) 2002-2008, Lars Ellenberg <lars.ellenberg@linbit.com>.

   Thanks to Carter Burden, Bart Grantham and Gennadiy Nerubayev
   from Logicworks, Inc. for making SDP replication support possible.

   drbd 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.

   drbd is distributed in the hope that it will be useful,
   but WITHOUT ANY WARRANTY; without even the implied warranty of
   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
   GNU General Public License for more details.

   You should have received a copy of the GNU General Public License
   along with drbd; see the file COPYING.  If not, write to
   the Free Software Foundation, 675 Mass Ave, Cambridge, MA 02139, USA.

 */

#include <linux/module.h>
#include <linux/drbd.h>
#include <asm/uaccess.h>
#include <asm/types.h>
#include <net/sock.h>
#include <linux/ctype.h>
35
#include <linux/mutex.h>
P
Philipp Reisner 已提交
36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66
#include <linux/fs.h>
#include <linux/file.h>
#include <linux/proc_fs.h>
#include <linux/init.h>
#include <linux/mm.h>
#include <linux/memcontrol.h>
#include <linux/mm_inline.h>
#include <linux/slab.h>
#include <linux/random.h>
#include <linux/reboot.h>
#include <linux/notifier.h>
#include <linux/kthread.h>

#define __KERNEL_SYSCALLS__
#include <linux/unistd.h>
#include <linux/vmalloc.h>

#include <linux/drbd_limits.h>
#include "drbd_int.h"
#include "drbd_req.h" /* only for _req_mod in tl_release and tl_clear */

#include "drbd_vli.h"

struct after_state_chg_work {
	struct drbd_work w;
	union drbd_state os;
	union drbd_state ns;
	enum chg_state_flags flags;
	struct completion *done;
};

67
static DEFINE_MUTEX(drbd_main_mutex);
P
Philipp Reisner 已提交
68 69 70 71 72 73 74 75 76 77 78 79 80
int drbdd_init(struct drbd_thread *);
int drbd_worker(struct drbd_thread *);
int drbd_asender(struct drbd_thread *);

int drbd_init(void);
static int drbd_open(struct block_device *bdev, fmode_t mode);
static int drbd_release(struct gendisk *gd, fmode_t mode);
static int w_after_state_ch(struct drbd_conf *mdev, struct drbd_work *w, int unused);
static void after_state_ch(struct drbd_conf *mdev, union drbd_state os,
			   union drbd_state ns, enum chg_state_flags flags);
static int w_md_sync(struct drbd_conf *mdev, struct drbd_work *w, int unused);
static void md_sync_timer_fn(unsigned long data);
static int w_bitmap_io(struct drbd_conf *mdev, struct drbd_work *w, int unused);
81
static int w_go_diskless(struct drbd_conf *mdev, struct drbd_work *w, int unused);
P
Philipp Reisner 已提交
82 83 84 85 86 87

MODULE_AUTHOR("Philipp Reisner <phil@linbit.com>, "
	      "Lars Ellenberg <lars@linbit.com>");
MODULE_DESCRIPTION("drbd - Distributed Replicated Block Device v" REL_VERSION);
MODULE_VERSION(REL_VERSION);
MODULE_LICENSE("GPL");
88 89
MODULE_PARM_DESC(minor_count, "Maximum number of drbd devices ("
		 __stringify(DRBD_MINOR_COUNT_MIN) "-" __stringify(DRBD_MINOR_COUNT_MAX) ")");
P
Philipp Reisner 已提交
90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118
MODULE_ALIAS_BLOCKDEV_MAJOR(DRBD_MAJOR);

#include <linux/moduleparam.h>
/* allow_open_on_secondary */
MODULE_PARM_DESC(allow_oos, "DONT USE!");
/* thanks to these macros, if compiled into the kernel (not-module),
 * this becomes the boot parameter drbd.minor_count */
module_param(minor_count, uint, 0444);
module_param(disable_sendpage, bool, 0644);
module_param(allow_oos, bool, 0);
module_param(cn_idx, uint, 0444);
module_param(proc_details, int, 0644);

#ifdef CONFIG_DRBD_FAULT_INJECTION
int enable_faults;
int fault_rate;
static int fault_count;
int fault_devs;
/* bitmap of enabled faults */
module_param(enable_faults, int, 0664);
/* fault rate % value - applies to all enabled faults */
module_param(fault_rate, int, 0664);
/* count of faults inserted */
module_param(fault_count, int, 0664);
/* bitmap of devices to insert faults on */
module_param(fault_devs, int, 0644);
#endif

/* module parameter, defined */
119
unsigned int minor_count = DRBD_MINOR_COUNT_DEF;
120 121
bool disable_sendpage;
bool allow_oos;
P
Philipp Reisner 已提交
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
unsigned int cn_idx = CN_IDX_DRBD;
int proc_details;       /* Detail level in proc drbd*/

/* Module parameter for setting the user mode helper program
 * to run. Default is /sbin/drbdadm */
char usermode_helper[80] = "/sbin/drbdadm";

module_param_string(usermode_helper, usermode_helper, sizeof(usermode_helper), 0644);

/* in 2.6.x, our device mapping and config info contains our virtual gendisks
 * as member "struct gendisk *vdisk;"
 */
struct drbd_conf **minor_table;

struct kmem_cache *drbd_request_cache;
struct kmem_cache *drbd_ee_cache;	/* epoch entries */
struct kmem_cache *drbd_bm_ext_cache;	/* bitmap extents */
struct kmem_cache *drbd_al_ext_cache;	/* activity log extents */
mempool_t *drbd_request_mempool;
mempool_t *drbd_ee_mempool;

/* I do not use a standard mempool, because:
   1) I want to hand out the pre-allocated objects first.
   2) I want to be able to interrupt sleeping allocation with a signal.
   Note: This is a single linked list, the next pointer is the private
	 member of struct page.
 */
struct page *drbd_pp_pool;
spinlock_t   drbd_pp_lock;
int          drbd_pp_vacant;
wait_queue_head_t drbd_pp_wait;

DEFINE_RATELIMIT_STATE(drbd_ratelimit_state, 5 * HZ, 5);

156
static const struct block_device_operations drbd_ops = {
P
Philipp Reisner 已提交
157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204
	.owner =   THIS_MODULE,
	.open =    drbd_open,
	.release = drbd_release,
};

#define ARRY_SIZE(A) (sizeof(A)/sizeof(A[0]))

#ifdef __CHECKER__
/* When checking with sparse, and this is an inline function, sparse will
   give tons of false positives. When this is a real functions sparse works.
 */
int _get_ldev_if_state(struct drbd_conf *mdev, enum drbd_disk_state mins)
{
	int io_allowed;

	atomic_inc(&mdev->local_cnt);
	io_allowed = (mdev->state.disk >= mins);
	if (!io_allowed) {
		if (atomic_dec_and_test(&mdev->local_cnt))
			wake_up(&mdev->misc_wait);
	}
	return io_allowed;
}

#endif

/**
 * DOC: The transfer log
 *
 * The transfer log is a single linked list of &struct drbd_tl_epoch objects.
 * mdev->newest_tle points to the head, mdev->oldest_tle points to the tail
 * of the list. There is always at least one &struct drbd_tl_epoch object.
 *
 * Each &struct drbd_tl_epoch has a circular double linked list of requests
 * attached.
 */
static int tl_init(struct drbd_conf *mdev)
{
	struct drbd_tl_epoch *b;

	/* during device minor initialization, we may well use GFP_KERNEL */
	b = kmalloc(sizeof(struct drbd_tl_epoch), GFP_KERNEL);
	if (!b)
		return 0;
	INIT_LIST_HEAD(&b->requests);
	INIT_LIST_HEAD(&b->w.list);
	b->next = NULL;
	b->br_number = 4711;
205
	b->n_writes = 0;
P
Philipp Reisner 已提交
206 207 208 209 210
	b->w.cb = NULL; /* if this is != NULL, we need to dec_ap_pending in tl_clear */

	mdev->oldest_tle = b;
	mdev->newest_tle = b;
	INIT_LIST_HEAD(&mdev->out_of_sequence_requests);
211
	INIT_LIST_HEAD(&mdev->barrier_acked_requests);
P
Philipp Reisner 已提交
212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246

	mdev->tl_hash = NULL;
	mdev->tl_hash_s = 0;

	return 1;
}

static void tl_cleanup(struct drbd_conf *mdev)
{
	D_ASSERT(mdev->oldest_tle == mdev->newest_tle);
	D_ASSERT(list_empty(&mdev->out_of_sequence_requests));
	kfree(mdev->oldest_tle);
	mdev->oldest_tle = NULL;
	kfree(mdev->unused_spare_tle);
	mdev->unused_spare_tle = NULL;
	kfree(mdev->tl_hash);
	mdev->tl_hash = NULL;
	mdev->tl_hash_s = 0;
}

/**
 * _tl_add_barrier() - Adds a barrier to the transfer log
 * @mdev:	DRBD device.
 * @new:	Barrier to be added before the current head of the TL.
 *
 * The caller must hold the req_lock.
 */
void _tl_add_barrier(struct drbd_conf *mdev, struct drbd_tl_epoch *new)
{
	struct drbd_tl_epoch *newest_before;

	INIT_LIST_HEAD(&new->requests);
	INIT_LIST_HEAD(&new->w.list);
	new->w.cb = NULL; /* if this is != NULL, we need to dec_ap_pending in tl_clear */
	new->next = NULL;
247
	new->n_writes = 0;
P
Philipp Reisner 已提交
248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290

	newest_before = mdev->newest_tle;
	/* never send a barrier number == 0, because that is special-cased
	 * when using TCQ for our write ordering code */
	new->br_number = (newest_before->br_number+1) ?: 1;
	if (mdev->newest_tle != new) {
		mdev->newest_tle->next = new;
		mdev->newest_tle = new;
	}
}

/**
 * tl_release() - Free or recycle the oldest &struct drbd_tl_epoch object of the TL
 * @mdev:	DRBD device.
 * @barrier_nr:	Expected identifier of the DRBD write barrier packet.
 * @set_size:	Expected number of requests before that barrier.
 *
 * In case the passed barrier_nr or set_size does not match the oldest
 * &struct drbd_tl_epoch objects this function will cause a termination
 * of the connection.
 */
void tl_release(struct drbd_conf *mdev, unsigned int barrier_nr,
		       unsigned int set_size)
{
	struct drbd_tl_epoch *b, *nob; /* next old barrier */
	struct list_head *le, *tle;
	struct drbd_request *r;

	spin_lock_irq(&mdev->req_lock);

	b = mdev->oldest_tle;

	/* first some paranoia code */
	if (b == NULL) {
		dev_err(DEV, "BAD! BarrierAck #%u received, but no epoch in tl!?\n",
			barrier_nr);
		goto bail;
	}
	if (b->br_number != barrier_nr) {
		dev_err(DEV, "BAD! BarrierAck #%u received, expected #%u!\n",
			barrier_nr, b->br_number);
		goto bail;
	}
291 292 293
	if (b->n_writes != set_size) {
		dev_err(DEV, "BAD! BarrierAck #%u received with n_writes=%u, expected n_writes=%u!\n",
			barrier_nr, set_size, b->n_writes);
P
Philipp Reisner 已提交
294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314
		goto bail;
	}

	/* Clean up list of requests processed during current epoch */
	list_for_each_safe(le, tle, &b->requests) {
		r = list_entry(le, struct drbd_request, tl_requests);
		_req_mod(r, barrier_acked);
	}
	/* There could be requests on the list waiting for completion
	   of the write to the local disk. To avoid corruptions of
	   slab's data structures we have to remove the lists head.

	   Also there could have been a barrier ack out of sequence, overtaking
	   the write acks - which would be a bug and violating write ordering.
	   To not deadlock in case we lose connection while such requests are
	   still pending, we need some way to find them for the
	   _req_mode(connection_lost_while_pending).

	   These have been list_move'd to the out_of_sequence_requests list in
	   _req_mod(, barrier_acked) above.
	   */
315
	list_splice_init(&b->requests, &mdev->barrier_acked_requests);
P
Philipp Reisner 已提交
316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339

	nob = b->next;
	if (test_and_clear_bit(CREATE_BARRIER, &mdev->flags)) {
		_tl_add_barrier(mdev, b);
		if (nob)
			mdev->oldest_tle = nob;
		/* if nob == NULL b was the only barrier, and becomes the new
		   barrier. Therefore mdev->oldest_tle points already to b */
	} else {
		D_ASSERT(nob != NULL);
		mdev->oldest_tle = nob;
		kfree(b);
	}

	spin_unlock_irq(&mdev->req_lock);
	dec_ap_pending(mdev);

	return;

bail:
	spin_unlock_irq(&mdev->req_lock);
	drbd_force_state(mdev, NS(conn, C_PROTOCOL_ERROR));
}

340

P
Philipp Reisner 已提交
341
/**
342
 * _tl_restart() - Walks the transfer log, and applies an action to all requests
P
Philipp Reisner 已提交
343
 * @mdev:	DRBD device.
344
 * @what:       The action/event to perform with all request objects
P
Philipp Reisner 已提交
345
 *
346
 * @what might be one of connection_lost_while_pending, resend, fail_frozen_disk_io,
347
 * restart_frozen_disk_io.
P
Philipp Reisner 已提交
348
 */
349
static void _tl_restart(struct drbd_conf *mdev, enum drbd_req_event what)
P
Philipp Reisner 已提交
350
{
351
	struct drbd_tl_epoch *b, *tmp, **pn;
352
	struct list_head *le, *tle, carry_reads;
353 354
	struct drbd_request *req;
	int rv, n_writes, n_reads;
P
Philipp Reisner 已提交
355 356

	b = mdev->oldest_tle;
357
	pn = &mdev->oldest_tle;
P
Philipp Reisner 已提交
358
	while (b) {
359 360
		n_writes = 0;
		n_reads = 0;
361
		INIT_LIST_HEAD(&carry_reads);
P
Philipp Reisner 已提交
362
		list_for_each_safe(le, tle, &b->requests) {
363 364 365 366 367
			req = list_entry(le, struct drbd_request, tl_requests);
			rv = _req_mod(req, what);

			n_writes += (rv & MR_WRITE) >> MR_WRITE_SHIFT;
			n_reads  += (rv & MR_READ) >> MR_READ_SHIFT;
P
Philipp Reisner 已提交
368 369 370
		}
		tmp = b->next;

371
		if (n_writes) {
372 373 374 375 376 377 378 379 380 381 382 383
			if (what == resend) {
				b->n_writes = n_writes;
				if (b->w.cb == NULL) {
					b->w.cb = w_send_barrier;
					inc_ap_pending(mdev);
					set_bit(CREATE_BARRIER, &mdev->flags);
				}

				drbd_queue_work(&mdev->data.work, &b->w);
			}
			pn = &b->next;
		} else {
384 385
			if (n_reads)
				list_add(&carry_reads, &b->requests);
386 387 388 389 390 391 392 393 394 395 396 397 398 399
			/* there could still be requests on that ring list,
			 * in case local io is still pending */
			list_del(&b->requests);

			/* dec_ap_pending corresponding to queue_barrier.
			 * the newest barrier may not have been queued yet,
			 * in which case w.cb is still NULL. */
			if (b->w.cb != NULL)
				dec_ap_pending(mdev);

			if (b == mdev->newest_tle) {
				/* recycle, but reinit! */
				D_ASSERT(tmp == NULL);
				INIT_LIST_HEAD(&b->requests);
400
				list_splice(&carry_reads, &b->requests);
401 402 403 404 405 406 407 408 409 410
				INIT_LIST_HEAD(&b->w.list);
				b->w.cb = NULL;
				b->br_number = net_random();
				b->n_writes = 0;

				*pn = b;
				break;
			}
			*pn = tmp;
			kfree(b);
P
Philipp Reisner 已提交
411 412
		}
		b = tmp;
413
		list_splice(&carry_reads, &b->requests);
P
Philipp Reisner 已提交
414
	}
415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431

	/* Actions operating on the disk state, also want to work on
	   requests that got barrier acked. */
	switch (what) {
	case fail_frozen_disk_io:
	case restart_frozen_disk_io:
		list_for_each_safe(le, tle, &mdev->barrier_acked_requests) {
			req = list_entry(le, struct drbd_request, tl_requests);
			_req_mod(req, what);
		}

	case connection_lost_while_pending:
	case resend:
		break;
	default:
		dev_err(DEV, "what = %d in _tl_restart()\n", what);
	}
432 433
}

P
Philipp Reisner 已提交
434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449

/**
 * tl_clear() - Clears all requests and &struct drbd_tl_epoch objects out of the TL
 * @mdev:	DRBD device.
 *
 * This is called after the connection to the peer was lost. The storage covered
 * by the requests on the transfer gets marked as our of sync. Called from the
 * receiver thread and the worker thread.
 */
void tl_clear(struct drbd_conf *mdev)
{
	struct list_head *le, *tle;
	struct drbd_request *r;

	spin_lock_irq(&mdev->req_lock);

450
	_tl_restart(mdev, connection_lost_while_pending);
P
Philipp Reisner 已提交
451 452 453 454 455 456 457 458 459 460 461 462 463 464 465

	/* we expect this list to be empty. */
	D_ASSERT(list_empty(&mdev->out_of_sequence_requests));

	/* but just in case, clean it up anyways! */
	list_for_each_safe(le, tle, &mdev->out_of_sequence_requests) {
		r = list_entry(le, struct drbd_request, tl_requests);
		/* It would be nice to complete outside of spinlock.
		 * But this is easier for now. */
		_req_mod(r, connection_lost_while_pending);
	}

	/* ensure bit indicating barrier is required is clear */
	clear_bit(CREATE_BARRIER, &mdev->flags);

466 467
	memset(mdev->app_reads_hash, 0, APP_R_HSIZE*sizeof(void *));

P
Philipp Reisner 已提交
468 469 470
	spin_unlock_irq(&mdev->req_lock);
}

471 472 473 474
void tl_restart(struct drbd_conf *mdev, enum drbd_req_event what)
{
	spin_lock_irq(&mdev->req_lock);
	_tl_restart(mdev, what);
P
Philipp Reisner 已提交
475 476 477
	spin_unlock_irq(&mdev->req_lock);
}

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
/**
 * tl_abort_disk_io() - Abort disk I/O for all requests for a certain mdev in the TL
 * @mdev:	DRBD device.
 */
void tl_abort_disk_io(struct drbd_conf *mdev)
{
	struct drbd_tl_epoch *b;
	struct list_head *le, *tle;
	struct drbd_request *req;

	spin_lock_irq(&mdev->req_lock);
	b = mdev->oldest_tle;
	while (b) {
		list_for_each_safe(le, tle, &b->requests) {
			req = list_entry(le, struct drbd_request, tl_requests);
			if (!(req->rq_state & RQ_LOCAL_PENDING))
				continue;
			_req_mod(req, abort_disk_io);
		}
		b = b->next;
	}

	list_for_each_safe(le, tle, &mdev->barrier_acked_requests) {
		req = list_entry(le, struct drbd_request, tl_requests);
		if (!(req->rq_state & RQ_LOCAL_PENDING))
			continue;
		_req_mod(req, abort_disk_io);
	}

	spin_unlock_irq(&mdev->req_lock);
}

P
Philipp Reisner 已提交
510
/**
511
 * cl_wide_st_chg() - true if the state change is a cluster wide one
P
Philipp Reisner 已提交
512 513 514 515 516 517 518 519 520 521 522
 * @mdev:	DRBD device.
 * @os:		old (current) state.
 * @ns:		new (wanted) state.
 */
static int cl_wide_st_chg(struct drbd_conf *mdev,
			  union drbd_state os, union drbd_state ns)
{
	return (os.conn >= C_CONNECTED && ns.conn >= C_CONNECTED &&
		 ((os.role != R_PRIMARY && ns.role == R_PRIMARY) ||
		  (os.conn != C_STARTING_SYNC_T && ns.conn == C_STARTING_SYNC_T) ||
		  (os.conn != C_STARTING_SYNC_S && ns.conn == C_STARTING_SYNC_S) ||
523
		  (os.disk != D_FAILED && ns.disk == D_FAILED))) ||
P
Philipp Reisner 已提交
524 525 526 527
		(os.conn >= C_CONNECTED && ns.conn == C_DISCONNECTING) ||
		(os.conn == C_CONNECTED && ns.conn == C_VERIFY_S);
}

528 529 530
enum drbd_state_rv
drbd_change_state(struct drbd_conf *mdev, enum chg_state_flags f,
		  union drbd_state mask, union drbd_state val)
P
Philipp Reisner 已提交
531 532 533
{
	unsigned long flags;
	union drbd_state os, ns;
534
	enum drbd_state_rv rv;
P
Philipp Reisner 已提交
535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557

	spin_lock_irqsave(&mdev->req_lock, flags);
	os = mdev->state;
	ns.i = (os.i & ~mask.i) | val.i;
	rv = _drbd_set_state(mdev, ns, f, NULL);
	ns = mdev->state;
	spin_unlock_irqrestore(&mdev->req_lock, flags);

	return rv;
}

/**
 * drbd_force_state() - Impose a change which happens outside our control on our state
 * @mdev:	DRBD device.
 * @mask:	mask of state bits to change.
 * @val:	value of new state bits.
 */
void drbd_force_state(struct drbd_conf *mdev,
	union drbd_state mask, union drbd_state val)
{
	drbd_change_state(mdev, CS_HARD, mask, val);
}

558 559 560 561
static enum drbd_state_rv is_valid_state(struct drbd_conf *, union drbd_state);
static enum drbd_state_rv is_valid_state_transition(struct drbd_conf *,
						    union drbd_state,
						    union drbd_state);
562 563 564 565 566 567 568 569
enum sanitize_state_warnings {
	NO_WARNING,
	ABORTED_ONLINE_VERIFY,
	ABORTED_RESYNC,
	CONNECTION_LOST_NEGOTIATING,
	IMPLICITLY_UPGRADED_DISK,
	IMPLICITLY_UPGRADED_PDSK,
};
P
Philipp Reisner 已提交
570
static union drbd_state sanitize_state(struct drbd_conf *mdev, union drbd_state os,
571
				       union drbd_state ns, enum sanitize_state_warnings *warn);
P
Philipp Reisner 已提交
572 573 574
int drbd_send_state_req(struct drbd_conf *,
			union drbd_state, union drbd_state);

575 576 577
static enum drbd_state_rv
_req_st_cond(struct drbd_conf *mdev, union drbd_state mask,
	     union drbd_state val)
P
Philipp Reisner 已提交
578 579 580
{
	union drbd_state os, ns;
	unsigned long flags;
581
	enum drbd_state_rv rv;
P
Philipp Reisner 已提交
582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601

	if (test_and_clear_bit(CL_ST_CHG_SUCCESS, &mdev->flags))
		return SS_CW_SUCCESS;

	if (test_and_clear_bit(CL_ST_CHG_FAIL, &mdev->flags))
		return SS_CW_FAILED_BY_PEER;

	rv = 0;
	spin_lock_irqsave(&mdev->req_lock, flags);
	os = mdev->state;
	ns.i = (os.i & ~mask.i) | val.i;
	ns = sanitize_state(mdev, os, ns, NULL);

	if (!cl_wide_st_chg(mdev, os, ns))
		rv = SS_CW_NO_NEED;
	if (!rv) {
		rv = is_valid_state(mdev, ns);
		if (rv == SS_SUCCESS) {
			rv = is_valid_state_transition(mdev, ns, os);
			if (rv == SS_SUCCESS)
602
				rv = SS_UNKNOWN_ERROR; /* cont waiting, otherwise fail. */
P
Philipp Reisner 已提交
603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619
		}
	}
	spin_unlock_irqrestore(&mdev->req_lock, flags);

	return rv;
}

/**
 * drbd_req_state() - Perform an eventually cluster wide state change
 * @mdev:	DRBD device.
 * @mask:	mask of state bits to change.
 * @val:	value of new state bits.
 * @f:		flags
 *
 * Should not be called directly, use drbd_request_state() or
 * _drbd_request_state().
 */
620 621 622
static enum drbd_state_rv
drbd_req_state(struct drbd_conf *mdev, union drbd_state mask,
	       union drbd_state val, enum chg_state_flags f)
P
Philipp Reisner 已提交
623 624 625 626
{
	struct completion done;
	unsigned long flags;
	union drbd_state os, ns;
627
	enum drbd_state_rv rv;
P
Philipp Reisner 已提交
628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701

	init_completion(&done);

	if (f & CS_SERIALIZE)
		mutex_lock(&mdev->state_mutex);

	spin_lock_irqsave(&mdev->req_lock, flags);
	os = mdev->state;
	ns.i = (os.i & ~mask.i) | val.i;
	ns = sanitize_state(mdev, os, ns, NULL);

	if (cl_wide_st_chg(mdev, os, ns)) {
		rv = is_valid_state(mdev, ns);
		if (rv == SS_SUCCESS)
			rv = is_valid_state_transition(mdev, ns, os);
		spin_unlock_irqrestore(&mdev->req_lock, flags);

		if (rv < SS_SUCCESS) {
			if (f & CS_VERBOSE)
				print_st_err(mdev, os, ns, rv);
			goto abort;
		}

		drbd_state_lock(mdev);
		if (!drbd_send_state_req(mdev, mask, val)) {
			drbd_state_unlock(mdev);
			rv = SS_CW_FAILED_BY_PEER;
			if (f & CS_VERBOSE)
				print_st_err(mdev, os, ns, rv);
			goto abort;
		}

		wait_event(mdev->state_wait,
			(rv = _req_st_cond(mdev, mask, val)));

		if (rv < SS_SUCCESS) {
			drbd_state_unlock(mdev);
			if (f & CS_VERBOSE)
				print_st_err(mdev, os, ns, rv);
			goto abort;
		}
		spin_lock_irqsave(&mdev->req_lock, flags);
		os = mdev->state;
		ns.i = (os.i & ~mask.i) | val.i;
		rv = _drbd_set_state(mdev, ns, f, &done);
		drbd_state_unlock(mdev);
	} else {
		rv = _drbd_set_state(mdev, ns, f, &done);
	}

	spin_unlock_irqrestore(&mdev->req_lock, flags);

	if (f & CS_WAIT_COMPLETE && rv == SS_SUCCESS) {
		D_ASSERT(current != mdev->worker.task);
		wait_for_completion(&done);
	}

abort:
	if (f & CS_SERIALIZE)
		mutex_unlock(&mdev->state_mutex);

	return rv;
}

/**
 * _drbd_request_state() - Request a state change (with flags)
 * @mdev:	DRBD device.
 * @mask:	mask of state bits to change.
 * @val:	value of new state bits.
 * @f:		flags
 *
 * Cousin of drbd_request_state(), useful with the CS_WAIT_COMPLETE
 * flag, or when logging of failed state change requests is not desired.
 */
702 703 704
enum drbd_state_rv
_drbd_request_state(struct drbd_conf *mdev, union drbd_state mask,
		    union drbd_state val, enum chg_state_flags f)
P
Philipp Reisner 已提交
705
{
706
	enum drbd_state_rv rv;
P
Philipp Reisner 已提交
707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722

	wait_event(mdev->state_wait,
		   (rv = drbd_req_state(mdev, mask, val, f)) != SS_IN_TRANSIENT_STATE);

	return rv;
}

static void print_st(struct drbd_conf *mdev, char *name, union drbd_state ns)
{
	dev_err(DEV, " %s = { cs:%s ro:%s/%s ds:%s/%s %c%c%c%c }\n",
	    name,
	    drbd_conn_str(ns.conn),
	    drbd_role_str(ns.role),
	    drbd_role_str(ns.peer),
	    drbd_disk_str(ns.disk),
	    drbd_disk_str(ns.pdsk),
723
	    is_susp(ns) ? 's' : 'r',
P
Philipp Reisner 已提交
724 725 726 727 728 729
	    ns.aftr_isp ? 'a' : '-',
	    ns.peer_isp ? 'p' : '-',
	    ns.user_isp ? 'u' : '-'
	    );
}

730 731
void print_st_err(struct drbd_conf *mdev, union drbd_state os,
	          union drbd_state ns, enum drbd_state_rv err)
P
Philipp Reisner 已提交
732 733 734 735 736 737 738 739 740 741 742 743 744 745
{
	if (err == SS_IN_TRANSIENT_STATE)
		return;
	dev_err(DEV, "State change failed: %s\n", drbd_set_st_err_str(err));
	print_st(mdev, " state", os);
	print_st(mdev, "wanted", ns);
}


/**
 * is_valid_state() - Returns an SS_ error code if ns is not valid
 * @mdev:	DRBD device.
 * @ns:		State to consider.
 */
746 747
static enum drbd_state_rv
is_valid_state(struct drbd_conf *mdev, union drbd_state ns)
P
Philipp Reisner 已提交
748 749 750 751
{
	/* See drbd_state_sw_errors in drbd_strings.c */

	enum drbd_fencing_p fp;
752
	enum drbd_state_rv rv = SS_SUCCESS;
P
Philipp Reisner 已提交
753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787

	fp = FP_DONT_CARE;
	if (get_ldev(mdev)) {
		fp = mdev->ldev->dc.fencing;
		put_ldev(mdev);
	}

	if (get_net_conf(mdev)) {
		if (!mdev->net_conf->two_primaries &&
		    ns.role == R_PRIMARY && ns.peer == R_PRIMARY)
			rv = SS_TWO_PRIMARIES;
		put_net_conf(mdev);
	}

	if (rv <= 0)
		/* already found a reason to abort */;
	else if (ns.role == R_SECONDARY && mdev->open_cnt)
		rv = SS_DEVICE_IN_USE;

	else if (ns.role == R_PRIMARY && ns.conn < C_CONNECTED && ns.disk < D_UP_TO_DATE)
		rv = SS_NO_UP_TO_DATE_DISK;

	else if (fp >= FP_RESOURCE &&
		 ns.role == R_PRIMARY && ns.conn < C_CONNECTED && ns.pdsk >= D_UNKNOWN)
		rv = SS_PRIMARY_NOP;

	else if (ns.role == R_PRIMARY && ns.disk <= D_INCONSISTENT && ns.pdsk <= D_INCONSISTENT)
		rv = SS_NO_UP_TO_DATE_DISK;

	else if (ns.conn > C_CONNECTED && ns.disk < D_INCONSISTENT)
		rv = SS_NO_LOCAL_DISK;

	else if (ns.conn > C_CONNECTED && ns.pdsk < D_INCONSISTENT)
		rv = SS_NO_REMOTE_DISK;

788 789 790
	else if (ns.conn > C_CONNECTED && ns.disk < D_UP_TO_DATE && ns.pdsk < D_UP_TO_DATE)
		rv = SS_NO_UP_TO_DATE_DISK;

P
Philipp Reisner 已提交
791 792 793 794 795 796 797 798 799 800 801 802 803 804 805
	else if ((ns.conn == C_CONNECTED ||
		  ns.conn == C_WF_BITMAP_S ||
		  ns.conn == C_SYNC_SOURCE ||
		  ns.conn == C_PAUSED_SYNC_S) &&
		  ns.disk == D_OUTDATED)
		rv = SS_CONNECTED_OUTDATES;

	else if ((ns.conn == C_VERIFY_S || ns.conn == C_VERIFY_T) &&
		 (mdev->sync_conf.verify_alg[0] == 0))
		rv = SS_NO_VERIFY_ALG;

	else if ((ns.conn == C_VERIFY_S || ns.conn == C_VERIFY_T) &&
		  mdev->agreed_pro_version < 88)
		rv = SS_NOT_SUPPORTED;

806 807 808
	else if (ns.conn >= C_CONNECTED && ns.pdsk == D_UNKNOWN)
		rv = SS_CONNECTED_OUTDATES;

P
Philipp Reisner 已提交
809 810 811 812 813 814 815 816 817
	return rv;
}

/**
 * is_valid_state_transition() - Returns an SS_ error code if the state transition is not possible
 * @mdev:	DRBD device.
 * @ns:		new state.
 * @os:		old state.
 */
818 819 820
static enum drbd_state_rv
is_valid_state_transition(struct drbd_conf *mdev, union drbd_state ns,
			  union drbd_state os)
P
Philipp Reisner 已提交
821
{
822
	enum drbd_state_rv rv = SS_SUCCESS;
P
Philipp Reisner 已提交
823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856

	if ((ns.conn == C_STARTING_SYNC_T || ns.conn == C_STARTING_SYNC_S) &&
	    os.conn > C_CONNECTED)
		rv = SS_RESYNC_RUNNING;

	if (ns.conn == C_DISCONNECTING && os.conn == C_STANDALONE)
		rv = SS_ALREADY_STANDALONE;

	if (ns.disk > D_ATTACHING && os.disk == D_DISKLESS)
		rv = SS_IS_DISKLESS;

	if (ns.conn == C_WF_CONNECTION && os.conn < C_UNCONNECTED)
		rv = SS_NO_NET_CONFIG;

	if (ns.disk == D_OUTDATED && os.disk < D_OUTDATED && os.disk != D_ATTACHING)
		rv = SS_LOWER_THAN_OUTDATED;

	if (ns.conn == C_DISCONNECTING && os.conn == C_UNCONNECTED)
		rv = SS_IN_TRANSIENT_STATE;

	if (ns.conn == os.conn && ns.conn == C_WF_REPORT_PARAMS)
		rv = SS_IN_TRANSIENT_STATE;

	if ((ns.conn == C_VERIFY_S || ns.conn == C_VERIFY_T) && os.conn < C_CONNECTED)
		rv = SS_NEED_CONNECTION;

	if ((ns.conn == C_VERIFY_S || ns.conn == C_VERIFY_T) &&
	    ns.conn != os.conn && os.conn > C_CONNECTED)
		rv = SS_RESYNC_RUNNING;

	if ((ns.conn == C_STARTING_SYNC_S || ns.conn == C_STARTING_SYNC_T) &&
	    os.conn < C_CONNECTED)
		rv = SS_NEED_CONNECTION;

857 858 859 860
	if ((ns.conn == C_SYNC_TARGET || ns.conn == C_SYNC_SOURCE)
	    && os.conn < C_WF_REPORT_PARAMS)
		rv = SS_NEED_CONNECTION; /* No NetworkFailure -> SyncTarget etc... */

P
Philipp Reisner 已提交
861 862 863
	return rv;
}

864 865 866 867 868 869 870 871 872 873 874 875 876 877 878
static void print_sanitize_warnings(struct drbd_conf *mdev, enum sanitize_state_warnings warn)
{
	static const char *msg_table[] = {
		[NO_WARNING] = "",
		[ABORTED_ONLINE_VERIFY] = "Online-verify aborted.",
		[ABORTED_RESYNC] = "Resync aborted.",
		[CONNECTION_LOST_NEGOTIATING] = "Connection lost while negotiating, no data!",
		[IMPLICITLY_UPGRADED_DISK] = "Implicitly upgraded disk",
		[IMPLICITLY_UPGRADED_PDSK] = "Implicitly upgraded pdsk",
	};

	if (warn != NO_WARNING)
		dev_warn(DEV, "%s\n", msg_table[warn]);
}

P
Philipp Reisner 已提交
879 880 881 882 883 884 885 886 887 888 889
/**
 * sanitize_state() - Resolves implicitly necessary additional changes to a state transition
 * @mdev:	DRBD device.
 * @os:		old state.
 * @ns:		new state.
 * @warn_sync_abort:
 *
 * When we loose connection, we have to set the state of the peers disk (pdsk)
 * to D_UNKNOWN. This rule and many more along those lines are in this function.
 */
static union drbd_state sanitize_state(struct drbd_conf *mdev, union drbd_state os,
890
				       union drbd_state ns, enum sanitize_state_warnings *warn)
P
Philipp Reisner 已提交
891 892
{
	enum drbd_fencing_p fp;
893
	enum drbd_disk_state disk_min, disk_max, pdsk_min, pdsk_max;
P
Philipp Reisner 已提交
894

895 896 897
	if (warn)
		*warn = NO_WARNING;

P
Philipp Reisner 已提交
898 899 900 901 902 903 904 905 906 907 908
	fp = FP_DONT_CARE;
	if (get_ldev(mdev)) {
		fp = mdev->ldev->dc.fencing;
		put_ldev(mdev);
	}

	/* Disallow Network errors to configure a device's network part */
	if ((ns.conn >= C_TIMEOUT && ns.conn <= C_TEAR_DOWN) &&
	    os.conn <= C_DISCONNECTING)
		ns.conn = os.conn;

909 910
	/* After a network error (+C_TEAR_DOWN) only C_UNCONNECTED or C_DISCONNECTING can follow.
	 * If you try to go into some Sync* state, that shall fail (elsewhere). */
P
Philipp Reisner 已提交
911
	if (os.conn >= C_TIMEOUT && os.conn <= C_TEAR_DOWN &&
912
	    ns.conn != C_UNCONNECTED && ns.conn != C_DISCONNECTING && ns.conn <= C_TEAR_DOWN)
P
Philipp Reisner 已提交
913 914
		ns.conn = os.conn;

915 916 917 918 919 920 921 922 923
	/* we cannot fail (again) if we already detached */
	if (ns.disk == D_FAILED && os.disk == D_DISKLESS)
		ns.disk = D_DISKLESS;

	/* if we are only D_ATTACHING yet,
	 * we can (and should) go directly to D_DISKLESS. */
	if (ns.disk == D_FAILED && os.disk == D_ATTACHING)
		ns.disk = D_DISKLESS;

P
Philipp Reisner 已提交
924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941
	/* After C_DISCONNECTING only C_STANDALONE may follow */
	if (os.conn == C_DISCONNECTING && ns.conn != C_STANDALONE)
		ns.conn = os.conn;

	if (ns.conn < C_CONNECTED) {
		ns.peer_isp = 0;
		ns.peer = R_UNKNOWN;
		if (ns.pdsk > D_UNKNOWN || ns.pdsk < D_INCONSISTENT)
			ns.pdsk = D_UNKNOWN;
	}

	/* Clear the aftr_isp when becoming unconfigured */
	if (ns.conn == C_STANDALONE && ns.disk == D_DISKLESS && ns.role == R_SECONDARY)
		ns.aftr_isp = 0;

	/* Abort resync if a disk fails/detaches */
	if (os.conn > C_CONNECTED && ns.conn > C_CONNECTED &&
	    (ns.disk <= D_FAILED || ns.pdsk <= D_FAILED)) {
942 943 944
		if (warn)
			*warn =	os.conn == C_VERIFY_S || os.conn == C_VERIFY_T ?
				ABORTED_ONLINE_VERIFY : ABORTED_RESYNC;
P
Philipp Reisner 已提交
945 946 947 948 949 950 951 952 953 954
		ns.conn = C_CONNECTED;
	}

	/* Connection breaks down before we finished "Negotiating" */
	if (ns.conn < C_CONNECTED && ns.disk == D_NEGOTIATING &&
	    get_ldev_if_state(mdev, D_NEGOTIATING)) {
		if (mdev->ed_uuid == mdev->ldev->md.uuid[UI_CURRENT]) {
			ns.disk = mdev->new_state_tmp.disk;
			ns.pdsk = mdev->new_state_tmp.pdsk;
		} else {
955 956
			if (warn)
				*warn = CONNECTION_LOST_NEGOTIATING;
P
Philipp Reisner 已提交
957 958 959 960 961 962
			ns.disk = D_DISKLESS;
			ns.pdsk = D_UNKNOWN;
		}
		put_ldev(mdev);
	}

963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037
	/* D_CONSISTENT and D_OUTDATED vanish when we get connected */
	if (ns.conn >= C_CONNECTED && ns.conn < C_AHEAD) {
		if (ns.disk == D_CONSISTENT || ns.disk == D_OUTDATED)
			ns.disk = D_UP_TO_DATE;
		if (ns.pdsk == D_CONSISTENT || ns.pdsk == D_OUTDATED)
			ns.pdsk = D_UP_TO_DATE;
	}

	/* Implications of the connection stat on the disk states */
	disk_min = D_DISKLESS;
	disk_max = D_UP_TO_DATE;
	pdsk_min = D_INCONSISTENT;
	pdsk_max = D_UNKNOWN;
	switch ((enum drbd_conns)ns.conn) {
	case C_WF_BITMAP_T:
	case C_PAUSED_SYNC_T:
	case C_STARTING_SYNC_T:
	case C_WF_SYNC_UUID:
	case C_BEHIND:
		disk_min = D_INCONSISTENT;
		disk_max = D_OUTDATED;
		pdsk_min = D_UP_TO_DATE;
		pdsk_max = D_UP_TO_DATE;
		break;
	case C_VERIFY_S:
	case C_VERIFY_T:
		disk_min = D_UP_TO_DATE;
		disk_max = D_UP_TO_DATE;
		pdsk_min = D_UP_TO_DATE;
		pdsk_max = D_UP_TO_DATE;
		break;
	case C_CONNECTED:
		disk_min = D_DISKLESS;
		disk_max = D_UP_TO_DATE;
		pdsk_min = D_DISKLESS;
		pdsk_max = D_UP_TO_DATE;
		break;
	case C_WF_BITMAP_S:
	case C_PAUSED_SYNC_S:
	case C_STARTING_SYNC_S:
	case C_AHEAD:
		disk_min = D_UP_TO_DATE;
		disk_max = D_UP_TO_DATE;
		pdsk_min = D_INCONSISTENT;
		pdsk_max = D_CONSISTENT; /* D_OUTDATED would be nice. But explicit outdate necessary*/
		break;
	case C_SYNC_TARGET:
		disk_min = D_INCONSISTENT;
		disk_max = D_INCONSISTENT;
		pdsk_min = D_UP_TO_DATE;
		pdsk_max = D_UP_TO_DATE;
		break;
	case C_SYNC_SOURCE:
		disk_min = D_UP_TO_DATE;
		disk_max = D_UP_TO_DATE;
		pdsk_min = D_INCONSISTENT;
		pdsk_max = D_INCONSISTENT;
		break;
	case C_STANDALONE:
	case C_DISCONNECTING:
	case C_UNCONNECTED:
	case C_TIMEOUT:
	case C_BROKEN_PIPE:
	case C_NETWORK_FAILURE:
	case C_PROTOCOL_ERROR:
	case C_TEAR_DOWN:
	case C_WF_CONNECTION:
	case C_WF_REPORT_PARAMS:
	case C_MASK:
		break;
	}
	if (ns.disk > disk_max)
		ns.disk = disk_max;

	if (ns.disk < disk_min) {
1038 1039
		if (warn)
			*warn = IMPLICITLY_UPGRADED_DISK;
1040 1041 1042 1043 1044 1045
		ns.disk = disk_min;
	}
	if (ns.pdsk > pdsk_max)
		ns.pdsk = pdsk_max;

	if (ns.pdsk < pdsk_min) {
1046 1047
		if (warn)
			*warn = IMPLICITLY_UPGRADED_PDSK;
1048 1049 1050
		ns.pdsk = pdsk_min;
	}

P
Philipp Reisner 已提交
1051
	if (fp == FP_STONITH &&
1052 1053
	    (ns.role == R_PRIMARY && ns.conn < C_CONNECTED && ns.pdsk > D_OUTDATED) &&
	    !(os.role == R_PRIMARY && os.conn < C_CONNECTED && os.pdsk > D_OUTDATED))
1054
		ns.susp_fen = 1; /* Suspend IO while fence-peer handler runs (peer lost) */
1055 1056 1057 1058

	if (mdev->sync_conf.on_no_data == OND_SUSPEND_IO &&
	    (ns.role == R_PRIMARY && ns.disk < D_UP_TO_DATE && ns.pdsk < D_UP_TO_DATE) &&
	    !(os.role == R_PRIMARY && os.disk < D_UP_TO_DATE && os.pdsk < D_UP_TO_DATE))
1059
		ns.susp_nod = 1; /* Suspend IO while no data available (no accessible data available) */
P
Philipp Reisner 已提交
1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078

	if (ns.aftr_isp || ns.peer_isp || ns.user_isp) {
		if (ns.conn == C_SYNC_SOURCE)
			ns.conn = C_PAUSED_SYNC_S;
		if (ns.conn == C_SYNC_TARGET)
			ns.conn = C_PAUSED_SYNC_T;
	} else {
		if (ns.conn == C_PAUSED_SYNC_S)
			ns.conn = C_SYNC_SOURCE;
		if (ns.conn == C_PAUSED_SYNC_T)
			ns.conn = C_SYNC_TARGET;
	}

	return ns;
}

/* helper for __drbd_set_state */
static void set_ov_position(struct drbd_conf *mdev, enum drbd_conns cs)
{
1079 1080 1081 1082
	if (mdev->agreed_pro_version < 90)
		mdev->ov_start_sector = 0;
	mdev->rs_total = drbd_bm_bits(mdev);
	mdev->ov_position = 0;
P
Philipp Reisner 已提交
1083 1084 1085 1086 1087 1088 1089 1090 1091
	if (cs == C_VERIFY_T) {
		/* starting online verify from an arbitrary position
		 * does not fit well into the existing protocol.
		 * on C_VERIFY_T, we initialize ov_left and friends
		 * implicitly in receive_DataRequest once the
		 * first P_OV_REQUEST is received */
		mdev->ov_start_sector = ~(sector_t)0;
	} else {
		unsigned long bit = BM_SECT_TO_BIT(mdev->ov_start_sector);
1092
		if (bit >= mdev->rs_total) {
P
Philipp Reisner 已提交
1093 1094
			mdev->ov_start_sector =
				BM_BIT_TO_SECT(mdev->rs_total - 1);
1095 1096 1097
			mdev->rs_total = 1;
		} else
			mdev->rs_total -= bit;
P
Philipp Reisner 已提交
1098 1099
		mdev->ov_position = mdev->ov_start_sector;
	}
1100
	mdev->ov_left = mdev->rs_total;
P
Philipp Reisner 已提交
1101 1102
}

1103 1104 1105 1106 1107 1108
static void drbd_resume_al(struct drbd_conf *mdev)
{
	if (test_and_clear_bit(AL_SUSPENDED, &mdev->flags))
		dev_info(DEV, "Resumed AL updates\n");
}

P
Philipp Reisner 已提交
1109 1110 1111 1112 1113 1114 1115 1116 1117
/**
 * __drbd_set_state() - Set a new DRBD state
 * @mdev:	DRBD device.
 * @ns:		new state.
 * @flags:	Flags
 * @done:	Optional completion, that will get completed after the after_state_ch() finished
 *
 * Caller needs to hold req_lock, and global_state_lock. Do not call directly.
 */
1118 1119 1120
enum drbd_state_rv
__drbd_set_state(struct drbd_conf *mdev, union drbd_state ns,
	         enum chg_state_flags flags, struct completion *done)
P
Philipp Reisner 已提交
1121 1122
{
	union drbd_state os;
1123
	enum drbd_state_rv rv = SS_SUCCESS;
1124
	enum sanitize_state_warnings ssw;
P
Philipp Reisner 已提交
1125 1126 1127 1128
	struct after_state_chg_work *ascw;

	os = mdev->state;

1129
	ns = sanitize_state(mdev, os, ns, &ssw);
P
Philipp Reisner 已提交
1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142

	if (ns.i == os.i)
		return SS_NOTHING_TO_DO;

	if (!(flags & CS_HARD)) {
		/*  pre-state-change checks ; only look at ns  */
		/* See drbd_state_sw_errors in drbd_strings.c */

		rv = is_valid_state(mdev, ns);
		if (rv < SS_SUCCESS) {
			/* If the old state was illegal as well, then let
			   this happen...*/

1143
			if (is_valid_state(mdev, os) == rv)
P
Philipp Reisner 已提交
1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154
				rv = is_valid_state_transition(mdev, ns, os);
		} else
			rv = is_valid_state_transition(mdev, ns, os);
	}

	if (rv < SS_SUCCESS) {
		if (flags & CS_VERBOSE)
			print_st_err(mdev, os, ns, rv);
		return rv;
	}

1155
	print_sanitize_warnings(mdev, ssw);
P
Philipp Reisner 已提交
1156 1157

	{
1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197
	char *pbp, pb[300];
	pbp = pb;
	*pbp = 0;
	if (ns.role != os.role)
		pbp += sprintf(pbp, "role( %s -> %s ) ",
			       drbd_role_str(os.role),
			       drbd_role_str(ns.role));
	if (ns.peer != os.peer)
		pbp += sprintf(pbp, "peer( %s -> %s ) ",
			       drbd_role_str(os.peer),
			       drbd_role_str(ns.peer));
	if (ns.conn != os.conn)
		pbp += sprintf(pbp, "conn( %s -> %s ) ",
			       drbd_conn_str(os.conn),
			       drbd_conn_str(ns.conn));
	if (ns.disk != os.disk)
		pbp += sprintf(pbp, "disk( %s -> %s ) ",
			       drbd_disk_str(os.disk),
			       drbd_disk_str(ns.disk));
	if (ns.pdsk != os.pdsk)
		pbp += sprintf(pbp, "pdsk( %s -> %s ) ",
			       drbd_disk_str(os.pdsk),
			       drbd_disk_str(ns.pdsk));
	if (is_susp(ns) != is_susp(os))
		pbp += sprintf(pbp, "susp( %d -> %d ) ",
			       is_susp(os),
			       is_susp(ns));
	if (ns.aftr_isp != os.aftr_isp)
		pbp += sprintf(pbp, "aftr_isp( %d -> %d ) ",
			       os.aftr_isp,
			       ns.aftr_isp);
	if (ns.peer_isp != os.peer_isp)
		pbp += sprintf(pbp, "peer_isp( %d -> %d ) ",
			       os.peer_isp,
			       ns.peer_isp);
	if (ns.user_isp != os.user_isp)
		pbp += sprintf(pbp, "user_isp( %d -> %d ) ",
			       os.user_isp,
			       ns.user_isp);
	dev_info(DEV, "%s\n", pb);
P
Philipp Reisner 已提交
1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213
	}

	/* solve the race between becoming unconfigured,
	 * worker doing the cleanup, and
	 * admin reconfiguring us:
	 * on (re)configure, first set CONFIG_PENDING,
	 * then wait for a potentially exiting worker,
	 * start the worker, and schedule one no_op.
	 * then proceed with configuration.
	 */
	if (ns.disk == D_DISKLESS &&
	    ns.conn == C_STANDALONE &&
	    ns.role == R_SECONDARY &&
	    !test_and_set_bit(CONFIG_PENDING, &mdev->flags))
		set_bit(DEVICE_DYING, &mdev->flags);

1214 1215 1216 1217 1218 1219 1220 1221 1222
	/* if we are going -> D_FAILED or D_DISKLESS, grab one extra reference
	 * on the ldev here, to be sure the transition -> D_DISKLESS resp.
	 * drbd_ldev_destroy() won't happen before our corresponding
	 * after_state_ch works run, where we put_ldev again. */
	if ((os.disk != D_FAILED && ns.disk == D_FAILED) ||
	    (os.disk != D_DISKLESS && ns.disk == D_DISKLESS))
		atomic_inc(&mdev->local_cnt);

	mdev->state = ns;
1223 1224 1225 1226

	if (os.disk == D_ATTACHING && ns.disk >= D_NEGOTIATING)
		drbd_print_uuids(mdev, "attached to UUIDs");

P
Philipp Reisner 已提交
1227 1228 1229 1230 1231 1232 1233
	wake_up(&mdev->misc_wait);
	wake_up(&mdev->state_wait);

	/* aborted verify run. log the last position */
	if ((os.conn == C_VERIFY_S || os.conn == C_VERIFY_T) &&
	    ns.conn < C_CONNECTED) {
		mdev->ov_start_sector =
1234
			BM_BIT_TO_SECT(drbd_bm_bits(mdev) - mdev->ov_left);
P
Philipp Reisner 已提交
1235 1236 1237 1238 1239 1240 1241
		dev_info(DEV, "Online Verify reached sector %llu\n",
			(unsigned long long)mdev->ov_start_sector);
	}

	if ((os.conn == C_PAUSED_SYNC_T || os.conn == C_PAUSED_SYNC_S) &&
	    (ns.conn == C_SYNC_TARGET  || ns.conn == C_SYNC_SOURCE)) {
		dev_info(DEV, "Syncer continues.\n");
1242 1243
		mdev->rs_paused += (long)jiffies
				  -(long)mdev->rs_mark_time[mdev->rs_last_mark];
1244 1245
		if (ns.conn == C_SYNC_TARGET)
			mod_timer(&mdev->resync_timer, jiffies);
P
Philipp Reisner 已提交
1246 1247 1248 1249 1250
	}

	if ((os.conn == C_SYNC_TARGET  || os.conn == C_SYNC_SOURCE) &&
	    (ns.conn == C_PAUSED_SYNC_T || ns.conn == C_PAUSED_SYNC_S)) {
		dev_info(DEV, "Resync suspended\n");
1251
		mdev->rs_mark_time[mdev->rs_last_mark] = jiffies;
P
Philipp Reisner 已提交
1252 1253 1254 1255
	}

	if (os.conn == C_CONNECTED &&
	    (ns.conn == C_VERIFY_S || ns.conn == C_VERIFY_T)) {
1256 1257 1258
		unsigned long now = jiffies;
		int i;

1259
		set_ov_position(mdev, ns.conn);
1260
		mdev->rs_start = now;
1261 1262
		mdev->rs_last_events = 0;
		mdev->rs_last_sect_ev = 0;
P
Philipp Reisner 已提交
1263 1264 1265
		mdev->ov_last_oos_size = 0;
		mdev->ov_last_oos_start = 0;

1266
		for (i = 0; i < DRBD_SYNC_MARKS; i++) {
1267
			mdev->rs_mark_left[i] = mdev->ov_left;
1268 1269 1270
			mdev->rs_mark_time[i] = now;
		}

1271 1272
		drbd_rs_controller_reset(mdev);

P
Philipp Reisner 已提交
1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320
		if (ns.conn == C_VERIFY_S) {
			dev_info(DEV, "Starting Online Verify from sector %llu\n",
					(unsigned long long)mdev->ov_position);
			mod_timer(&mdev->resync_timer, jiffies);
		}
	}

	if (get_ldev(mdev)) {
		u32 mdf = mdev->ldev->md.flags & ~(MDF_CONSISTENT|MDF_PRIMARY_IND|
						 MDF_CONNECTED_IND|MDF_WAS_UP_TO_DATE|
						 MDF_PEER_OUT_DATED|MDF_CRASHED_PRIMARY);

		if (test_bit(CRASHED_PRIMARY, &mdev->flags))
			mdf |= MDF_CRASHED_PRIMARY;
		if (mdev->state.role == R_PRIMARY ||
		    (mdev->state.pdsk < D_INCONSISTENT && mdev->state.peer == R_PRIMARY))
			mdf |= MDF_PRIMARY_IND;
		if (mdev->state.conn > C_WF_REPORT_PARAMS)
			mdf |= MDF_CONNECTED_IND;
		if (mdev->state.disk > D_INCONSISTENT)
			mdf |= MDF_CONSISTENT;
		if (mdev->state.disk > D_OUTDATED)
			mdf |= MDF_WAS_UP_TO_DATE;
		if (mdev->state.pdsk <= D_OUTDATED && mdev->state.pdsk >= D_INCONSISTENT)
			mdf |= MDF_PEER_OUT_DATED;
		if (mdf != mdev->ldev->md.flags) {
			mdev->ldev->md.flags = mdf;
			drbd_md_mark_dirty(mdev);
		}
		if (os.disk < D_CONSISTENT && ns.disk >= D_CONSISTENT)
			drbd_set_ed_uuid(mdev, mdev->ldev->md.uuid[UI_CURRENT]);
		put_ldev(mdev);
	}

	/* Peer was forced D_UP_TO_DATE & R_PRIMARY, consider to resync */
	if (os.disk == D_INCONSISTENT && os.pdsk == D_INCONSISTENT &&
	    os.peer == R_SECONDARY && ns.peer == R_PRIMARY)
		set_bit(CONSIDER_RESYNC, &mdev->flags);

	/* Receiver should clean up itself */
	if (os.conn != C_DISCONNECTING && ns.conn == C_DISCONNECTING)
		drbd_thread_stop_nowait(&mdev->receiver);

	/* Now the receiver finished cleaning up itself, it should die */
	if (os.conn != C_STANDALONE && ns.conn == C_STANDALONE)
		drbd_thread_stop_nowait(&mdev->receiver);

	/* Upon network failure, we need to restart the receiver. */
1321
	if (os.conn > C_WF_CONNECTION &&
P
Philipp Reisner 已提交
1322 1323 1324
	    ns.conn <= C_TEAR_DOWN && ns.conn >= C_TIMEOUT)
		drbd_thread_restart_nowait(&mdev->receiver);

1325 1326 1327 1328
	/* Resume AL writing if we get a connection */
	if (os.conn < C_CONNECTED && ns.conn >= C_CONNECTED)
		drbd_resume_al(mdev);

P
Philipp Reisner 已提交
1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375
	ascw = kmalloc(sizeof(*ascw), GFP_ATOMIC);
	if (ascw) {
		ascw->os = os;
		ascw->ns = ns;
		ascw->flags = flags;
		ascw->w.cb = w_after_state_ch;
		ascw->done = done;
		drbd_queue_work(&mdev->data.work, &ascw->w);
	} else {
		dev_warn(DEV, "Could not kmalloc an ascw\n");
	}

	return rv;
}

static int w_after_state_ch(struct drbd_conf *mdev, struct drbd_work *w, int unused)
{
	struct after_state_chg_work *ascw =
		container_of(w, struct after_state_chg_work, w);
	after_state_ch(mdev, ascw->os, ascw->ns, ascw->flags);
	if (ascw->flags & CS_WAIT_COMPLETE) {
		D_ASSERT(ascw->done != NULL);
		complete(ascw->done);
	}
	kfree(ascw);

	return 1;
}

static void abw_start_sync(struct drbd_conf *mdev, int rv)
{
	if (rv) {
		dev_err(DEV, "Writing the bitmap failed not starting resync.\n");
		_drbd_request_state(mdev, NS(conn, C_CONNECTED), CS_VERBOSE);
		return;
	}

	switch (mdev->state.conn) {
	case C_STARTING_SYNC_T:
		_drbd_request_state(mdev, NS(conn, C_WF_SYNC_UUID), CS_VERBOSE);
		break;
	case C_STARTING_SYNC_S:
		drbd_start_resync(mdev, C_SYNC_SOURCE);
		break;
	}
}

1376 1377 1378
int drbd_bitmap_io_from_worker(struct drbd_conf *mdev,
		int (*io_fn)(struct drbd_conf *),
		char *why, enum bm_flag flags)
1379 1380 1381 1382 1383 1384 1385 1386
{
	int rv;

	D_ASSERT(current == mdev->worker.task);

	/* open coded non-blocking drbd_suspend_io(mdev); */
	set_bit(SUSPEND_IO, &mdev->flags);

1387
	drbd_bm_lock(mdev, why, flags);
1388 1389 1390 1391 1392 1393 1394 1395
	rv = io_fn(mdev);
	drbd_bm_unlock(mdev);

	drbd_resume_io(mdev);

	return rv;
}

P
Philipp Reisner 已提交
1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406
/**
 * after_state_ch() - Perform after state change actions that may sleep
 * @mdev:	DRBD device.
 * @os:		old state.
 * @ns:		new state.
 * @flags:	Flags
 */
static void after_state_ch(struct drbd_conf *mdev, union drbd_state os,
			   union drbd_state ns, enum chg_state_flags flags)
{
	enum drbd_fencing_p fp;
1407
	enum drbd_req_event what = nothing;
1408
	union drbd_state nsm = (union drbd_state){ .i = -1 };
P
Philipp Reisner 已提交
1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431

	if (os.conn != C_CONNECTED && ns.conn == C_CONNECTED) {
		clear_bit(CRASHED_PRIMARY, &mdev->flags);
		if (mdev->p_uuid)
			mdev->p_uuid[UI_FLAGS] &= ~((u64)2);
	}

	fp = FP_DONT_CARE;
	if (get_ldev(mdev)) {
		fp = mdev->ldev->dc.fencing;
		put_ldev(mdev);
	}

	/* Inform userspace about the change... */
	drbd_bcast_state(mdev, ns);

	if (!(os.role == R_PRIMARY && os.disk < D_UP_TO_DATE && os.pdsk < D_UP_TO_DATE) &&
	    (ns.role == R_PRIMARY && ns.disk < D_UP_TO_DATE && ns.pdsk < D_UP_TO_DATE))
		drbd_khelper(mdev, "pri-on-incon-degr");

	/* Here we have the actions that are performed after a
	   state change. This function might sleep */

1432 1433 1434
	if (os.disk <= D_NEGOTIATING && ns.disk > D_NEGOTIATING)
		mod_timer(&mdev->request_timer, jiffies + HZ);

1435 1436
	nsm.i = -1;
	if (ns.susp_nod) {
1437 1438
		if (os.conn < C_CONNECTED && ns.conn >= C_CONNECTED)
			what = resend;
1439

1440 1441
		if ((os.disk == D_ATTACHING || os.disk == D_NEGOTIATING) &&
		    ns.disk > D_NEGOTIATING)
1442
			what = restart_frozen_disk_io;
1443

1444 1445
		if (what != nothing)
			nsm.susp_nod = 0;
1446 1447
	}

1448
	if (ns.susp_fen) {
1449 1450
		/* case1: The outdate peer handler is successful: */
		if (os.pdsk > D_OUTDATED  && ns.pdsk <= D_OUTDATED) {
P
Philipp Reisner 已提交
1451
			tl_clear(mdev);
1452 1453 1454 1455
			if (test_bit(NEW_CUR_UUID, &mdev->flags)) {
				drbd_uuid_new_current(mdev);
				clear_bit(NEW_CUR_UUID, &mdev->flags);
			}
P
Philipp Reisner 已提交
1456
			spin_lock_irq(&mdev->req_lock);
1457
			_drbd_set_state(_NS(mdev, susp_fen, 0), CS_VERBOSE, NULL);
P
Philipp Reisner 已提交
1458 1459
			spin_unlock_irq(&mdev->req_lock);
		}
1460 1461 1462
		/* case2: The connection was established again: */
		if (os.conn < C_CONNECTED && ns.conn >= C_CONNECTED) {
			clear_bit(NEW_CUR_UUID, &mdev->flags);
1463
			what = resend;
1464
			nsm.susp_fen = 0;
1465
		}
P
Philipp Reisner 已提交
1466
	}
1467 1468 1469 1470

	if (what != nothing) {
		spin_lock_irq(&mdev->req_lock);
		_tl_restart(mdev, what);
1471 1472
		nsm.i &= mdev->state.i;
		_drbd_set_state(mdev, nsm, CS_VERBOSE, NULL);
1473
		spin_unlock_irq(&mdev->req_lock);
P
Philipp Reisner 已提交
1474
	}
1475

1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486
	/* Became sync source.  With protocol >= 96, we still need to send out
	 * the sync uuid now. Need to do that before any drbd_send_state, or
	 * the other side may go "paused sync" before receiving the sync uuids,
	 * which is unexpected. */
	if ((os.conn != C_SYNC_SOURCE && os.conn != C_PAUSED_SYNC_S) &&
	    (ns.conn == C_SYNC_SOURCE || ns.conn == C_PAUSED_SYNC_S) &&
	    mdev->agreed_pro_version >= 96 && get_ldev(mdev)) {
		drbd_gen_and_send_sync_uuid(mdev);
		put_ldev(mdev);
	}

P
Philipp Reisner 已提交
1487 1488 1489 1490 1491
	/* Do not change the order of the if above and the two below... */
	if (os.pdsk == D_DISKLESS && ns.pdsk > D_DISKLESS) {      /* attach on the peer */
		drbd_send_uuids(mdev);
		drbd_send_state(mdev);
	}
1492 1493 1494 1495 1496 1497
	/* No point in queuing send_bitmap if we don't have a connection
	 * anymore, so check also the _current_ state, not only the new state
	 * at the time this work was queued. */
	if (os.conn != C_WF_BITMAP_S && ns.conn == C_WF_BITMAP_S &&
	    mdev->state.conn == C_WF_BITMAP_S)
		drbd_queue_bitmap_io(mdev, &drbd_send_bitmap, NULL,
1498 1499
				"send_bitmap (WFBitMapS)",
				BM_LOCKED_TEST_ALLOWED);
P
Philipp Reisner 已提交
1500 1501 1502 1503 1504 1505 1506 1507 1508 1509

	/* Lost contact to peer's copy of the data */
	if ((os.pdsk >= D_INCONSISTENT &&
	     os.pdsk != D_UNKNOWN &&
	     os.pdsk != D_OUTDATED)
	&&  (ns.pdsk < D_INCONSISTENT ||
	     ns.pdsk == D_UNKNOWN ||
	     ns.pdsk == D_OUTDATED)) {
		if (get_ldev(mdev)) {
			if ((ns.role == R_PRIMARY || ns.peer == R_PRIMARY) &&
1510
			    mdev->ldev->md.uuid[UI_BITMAP] == 0 && ns.disk >= D_UP_TO_DATE) {
1511
				if (is_susp(mdev->state)) {
1512 1513 1514 1515 1516
					set_bit(NEW_CUR_UUID, &mdev->flags);
				} else {
					drbd_uuid_new_current(mdev);
					drbd_send_uuids(mdev);
				}
1517
			}
P
Philipp Reisner 已提交
1518 1519 1520 1521 1522
			put_ldev(mdev);
		}
	}

	if (ns.pdsk < D_INCONSISTENT && get_ldev(mdev)) {
1523 1524
		if (os.peer == R_SECONDARY && ns.peer == R_PRIMARY &&
		    mdev->ldev->md.uuid[UI_BITMAP] == 0 && ns.disk >= D_UP_TO_DATE) {
1525
			drbd_uuid_new_current(mdev);
1526 1527
			drbd_send_uuids(mdev);
		}
P
Philipp Reisner 已提交
1528 1529
		/* D_DISKLESS Peer becomes secondary */
		if (os.peer == R_PRIMARY && ns.peer == R_SECONDARY)
1530 1531 1532 1533 1534
			/* We may still be Primary ourselves.
			 * No harm done if the bitmap still changes,
			 * redirtied pages will follow later. */
			drbd_bitmap_io_from_worker(mdev, &drbd_bm_write,
				"demote diskless peer", BM_LOCKED_SET_ALLOWED);
1535 1536 1537
		put_ldev(mdev);
	}

1538 1539 1540 1541 1542
	/* Write out all changed bits on demote.
	 * Though, no need to da that just yet
	 * if there is a resync going on still */
	if (os.role == R_PRIMARY && ns.role == R_SECONDARY &&
		mdev->state.conn <= C_CONNECTED && get_ldev(mdev)) {
1543 1544 1545 1546
		/* No changes to the bitmap expected this time, so assert that,
		 * even though no harm was done if it did change. */
		drbd_bitmap_io_from_worker(mdev, &drbd_bm_write,
				"demote", BM_LOCKED_TEST_ALLOWED);
P
Philipp Reisner 已提交
1547 1548 1549 1550 1551 1552
		put_ldev(mdev);
	}

	/* Last part of the attaching process ... */
	if (ns.conn >= C_CONNECTED &&
	    os.disk == D_ATTACHING && ns.disk == D_NEGOTIATING) {
1553
		drbd_send_sizes(mdev, 0, 0);  /* to start sync... */
P
Philipp Reisner 已提交
1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573
		drbd_send_uuids(mdev);
		drbd_send_state(mdev);
	}

	/* We want to pause/continue resync, tell peer. */
	if (ns.conn >= C_CONNECTED &&
	     ((os.aftr_isp != ns.aftr_isp) ||
	      (os.user_isp != ns.user_isp)))
		drbd_send_state(mdev);

	/* In case one of the isp bits got set, suspend other devices. */
	if ((!os.aftr_isp && !os.peer_isp && !os.user_isp) &&
	    (ns.aftr_isp || ns.peer_isp || ns.user_isp))
		suspend_other_sg(mdev);

	/* Make sure the peer gets informed about eventual state
	   changes (ISP bits) while we were in WFReportParams. */
	if (os.conn == C_WF_REPORT_PARAMS && ns.conn >= C_CONNECTED)
		drbd_send_state(mdev);

1574 1575 1576
	if (os.conn != C_AHEAD && ns.conn == C_AHEAD)
		drbd_send_state(mdev);

P
Philipp Reisner 已提交
1577 1578 1579
	/* We are in the progress to start a full sync... */
	if ((os.conn != C_STARTING_SYNC_T && ns.conn == C_STARTING_SYNC_T) ||
	    (os.conn != C_STARTING_SYNC_S && ns.conn == C_STARTING_SYNC_S))
1580 1581 1582 1583
		/* no other bitmap changes expected during this phase */
		drbd_queue_bitmap_io(mdev,
			&drbd_bmio_set_n_write, &abw_start_sync,
			"set_n_write from StartingSync", BM_LOCKED_TEST_ALLOWED);
P
Philipp Reisner 已提交
1584 1585 1586 1587

	/* We are invalidating our self... */
	if (os.conn < C_CONNECTED && ns.conn < C_CONNECTED &&
	    os.disk > D_INCONSISTENT && ns.disk == D_INCONSISTENT)
1588 1589 1590
		/* other bitmap operation expected during this phase */
		drbd_queue_bitmap_io(mdev, &drbd_bmio_set_n_write, NULL,
			"set_n_write from invalidate", BM_LOCKED_MASK);
P
Philipp Reisner 已提交
1591

1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602
	/* first half of local IO error, failure to attach,
	 * or administrative detach */
	if (os.disk != D_FAILED && ns.disk == D_FAILED) {
		enum drbd_io_error_p eh;
		int was_io_error;
		/* corresponding get_ldev was in __drbd_set_state, to serialize
		 * our cleanup here with the transition to D_DISKLESS,
		 * so it is safe to dreference ldev here. */
		eh = mdev->ldev->dc.on_io_error;
		was_io_error = test_and_clear_bit(WAS_IO_ERROR, &mdev->flags);

1603 1604
		/* Immediately allow completion of all application IO, that waits
		   for completion from the local disk. */
1605
		tl_abort_disk_io(mdev);
1606

1607 1608 1609 1610 1611 1612 1613
		/* current state still has to be D_FAILED,
		 * there is only one way out: to D_DISKLESS,
		 * and that may only happen after our put_ldev below. */
		if (mdev->state.disk != D_FAILED)
			dev_err(DEV,
				"ASSERT FAILED: disk is %s during detach\n",
				drbd_disk_str(mdev->state.disk));
1614 1615

		if (drbd_send_state(mdev))
1616
			dev_info(DEV, "Notified peer that I am detaching my disk\n");
1617 1618

		drbd_rs_cancel_all(mdev);
P
Philipp Reisner 已提交
1619

1620 1621 1622 1623 1624 1625 1626
		/* In case we want to get something to stable storage still,
		 * this may be the last chance.
		 * Following put_ldev may transition to D_DISKLESS. */
		drbd_md_sync(mdev);
		put_ldev(mdev);

		if (was_io_error && eh == EP_CALL_HELPER)
1627 1628
			drbd_khelper(mdev, "local-io-error");
	}
P
Philipp Reisner 已提交
1629

1630 1631 1632 1633 1634 1635 1636 1637 1638 1639
        /* second half of local IO error, failure to attach,
         * or administrative detach,
         * after local_cnt references have reached zero again */
        if (os.disk != D_DISKLESS && ns.disk == D_DISKLESS) {
                /* We must still be diskless,
                 * re-attach has to be serialized with this! */
                if (mdev->state.disk != D_DISKLESS)
                        dev_err(DEV,
                                "ASSERT FAILED: disk is %s while going diskless\n",
                                drbd_disk_str(mdev->state.disk));
1640

1641 1642 1643
                mdev->rs_total = 0;
                mdev->rs_failed = 0;
                atomic_set(&mdev->rs_pending_cnt, 0);
1644

1645
		if (drbd_send_state(mdev))
1646
			dev_info(DEV, "Notified peer that I'm now diskless.\n");
1647
		/* corresponding get_ldev in __drbd_set_state
L
Lucas De Marchi 已提交
1648
		 * this may finally trigger drbd_ldev_destroy. */
1649
		put_ldev(mdev);
P
Philipp Reisner 已提交
1650 1651
	}

1652 1653 1654 1655
	/* Notify peer that I had a local IO error, and did not detached.. */
	if (os.disk == D_UP_TO_DATE && ns.disk == D_INCONSISTENT)
		drbd_send_state(mdev);

P
Philipp Reisner 已提交
1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668
	/* Disks got bigger while they were detached */
	if (ns.disk > D_NEGOTIATING && ns.pdsk > D_NEGOTIATING &&
	    test_and_clear_bit(RESYNC_AFTER_NEG, &mdev->flags)) {
		if (ns.conn == C_CONNECTED)
			resync_after_online_grow(mdev);
	}

	/* A resync finished or aborted, wake paused devices... */
	if ((os.conn > C_CONNECTED && ns.conn <= C_CONNECTED) ||
	    (os.peer_isp && !ns.peer_isp) ||
	    (os.user_isp && !ns.user_isp))
		resume_next_sg(mdev);

1669 1670 1671 1672 1673
	/* sync target done with resync.  Explicitly notify peer, even though
	 * it should (at least for non-empty resyncs) already know itself. */
	if (os.disk < D_UP_TO_DATE && os.conn >= C_SYNC_SOURCE && ns.conn == C_CONNECTED)
		drbd_send_state(mdev);

1674 1675
	/* This triggers bitmap writeout of potentially still unwritten pages
	 * if the resync finished cleanly, or aborted because of peer disk
1676
	 * failure, or because of connection loss.
1677 1678
	 * For resync aborted because of local disk failure, we cannot do
	 * any bitmap writeout anymore.
1679
	 * No harm done if some bits change during this phase.
1680
	 */
1681 1682 1683
	if (os.conn > C_CONNECTED && ns.conn <= C_CONNECTED && get_ldev(mdev)) {
		drbd_queue_bitmap_io(mdev, &drbd_bm_write, NULL,
			"write from resync_finished", BM_LOCKED_SET_ALLOWED);
1684 1685
		put_ldev(mdev);
	}
1686

1687
	/* free tl_hash if we Got thawed and are C_STANDALONE */
1688
	if (ns.conn == C_STANDALONE && !is_susp(ns) && mdev->tl_hash)
1689 1690
		drbd_free_tl_hash(mdev);

P
Philipp Reisner 已提交
1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786
	/* Upon network connection, we need to start the receiver */
	if (os.conn == C_STANDALONE && ns.conn == C_UNCONNECTED)
		drbd_thread_start(&mdev->receiver);

	/* Terminate worker thread if we are unconfigured - it will be
	   restarted as needed... */
	if (ns.disk == D_DISKLESS &&
	    ns.conn == C_STANDALONE &&
	    ns.role == R_SECONDARY) {
		if (os.aftr_isp != ns.aftr_isp)
			resume_next_sg(mdev);
		/* set in __drbd_set_state, unless CONFIG_PENDING was set */
		if (test_bit(DEVICE_DYING, &mdev->flags))
			drbd_thread_stop_nowait(&mdev->worker);
	}

	drbd_md_sync(mdev);
}


static int drbd_thread_setup(void *arg)
{
	struct drbd_thread *thi = (struct drbd_thread *) arg;
	struct drbd_conf *mdev = thi->mdev;
	unsigned long flags;
	int retval;

restart:
	retval = thi->function(thi);

	spin_lock_irqsave(&thi->t_lock, flags);

	/* if the receiver has been "Exiting", the last thing it did
	 * was set the conn state to "StandAlone",
	 * if now a re-connect request comes in, conn state goes C_UNCONNECTED,
	 * and receiver thread will be "started".
	 * drbd_thread_start needs to set "Restarting" in that case.
	 * t_state check and assignment needs to be within the same spinlock,
	 * so either thread_start sees Exiting, and can remap to Restarting,
	 * or thread_start see None, and can proceed as normal.
	 */

	if (thi->t_state == Restarting) {
		dev_info(DEV, "Restarting %s\n", current->comm);
		thi->t_state = Running;
		spin_unlock_irqrestore(&thi->t_lock, flags);
		goto restart;
	}

	thi->task = NULL;
	thi->t_state = None;
	smp_mb();
	complete(&thi->stop);
	spin_unlock_irqrestore(&thi->t_lock, flags);

	dev_info(DEV, "Terminating %s\n", current->comm);

	/* Release mod reference taken when thread was started */
	module_put(THIS_MODULE);
	return retval;
}

static void drbd_thread_init(struct drbd_conf *mdev, struct drbd_thread *thi,
		      int (*func) (struct drbd_thread *))
{
	spin_lock_init(&thi->t_lock);
	thi->task    = NULL;
	thi->t_state = None;
	thi->function = func;
	thi->mdev = mdev;
}

int drbd_thread_start(struct drbd_thread *thi)
{
	struct drbd_conf *mdev = thi->mdev;
	struct task_struct *nt;
	unsigned long flags;

	const char *me =
		thi == &mdev->receiver ? "receiver" :
		thi == &mdev->asender  ? "asender"  :
		thi == &mdev->worker   ? "worker"   : "NONSENSE";

	/* is used from state engine doing drbd_thread_stop_nowait,
	 * while holding the req lock irqsave */
	spin_lock_irqsave(&thi->t_lock, flags);

	switch (thi->t_state) {
	case None:
		dev_info(DEV, "Starting %s thread (from %s [%d])\n",
				me, current->comm, current->pid);

		/* Get ref on module for thread - this is released when thread exits */
		if (!try_module_get(THIS_MODULE)) {
			dev_err(DEV, "Failed to get module reference in drbd_thread_start\n");
			spin_unlock_irqrestore(&thi->t_lock, flags);
1787
			return false;
P
Philipp Reisner 已提交
1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803
		}

		init_completion(&thi->stop);
		D_ASSERT(thi->task == NULL);
		thi->reset_cpu_mask = 1;
		thi->t_state = Running;
		spin_unlock_irqrestore(&thi->t_lock, flags);
		flush_signals(current); /* otherw. may get -ERESTARTNOINTR */

		nt = kthread_create(drbd_thread_setup, (void *) thi,
				    "drbd%d_%s", mdev_to_minor(mdev), me);

		if (IS_ERR(nt)) {
			dev_err(DEV, "Couldn't start thread\n");

			module_put(THIS_MODULE);
1804
			return false;
P
Philipp Reisner 已提交
1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823
		}
		spin_lock_irqsave(&thi->t_lock, flags);
		thi->task = nt;
		thi->t_state = Running;
		spin_unlock_irqrestore(&thi->t_lock, flags);
		wake_up_process(nt);
		break;
	case Exiting:
		thi->t_state = Restarting;
		dev_info(DEV, "Restarting %s thread (from %s [%d])\n",
				me, current->comm, current->pid);
		/* fall through */
	case Running:
	case Restarting:
	default:
		spin_unlock_irqrestore(&thi->t_lock, flags);
		break;
	}

1824
	return true;
P
Philipp Reisner 已提交
1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916
}


void _drbd_thread_stop(struct drbd_thread *thi, int restart, int wait)
{
	unsigned long flags;

	enum drbd_thread_state ns = restart ? Restarting : Exiting;

	/* may be called from state engine, holding the req lock irqsave */
	spin_lock_irqsave(&thi->t_lock, flags);

	if (thi->t_state == None) {
		spin_unlock_irqrestore(&thi->t_lock, flags);
		if (restart)
			drbd_thread_start(thi);
		return;
	}

	if (thi->t_state != ns) {
		if (thi->task == NULL) {
			spin_unlock_irqrestore(&thi->t_lock, flags);
			return;
		}

		thi->t_state = ns;
		smp_mb();
		init_completion(&thi->stop);
		if (thi->task != current)
			force_sig(DRBD_SIGKILL, thi->task);

	}

	spin_unlock_irqrestore(&thi->t_lock, flags);

	if (wait)
		wait_for_completion(&thi->stop);
}

#ifdef CONFIG_SMP
/**
 * drbd_calc_cpu_mask() - Generate CPU masks, spread over all CPUs
 * @mdev:	DRBD device.
 *
 * Forces all threads of a device onto the same CPU. This is beneficial for
 * DRBD's performance. May be overwritten by user's configuration.
 */
void drbd_calc_cpu_mask(struct drbd_conf *mdev)
{
	int ord, cpu;

	/* user override. */
	if (cpumask_weight(mdev->cpu_mask))
		return;

	ord = mdev_to_minor(mdev) % cpumask_weight(cpu_online_mask);
	for_each_online_cpu(cpu) {
		if (ord-- == 0) {
			cpumask_set_cpu(cpu, mdev->cpu_mask);
			return;
		}
	}
	/* should not be reached */
	cpumask_setall(mdev->cpu_mask);
}

/**
 * drbd_thread_current_set_cpu() - modifies the cpu mask of the _current_ thread
 * @mdev:	DRBD device.
 *
 * call in the "main loop" of _all_ threads, no need for any mutex, current won't die
 * prematurely.
 */
void drbd_thread_current_set_cpu(struct drbd_conf *mdev)
{
	struct task_struct *p = current;
	struct drbd_thread *thi =
		p == mdev->asender.task  ? &mdev->asender  :
		p == mdev->receiver.task ? &mdev->receiver :
		p == mdev->worker.task   ? &mdev->worker   :
		NULL;
	ERR_IF(thi == NULL)
		return;
	if (!thi->reset_cpu_mask)
		return;
	thi->reset_cpu_mask = 0;
	set_cpus_allowed_ptr(p, mdev->cpu_mask);
}
#endif

/* the appropriate socket mutex must be held already */
int _drbd_send_cmd(struct drbd_conf *mdev, struct socket *sock,
1917
			  enum drbd_packets cmd, struct p_header80 *h,
P
Philipp Reisner 已提交
1918 1919 1920 1921
			  size_t size, unsigned msg_flags)
{
	int sent, ok;

1922 1923
	ERR_IF(!h) return false;
	ERR_IF(!size) return false;
P
Philipp Reisner 已提交
1924 1925 1926

	h->magic   = BE_DRBD_MAGIC;
	h->command = cpu_to_be16(cmd);
1927
	h->length  = cpu_to_be16(size-sizeof(struct p_header80));
P
Philipp Reisner 已提交
1928 1929 1930 1931

	sent = drbd_send(mdev, sock, h, size, msg_flags);

	ok = (sent == size);
1932 1933
	if (!ok && !signal_pending(current))
		dev_warn(DEV, "short sent %s size=%d sent=%d\n",
P
Philipp Reisner 已提交
1934 1935 1936 1937 1938 1939 1940 1941
		    cmdname(cmd), (int)size, sent);
	return ok;
}

/* don't pass the socket. we may only look at it
 * when we hold the appropriate socket mutex.
 */
int drbd_send_cmd(struct drbd_conf *mdev, int use_data_socket,
1942
		  enum drbd_packets cmd, struct p_header80 *h, size_t size)
P
Philipp Reisner 已提交
1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969
{
	int ok = 0;
	struct socket *sock;

	if (use_data_socket) {
		mutex_lock(&mdev->data.mutex);
		sock = mdev->data.socket;
	} else {
		mutex_lock(&mdev->meta.mutex);
		sock = mdev->meta.socket;
	}

	/* drbd_disconnect() could have called drbd_free_sock()
	 * while we were waiting in down()... */
	if (likely(sock != NULL))
		ok = _drbd_send_cmd(mdev, sock, cmd, h, size, 0);

	if (use_data_socket)
		mutex_unlock(&mdev->data.mutex);
	else
		mutex_unlock(&mdev->meta.mutex);
	return ok;
}

int drbd_send_cmd2(struct drbd_conf *mdev, enum drbd_packets cmd, char *data,
		   size_t size)
{
1970
	struct p_header80 h;
P
Philipp Reisner 已提交
1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991
	int ok;

	h.magic   = BE_DRBD_MAGIC;
	h.command = cpu_to_be16(cmd);
	h.length  = cpu_to_be16(size);

	if (!drbd_get_data_sock(mdev))
		return 0;

	ok = (sizeof(h) ==
		drbd_send(mdev, mdev->data.socket, &h, sizeof(h), 0));
	ok = ok && (size ==
		drbd_send(mdev, mdev->data.socket, data, size, 0));

	drbd_put_data_sock(mdev);

	return ok;
}

int drbd_send_sync_param(struct drbd_conf *mdev, struct syncer_conf *sc)
{
1992
	struct p_rs_param_95 *p;
P
Philipp Reisner 已提交
1993 1994 1995 1996 1997 1998 1999
	struct socket *sock;
	int size, rv;
	const int apv = mdev->agreed_pro_version;

	size = apv <= 87 ? sizeof(struct p_rs_param)
		: apv == 88 ? sizeof(struct p_rs_param)
			+ strlen(mdev->sync_conf.verify_alg) + 1
2000 2001
		: apv <= 94 ? sizeof(struct p_rs_param_89)
		: /* apv >= 95 */ sizeof(struct p_rs_param_95);
P
Philipp Reisner 已提交
2002 2003 2004 2005 2006 2007 2008 2009 2010 2011

	/* used from admin command context and receiver/worker context.
	 * to avoid kmalloc, grab the socket right here,
	 * then use the pre-allocated sbuf there */
	mutex_lock(&mdev->data.mutex);
	sock = mdev->data.socket;

	if (likely(sock != NULL)) {
		enum drbd_packets cmd = apv >= 89 ? P_SYNC_PARAM89 : P_SYNC_PARAM;

2012
		p = &mdev->data.sbuf.rs_param_95;
P
Philipp Reisner 已提交
2013 2014 2015 2016 2017

		/* initialize verify_alg and csums_alg */
		memset(p->verify_alg, 0, 2 * SHARED_SECRET_MAX);

		p->rate = cpu_to_be32(sc->rate);
2018 2019 2020 2021
		p->c_plan_ahead = cpu_to_be32(sc->c_plan_ahead);
		p->c_delay_target = cpu_to_be32(sc->c_delay_target);
		p->c_fill_target = cpu_to_be32(sc->c_fill_target);
		p->c_max_rate = cpu_to_be32(sc->c_max_rate);
P
Philipp Reisner 已提交
2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039

		if (apv >= 88)
			strcpy(p->verify_alg, mdev->sync_conf.verify_alg);
		if (apv >= 89)
			strcpy(p->csums_alg, mdev->sync_conf.csums_alg);

		rv = _drbd_send_cmd(mdev, sock, cmd, &p->head, size, 0);
	} else
		rv = 0; /* not ok */

	mutex_unlock(&mdev->data.mutex);

	return rv;
}

int drbd_send_protocol(struct drbd_conf *mdev)
{
	struct p_protocol *p;
2040
	int size, cf, rv;
P
Philipp Reisner 已提交
2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058

	size = sizeof(struct p_protocol);

	if (mdev->agreed_pro_version >= 87)
		size += strlen(mdev->net_conf->integrity_alg) + 1;

	/* we must not recurse into our own queue,
	 * as that is blocked during handshake */
	p = kmalloc(size, GFP_NOIO);
	if (p == NULL)
		return 0;

	p->protocol      = cpu_to_be32(mdev->net_conf->wire_protocol);
	p->after_sb_0p   = cpu_to_be32(mdev->net_conf->after_sb_0p);
	p->after_sb_1p   = cpu_to_be32(mdev->net_conf->after_sb_1p);
	p->after_sb_2p   = cpu_to_be32(mdev->net_conf->after_sb_2p);
	p->two_primaries = cpu_to_be32(mdev->net_conf->two_primaries);

2059 2060 2061 2062 2063 2064 2065 2066
	cf = 0;
	if (mdev->net_conf->want_lose)
		cf |= CF_WANT_LOSE;
	if (mdev->net_conf->dry_run) {
		if (mdev->agreed_pro_version >= 92)
			cf |= CF_DRY_RUN;
		else {
			dev_err(DEV, "--dry-run is not supported by peer");
D
Dan Carpenter 已提交
2067
			kfree(p);
2068
			return -1;
2069 2070 2071 2072
		}
	}
	p->conn_flags    = cpu_to_be32(cf);

P
Philipp Reisner 已提交
2073 2074 2075 2076
	if (mdev->agreed_pro_version >= 87)
		strcpy(p->integrity_alg, mdev->net_conf->integrity_alg);

	rv = drbd_send_cmd(mdev, USE_DATA_SOCKET, P_PROTOCOL,
2077
			   (struct p_header80 *)p, size);
P
Philipp Reisner 已提交
2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102
	kfree(p);
	return rv;
}

int _drbd_send_uuids(struct drbd_conf *mdev, u64 uuid_flags)
{
	struct p_uuids p;
	int i;

	if (!get_ldev_if_state(mdev, D_NEGOTIATING))
		return 1;

	for (i = UI_CURRENT; i < UI_SIZE; i++)
		p.uuid[i] = mdev->ldev ? cpu_to_be64(mdev->ldev->md.uuid[i]) : 0;

	mdev->comm_bm_set = drbd_bm_total_weight(mdev);
	p.uuid[UI_SIZE] = cpu_to_be64(mdev->comm_bm_set);
	uuid_flags |= mdev->net_conf->want_lose ? 1 : 0;
	uuid_flags |= test_bit(CRASHED_PRIMARY, &mdev->flags) ? 2 : 0;
	uuid_flags |= mdev->new_state_tmp.disk == D_INCONSISTENT ? 4 : 0;
	p.uuid[UI_FLAGS] = cpu_to_be64(uuid_flags);

	put_ldev(mdev);

	return drbd_send_cmd(mdev, USE_DATA_SOCKET, P_UUIDS,
2103
			     (struct p_header80 *)&p, sizeof(p));
P
Philipp Reisner 已提交
2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115
}

int drbd_send_uuids(struct drbd_conf *mdev)
{
	return _drbd_send_uuids(mdev, 0);
}

int drbd_send_uuids_skip_initial_sync(struct drbd_conf *mdev)
{
	return _drbd_send_uuids(mdev, 8);
}

2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133
void drbd_print_uuids(struct drbd_conf *mdev, const char *text)
{
	if (get_ldev_if_state(mdev, D_NEGOTIATING)) {
		u64 *uuid = mdev->ldev->md.uuid;
		dev_info(DEV, "%s %016llX:%016llX:%016llX:%016llX\n",
		     text,
		     (unsigned long long)uuid[UI_CURRENT],
		     (unsigned long long)uuid[UI_BITMAP],
		     (unsigned long long)uuid[UI_HISTORY_START],
		     (unsigned long long)uuid[UI_HISTORY_END]);
		put_ldev(mdev);
	} else {
		dev_info(DEV, "%s effective data uuid: %016llX\n",
				text,
				(unsigned long long)mdev->ed_uuid);
	}
}

2134
int drbd_gen_and_send_sync_uuid(struct drbd_conf *mdev)
P
Philipp Reisner 已提交
2135 2136
{
	struct p_rs_uuid p;
2137 2138 2139
	u64 uuid;

	D_ASSERT(mdev->state.disk == D_UP_TO_DATE);
P
Philipp Reisner 已提交
2140

2141
	uuid = mdev->ldev->md.uuid[UI_BITMAP] + UUID_NEW_BM_OFFSET;
2142
	drbd_uuid_set(mdev, UI_BITMAP, uuid);
2143
	drbd_print_uuids(mdev, "updated sync UUID");
2144 2145
	drbd_md_sync(mdev);
	p.uuid = cpu_to_be64(uuid);
P
Philipp Reisner 已提交
2146 2147

	return drbd_send_cmd(mdev, USE_DATA_SOCKET, P_SYNC_UUID,
2148
			     (struct p_header80 *)&p, sizeof(p));
P
Philipp Reisner 已提交
2149 2150
}

2151
int drbd_send_sizes(struct drbd_conf *mdev, int trigger_reply, enum dds_flags flags)
P
Philipp Reisner 已提交
2152 2153 2154
{
	struct p_sizes p;
	sector_t d_size, u_size;
2155
	int q_order_type, max_bio_size;
P
Philipp Reisner 已提交
2156 2157 2158 2159 2160 2161 2162
	int ok;

	if (get_ldev_if_state(mdev, D_NEGOTIATING)) {
		D_ASSERT(mdev->ldev->backing_bdev);
		d_size = drbd_get_max_capacity(mdev->ldev);
		u_size = mdev->ldev->dc.disk_size;
		q_order_type = drbd_queue_order_type(mdev);
2163 2164
		max_bio_size = queue_max_hw_sectors(mdev->ldev->backing_bdev->bd_disk->queue) << 9;
		max_bio_size = min_t(int, max_bio_size, DRBD_MAX_BIO_SIZE);
P
Philipp Reisner 已提交
2165 2166 2167 2168 2169
		put_ldev(mdev);
	} else {
		d_size = 0;
		u_size = 0;
		q_order_type = QUEUE_ORDERED_NONE;
2170
		max_bio_size = DRBD_MAX_BIO_SIZE; /* ... multiple BIOs per peer_request */
P
Philipp Reisner 已提交
2171 2172
	}

2173 2174 2175 2176
	/* Never allow old drbd (up to 8.3.7) to see more than 32KiB */
	if (mdev->agreed_pro_version <= 94)
		max_bio_size = min_t(int, max_bio_size, DRBD_MAX_SIZE_H80_PACKET);

P
Philipp Reisner 已提交
2177 2178 2179
	p.d_size = cpu_to_be64(d_size);
	p.u_size = cpu_to_be64(u_size);
	p.c_size = cpu_to_be64(trigger_reply ? 0 : drbd_get_capacity(mdev->this_bdev));
2180
	p.max_bio_size = cpu_to_be32(max_bio_size);
2181 2182
	p.queue_order_type = cpu_to_be16(q_order_type);
	p.dds_flags = cpu_to_be16(flags);
P
Philipp Reisner 已提交
2183 2184

	ok = drbd_send_cmd(mdev, USE_DATA_SOCKET, P_SIZES,
2185
			   (struct p_header80 *)&p, sizeof(p));
P
Philipp Reisner 已提交
2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209
	return ok;
}

/**
 * drbd_send_state() - Sends the drbd state to the peer
 * @mdev:	DRBD device.
 */
int drbd_send_state(struct drbd_conf *mdev)
{
	struct socket *sock;
	struct p_state p;
	int ok = 0;

	/* Grab state lock so we wont send state if we're in the middle
	 * of a cluster wide state change on another thread */
	drbd_state_lock(mdev);

	mutex_lock(&mdev->data.mutex);

	p.state = cpu_to_be32(mdev->state.i); /* Within the send mutex */
	sock = mdev->data.socket;

	if (likely(sock != NULL)) {
		ok = _drbd_send_cmd(mdev, sock, P_STATE,
2210
				    (struct p_header80 *)&p, sizeof(p), 0);
P
Philipp Reisner 已提交
2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227
	}

	mutex_unlock(&mdev->data.mutex);

	drbd_state_unlock(mdev);
	return ok;
}

int drbd_send_state_req(struct drbd_conf *mdev,
	union drbd_state mask, union drbd_state val)
{
	struct p_req_state p;

	p.mask    = cpu_to_be32(mask.i);
	p.val     = cpu_to_be32(val.i);

	return drbd_send_cmd(mdev, USE_DATA_SOCKET, P_STATE_CHG_REQ,
2228
			     (struct p_header80 *)&p, sizeof(p));
P
Philipp Reisner 已提交
2229 2230
}

2231
int drbd_send_sr_reply(struct drbd_conf *mdev, enum drbd_state_rv retcode)
P
Philipp Reisner 已提交
2232 2233 2234 2235 2236 2237
{
	struct p_req_state_reply p;

	p.retcode    = cpu_to_be32(retcode);

	return drbd_send_cmd(mdev, USE_META_SOCKET, P_STATE_CHG_REPLY,
2238
			     (struct p_header80 *)&p, sizeof(p));
P
Philipp Reisner 已提交
2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334
}

int fill_bitmap_rle_bits(struct drbd_conf *mdev,
	struct p_compressed_bm *p,
	struct bm_xfer_ctx *c)
{
	struct bitstream bs;
	unsigned long plain_bits;
	unsigned long tmp;
	unsigned long rl;
	unsigned len;
	unsigned toggle;
	int bits;

	/* may we use this feature? */
	if ((mdev->sync_conf.use_rle == 0) ||
		(mdev->agreed_pro_version < 90))
			return 0;

	if (c->bit_offset >= c->bm_bits)
		return 0; /* nothing to do. */

	/* use at most thus many bytes */
	bitstream_init(&bs, p->code, BM_PACKET_VLI_BYTES_MAX, 0);
	memset(p->code, 0, BM_PACKET_VLI_BYTES_MAX);
	/* plain bits covered in this code string */
	plain_bits = 0;

	/* p->encoding & 0x80 stores whether the first run length is set.
	 * bit offset is implicit.
	 * start with toggle == 2 to be able to tell the first iteration */
	toggle = 2;

	/* see how much plain bits we can stuff into one packet
	 * using RLE and VLI. */
	do {
		tmp = (toggle == 0) ? _drbd_bm_find_next_zero(mdev, c->bit_offset)
				    : _drbd_bm_find_next(mdev, c->bit_offset);
		if (tmp == -1UL)
			tmp = c->bm_bits;
		rl = tmp - c->bit_offset;

		if (toggle == 2) { /* first iteration */
			if (rl == 0) {
				/* the first checked bit was set,
				 * store start value, */
				DCBP_set_start(p, 1);
				/* but skip encoding of zero run length */
				toggle = !toggle;
				continue;
			}
			DCBP_set_start(p, 0);
		}

		/* paranoia: catch zero runlength.
		 * can only happen if bitmap is modified while we scan it. */
		if (rl == 0) {
			dev_err(DEV, "unexpected zero runlength while encoding bitmap "
			    "t:%u bo:%lu\n", toggle, c->bit_offset);
			return -1;
		}

		bits = vli_encode_bits(&bs, rl);
		if (bits == -ENOBUFS) /* buffer full */
			break;
		if (bits <= 0) {
			dev_err(DEV, "error while encoding bitmap: %d\n", bits);
			return 0;
		}

		toggle = !toggle;
		plain_bits += rl;
		c->bit_offset = tmp;
	} while (c->bit_offset < c->bm_bits);

	len = bs.cur.b - p->code + !!bs.cur.bit;

	if (plain_bits < (len << 3)) {
		/* incompressible with this method.
		 * we need to rewind both word and bit position. */
		c->bit_offset -= plain_bits;
		bm_xfer_ctx_bit_to_word_offset(c);
		c->bit_offset = c->word_offset * BITS_PER_LONG;
		return 0;
	}

	/* RLE + VLI was able to compress it just fine.
	 * update c->word_offset. */
	bm_xfer_ctx_bit_to_word_offset(c);

	/* store pad_bits */
	DCBP_set_pad_bits(p, (8 - bs.cur.bit) & 0x7);

	return len;
}

2335 2336 2337 2338 2339 2340 2341
/**
 * send_bitmap_rle_or_plain
 *
 * Return 0 when done, 1 when another iteration is needed, and a negative error
 * code upon failure.
 */
static int
P
Philipp Reisner 已提交
2342
send_bitmap_rle_or_plain(struct drbd_conf *mdev,
2343
			 struct p_header80 *h, struct bm_xfer_ctx *c)
P
Philipp Reisner 已提交
2344 2345 2346 2347 2348 2349 2350 2351 2352
{
	struct p_compressed_bm *p = (void*)h;
	unsigned long num_words;
	int len;
	int ok;

	len = fill_bitmap_rle_bits(mdev, p, c);

	if (len < 0)
2353
		return -EIO;
P
Philipp Reisner 已提交
2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372

	if (len) {
		DCBP_set_code(p, RLE_VLI_Bits);
		ok = _drbd_send_cmd(mdev, mdev->data.socket, P_COMPRESSED_BITMAP, h,
			sizeof(*p) + len, 0);

		c->packets[0]++;
		c->bytes[0] += sizeof(*p) + len;

		if (c->bit_offset >= c->bm_bits)
			len = 0; /* DONE */
	} else {
		/* was not compressible.
		 * send a buffer full of plain text bits instead. */
		num_words = min_t(size_t, BM_PACKET_WORDS, c->bm_words - c->word_offset);
		len = num_words * sizeof(long);
		if (len)
			drbd_bm_get_lel(mdev, c->word_offset, num_words, (unsigned long*)h->payload);
		ok = _drbd_send_cmd(mdev, mdev->data.socket, P_BITMAP,
2373
				   h, sizeof(struct p_header80) + len, 0);
P
Philipp Reisner 已提交
2374 2375 2376 2377
		c->word_offset += num_words;
		c->bit_offset = c->word_offset * BITS_PER_LONG;

		c->packets[1]++;
2378
		c->bytes[1] += sizeof(struct p_header80) + len;
P
Philipp Reisner 已提交
2379 2380 2381 2382

		if (c->bit_offset > c->bm_bits)
			c->bit_offset = c->bm_bits;
	}
2383 2384 2385 2386 2387 2388 2389 2390
	if (ok) {
		if (len == 0) {
			INFO_bm_xfer_stats(mdev, "send", c);
			return 0;
		} else
			return 1;
	}
	return -EIO;
P
Philipp Reisner 已提交
2391 2392 2393 2394 2395 2396
}

/* See the comment at receive_bitmap() */
int _drbd_send_bitmap(struct drbd_conf *mdev)
{
	struct bm_xfer_ctx c;
2397
	struct p_header80 *p;
2398
	int err;
P
Philipp Reisner 已提交
2399

2400
	ERR_IF(!mdev->bitmap) return false;
P
Philipp Reisner 已提交
2401 2402 2403

	/* maybe we should use some per thread scratch page,
	 * and allocate that during initial device creation? */
2404
	p = (struct p_header80 *) __get_free_page(GFP_NOIO);
P
Philipp Reisner 已提交
2405 2406
	if (!p) {
		dev_err(DEV, "failed to allocate one page buffer in %s\n", __func__);
2407
		return false;
P
Philipp Reisner 已提交
2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432
	}

	if (get_ldev(mdev)) {
		if (drbd_md_test_flag(mdev->ldev, MDF_FULL_SYNC)) {
			dev_info(DEV, "Writing the whole bitmap, MDF_FullSync was set.\n");
			drbd_bm_set_all(mdev);
			if (drbd_bm_write(mdev)) {
				/* write_bm did fail! Leave full sync flag set in Meta P_DATA
				 * but otherwise process as per normal - need to tell other
				 * side that a full resync is required! */
				dev_err(DEV, "Failed to write bitmap to disk!\n");
			} else {
				drbd_md_clear_flag(mdev, MDF_FULL_SYNC);
				drbd_md_sync(mdev);
			}
		}
		put_ldev(mdev);
	}

	c = (struct bm_xfer_ctx) {
		.bm_bits = drbd_bm_bits(mdev),
		.bm_words = drbd_bm_words(mdev),
	};

	do {
2433 2434
		err = send_bitmap_rle_or_plain(mdev, p, &c);
	} while (err > 0);
P
Philipp Reisner 已提交
2435 2436

	free_page((unsigned long) p);
2437
	return err == 0;
P
Philipp Reisner 已提交
2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459
}

int drbd_send_bitmap(struct drbd_conf *mdev)
{
	int err;

	if (!drbd_get_data_sock(mdev))
		return -1;
	err = !_drbd_send_bitmap(mdev);
	drbd_put_data_sock(mdev);
	return err;
}

int drbd_send_b_ack(struct drbd_conf *mdev, u32 barrier_nr, u32 set_size)
{
	int ok;
	struct p_barrier_ack p;

	p.barrier  = barrier_nr;
	p.set_size = cpu_to_be32(set_size);

	if (mdev->state.conn < C_CONNECTED)
2460
		return false;
P
Philipp Reisner 已提交
2461
	ok = drbd_send_cmd(mdev, USE_META_SOCKET, P_BARRIER_ACK,
2462
			(struct p_header80 *)&p, sizeof(p));
P
Philipp Reisner 已提交
2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487
	return ok;
}

/**
 * _drbd_send_ack() - Sends an ack packet
 * @mdev:	DRBD device.
 * @cmd:	Packet command code.
 * @sector:	sector, needs to be in big endian byte order
 * @blksize:	size in byte, needs to be in big endian byte order
 * @block_id:	Id, big endian byte order
 */
static int _drbd_send_ack(struct drbd_conf *mdev, enum drbd_packets cmd,
			  u64 sector,
			  u32 blksize,
			  u64 block_id)
{
	int ok;
	struct p_block_ack p;

	p.sector   = sector;
	p.block_id = block_id;
	p.blksize  = blksize;
	p.seq_num  = cpu_to_be32(atomic_add_return(1, &mdev->packet_seq));

	if (!mdev->meta.socket || mdev->state.conn < C_CONNECTED)
2488
		return false;
P
Philipp Reisner 已提交
2489
	ok = drbd_send_cmd(mdev, USE_META_SOCKET, cmd,
2490
				(struct p_header80 *)&p, sizeof(p));
P
Philipp Reisner 已提交
2491 2492 2493
	return ok;
}

2494 2495 2496
/* dp->sector and dp->block_id already/still in network byte order,
 * data_size is payload size according to dp->head,
 * and may need to be corrected for digest size. */
P
Philipp Reisner 已提交
2497
int drbd_send_ack_dp(struct drbd_conf *mdev, enum drbd_packets cmd,
2498
		     struct p_data *dp, int data_size)
P
Philipp Reisner 已提交
2499
{
2500 2501
	data_size -= (mdev->agreed_pro_version >= 87 && mdev->integrity_r_tfm) ?
		crypto_hash_digestsize(mdev->integrity_r_tfm) : 0;
P
Philipp Reisner 已提交
2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548
	return _drbd_send_ack(mdev, cmd, dp->sector, cpu_to_be32(data_size),
			      dp->block_id);
}

int drbd_send_ack_rp(struct drbd_conf *mdev, enum drbd_packets cmd,
		     struct p_block_req *rp)
{
	return _drbd_send_ack(mdev, cmd, rp->sector, rp->blksize, rp->block_id);
}

/**
 * drbd_send_ack() - Sends an ack packet
 * @mdev:	DRBD device.
 * @cmd:	Packet command code.
 * @e:		Epoch entry.
 */
int drbd_send_ack(struct drbd_conf *mdev,
	enum drbd_packets cmd, struct drbd_epoch_entry *e)
{
	return _drbd_send_ack(mdev, cmd,
			      cpu_to_be64(e->sector),
			      cpu_to_be32(e->size),
			      e->block_id);
}

/* This function misuses the block_id field to signal if the blocks
 * are is sync or not. */
int drbd_send_ack_ex(struct drbd_conf *mdev, enum drbd_packets cmd,
		     sector_t sector, int blksize, u64 block_id)
{
	return _drbd_send_ack(mdev, cmd,
			      cpu_to_be64(sector),
			      cpu_to_be32(blksize),
			      cpu_to_be64(block_id));
}

int drbd_send_drequest(struct drbd_conf *mdev, int cmd,
		       sector_t sector, int size, u64 block_id)
{
	int ok;
	struct p_block_req p;

	p.sector   = cpu_to_be64(sector);
	p.block_id = block_id;
	p.blksize  = cpu_to_be32(size);

	ok = drbd_send_cmd(mdev, USE_DATA_SOCKET, cmd,
2549
				(struct p_header80 *)&p, sizeof(p));
P
Philipp Reisner 已提交
2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566
	return ok;
}

int drbd_send_drequest_csum(struct drbd_conf *mdev,
			    sector_t sector, int size,
			    void *digest, int digest_size,
			    enum drbd_packets cmd)
{
	int ok;
	struct p_block_req p;

	p.sector   = cpu_to_be64(sector);
	p.block_id = BE_DRBD_MAGIC + 0xbeef;
	p.blksize  = cpu_to_be32(size);

	p.head.magic   = BE_DRBD_MAGIC;
	p.head.command = cpu_to_be16(cmd);
2567
	p.head.length  = cpu_to_be16(sizeof(p) - sizeof(struct p_header80) + digest_size);
P
Philipp Reisner 已提交
2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588

	mutex_lock(&mdev->data.mutex);

	ok = (sizeof(p) == drbd_send(mdev, mdev->data.socket, &p, sizeof(p), 0));
	ok = ok && (digest_size == drbd_send(mdev, mdev->data.socket, digest, digest_size, 0));

	mutex_unlock(&mdev->data.mutex);

	return ok;
}

int drbd_send_ov_request(struct drbd_conf *mdev, sector_t sector, int size)
{
	int ok;
	struct p_block_req p;

	p.sector   = cpu_to_be64(sector);
	p.block_id = BE_DRBD_MAGIC + 0xbabe;
	p.blksize  = cpu_to_be32(size);

	ok = drbd_send_cmd(mdev, USE_DATA_SOCKET, P_OV_REQUEST,
2589
			   (struct p_header80 *)&p, sizeof(p));
P
Philipp Reisner 已提交
2590 2591 2592 2593
	return ok;
}

/* called on sndtimeo
2594 2595
 * returns false if we should retry,
 * true if we think connection is dead
P
Philipp Reisner 已提交
2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607
 */
static int we_should_drop_the_connection(struct drbd_conf *mdev, struct socket *sock)
{
	int drop_it;
	/* long elapsed = (long)(jiffies - mdev->last_received); */

	drop_it =   mdev->meta.socket == sock
		|| !mdev->asender.task
		|| get_t_state(&mdev->asender) != Running
		|| mdev->state.conn < C_CONNECTED;

	if (drop_it)
2608
		return true;
P
Philipp Reisner 已提交
2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641

	drop_it = !--mdev->ko_count;
	if (!drop_it) {
		dev_err(DEV, "[%s/%d] sock_sendmsg time expired, ko = %u\n",
		       current->comm, current->pid, mdev->ko_count);
		request_ping(mdev);
	}

	return drop_it; /* && (mdev->state == R_PRIMARY) */;
}

/* The idea of sendpage seems to be to put some kind of reference
 * to the page into the skb, and to hand it over to the NIC. In
 * this process get_page() gets called.
 *
 * As soon as the page was really sent over the network put_page()
 * gets called by some part of the network layer. [ NIC driver? ]
 *
 * [ get_page() / put_page() increment/decrement the count. If count
 *   reaches 0 the page will be freed. ]
 *
 * This works nicely with pages from FSs.
 * But this means that in protocol A we might signal IO completion too early!
 *
 * In order not to corrupt data during a resync we must make sure
 * that we do not reuse our own buffer pages (EEs) to early, therefore
 * we have the net_ee list.
 *
 * XFS seems to have problems, still, it submits pages with page_count == 0!
 * As a workaround, we disable sendpage on pages
 * with page_count == 0 or PageSlab.
 */
static int _drbd_no_send_page(struct drbd_conf *mdev, struct page *page,
L
Lars Ellenberg 已提交
2642
		   int offset, size_t size, unsigned msg_flags)
P
Philipp Reisner 已提交
2643
{
L
Lars Ellenberg 已提交
2644
	int sent = drbd_send(mdev, mdev->data.socket, kmap(page) + offset, size, msg_flags);
P
Philipp Reisner 已提交
2645 2646 2647 2648 2649 2650 2651
	kunmap(page);
	if (sent == size)
		mdev->send_cnt += size>>9;
	return sent == size;
}

static int _drbd_send_page(struct drbd_conf *mdev, struct page *page,
L
Lars Ellenberg 已提交
2652
		    int offset, size_t size, unsigned msg_flags)
P
Philipp Reisner 已提交
2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664
{
	mm_segment_t oldfs = get_fs();
	int sent, ok;
	int len = size;

	/* e.g. XFS meta- & log-data is in slab pages, which have a
	 * page_count of 0 and/or have PageSlab() set.
	 * we cannot use send_page for those, as that does get_page();
	 * put_page(); and would cause either a VM_BUG directly, or
	 * __page_cache_release a page that would actually still be referenced
	 * by someone, leading to some obscure delayed Oops somewhere else. */
	if (disable_sendpage || (page_count(page) < 1) || PageSlab(page))
L
Lars Ellenberg 已提交
2665
		return _drbd_no_send_page(mdev, page, offset, size, msg_flags);
P
Philipp Reisner 已提交
2666

L
Lars Ellenberg 已提交
2667
	msg_flags |= MSG_NOSIGNAL;
P
Philipp Reisner 已提交
2668 2669 2670 2671 2672
	drbd_update_congested(mdev);
	set_fs(KERNEL_DS);
	do {
		sent = mdev->data.socket->ops->sendpage(mdev->data.socket, page,
							offset, len,
L
Lars Ellenberg 已提交
2673
							msg_flags);
P
Philipp Reisner 已提交
2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701
		if (sent == -EAGAIN) {
			if (we_should_drop_the_connection(mdev,
							  mdev->data.socket))
				break;
			else
				continue;
		}
		if (sent <= 0) {
			dev_warn(DEV, "%s: size=%d len=%d sent=%d\n",
			     __func__, (int)size, len, sent);
			break;
		}
		len    -= sent;
		offset += sent;
	} while (len > 0 /* THINK && mdev->cstate >= C_CONNECTED*/);
	set_fs(oldfs);
	clear_bit(NET_CONGESTED, &mdev->flags);

	ok = (len == 0);
	if (likely(ok))
		mdev->send_cnt += size>>9;
	return ok;
}

static int _drbd_send_bio(struct drbd_conf *mdev, struct bio *bio)
{
	struct bio_vec *bvec;
	int i;
L
Lars Ellenberg 已提交
2702
	/* hint all but last page with MSG_MORE */
P
Philipp Reisner 已提交
2703 2704
	__bio_for_each_segment(bvec, bio, i, 0) {
		if (!_drbd_no_send_page(mdev, bvec->bv_page,
L
Lars Ellenberg 已提交
2705 2706
				     bvec->bv_offset, bvec->bv_len,
				     i == bio->bi_vcnt -1 ? 0 : MSG_MORE))
P
Philipp Reisner 已提交
2707 2708 2709 2710 2711 2712 2713 2714 2715
			return 0;
	}
	return 1;
}

static int _drbd_send_zc_bio(struct drbd_conf *mdev, struct bio *bio)
{
	struct bio_vec *bvec;
	int i;
L
Lars Ellenberg 已提交
2716
	/* hint all but last page with MSG_MORE */
P
Philipp Reisner 已提交
2717 2718
	__bio_for_each_segment(bvec, bio, i, 0) {
		if (!_drbd_send_page(mdev, bvec->bv_page,
L
Lars Ellenberg 已提交
2719 2720
				     bvec->bv_offset, bvec->bv_len,
				     i == bio->bi_vcnt -1 ? 0 : MSG_MORE))
P
Philipp Reisner 已提交
2721 2722 2723 2724 2725
			return 0;
	}
	return 1;
}

2726 2727 2728 2729
static int _drbd_send_zc_ee(struct drbd_conf *mdev, struct drbd_epoch_entry *e)
{
	struct page *page = e->pages;
	unsigned len = e->size;
L
Lars Ellenberg 已提交
2730
	/* hint all but last page with MSG_MORE */
2731 2732
	page_chain_for_each(page) {
		unsigned l = min_t(unsigned, len, PAGE_SIZE);
L
Lars Ellenberg 已提交
2733 2734
		if (!_drbd_send_page(mdev, page, 0, l,
				page_chain_next(page) ? MSG_MORE : 0))
2735 2736 2737 2738 2739 2740
			return 0;
		len -= l;
	}
	return 1;
}

2741 2742 2743 2744 2745 2746 2747 2748
static u32 bio_flags_to_wire(struct drbd_conf *mdev, unsigned long bi_rw)
{
	if (mdev->agreed_pro_version >= 95)
		return  (bi_rw & REQ_SYNC ? DP_RW_SYNC : 0) |
			(bi_rw & REQ_FUA ? DP_FUA : 0) |
			(bi_rw & REQ_FLUSH ? DP_FLUSH : 0) |
			(bi_rw & REQ_DISCARD ? DP_DISCARD : 0);
	else
J
Jens Axboe 已提交
2749
		return bi_rw & REQ_SYNC ? DP_RW_SYNC : 0;
2750 2751
}

P
Philipp Reisner 已提交
2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768
/* Used to send write requests
 * R_PRIMARY -> Peer	(P_DATA)
 */
int drbd_send_dblock(struct drbd_conf *mdev, struct drbd_request *req)
{
	int ok = 1;
	struct p_data p;
	unsigned int dp_flags = 0;
	void *dgb;
	int dgs;

	if (!drbd_get_data_sock(mdev))
		return 0;

	dgs = (mdev->agreed_pro_version >= 87 && mdev->integrity_w_tfm) ?
		crypto_hash_digestsize(mdev->integrity_w_tfm) : 0;

2769
	if (req->size <= DRBD_MAX_SIZE_H80_PACKET) {
2770 2771 2772 2773 2774 2775 2776 2777 2778 2779
		p.head.h80.magic   = BE_DRBD_MAGIC;
		p.head.h80.command = cpu_to_be16(P_DATA);
		p.head.h80.length  =
			cpu_to_be16(sizeof(p) - sizeof(union p_header) + dgs + req->size);
	} else {
		p.head.h95.magic   = BE_DRBD_MAGIC_BIG;
		p.head.h95.command = cpu_to_be16(P_DATA);
		p.head.h95.length  =
			cpu_to_be32(sizeof(p) - sizeof(union p_header) + dgs + req->size);
	}
P
Philipp Reisner 已提交
2780 2781 2782 2783 2784 2785

	p.sector   = cpu_to_be64(req->sector);
	p.block_id = (unsigned long)req;
	p.seq_num  = cpu_to_be32(req->seq_num =
				 atomic_add_return(1, &mdev->packet_seq));

2786 2787
	dp_flags = bio_flags_to_wire(mdev, req->master_bio->bi_rw);

P
Philipp Reisner 已提交
2788 2789 2790 2791 2792 2793 2794
	if (mdev->state.conn >= C_SYNC_SOURCE &&
	    mdev->state.conn <= C_PAUSED_SYNC_T)
		dp_flags |= DP_MAY_SET_IN_SYNC;

	p.dp_flags = cpu_to_be32(dp_flags);
	set_bit(UNPLUG_REMOTE, &mdev->flags);
	ok = (sizeof(p) ==
L
Lars Ellenberg 已提交
2795
		drbd_send(mdev, mdev->data.socket, &p, sizeof(p), dgs ? MSG_MORE : 0));
P
Philipp Reisner 已提交
2796 2797
	if (ok && dgs) {
		dgb = mdev->int_dig_out;
2798
		drbd_csum_bio(mdev, mdev->integrity_w_tfm, req->master_bio, dgb);
2799
		ok = dgs == drbd_send(mdev, mdev->data.socket, dgb, dgs, 0);
P
Philipp Reisner 已提交
2800 2801
	}
	if (ok) {
2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813
		/* For protocol A, we have to memcpy the payload into
		 * socket buffers, as we may complete right away
		 * as soon as we handed it over to tcp, at which point the data
		 * pages may become invalid.
		 *
		 * For data-integrity enabled, we copy it as well, so we can be
		 * sure that even if the bio pages may still be modified, it
		 * won't change the data on the wire, thus if the digest checks
		 * out ok after sending on this side, but does not fit on the
		 * receiving side, we sure have detected corruption elsewhere.
		 */
		if (mdev->net_conf->wire_protocol == DRBD_PROT_A || dgs)
P
Philipp Reisner 已提交
2814 2815 2816
			ok = _drbd_send_bio(mdev, req->master_bio);
		else
			ok = _drbd_send_zc_bio(mdev, req->master_bio);
2817 2818 2819

		/* double check digest, sometimes buffers have been modified in flight. */
		if (dgs > 0 && dgs <= 64) {
B
Bart Van Assche 已提交
2820
			/* 64 byte, 512 bit, is the largest digest size
2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831
			 * currently supported in kernel crypto. */
			unsigned char digest[64];
			drbd_csum_bio(mdev, mdev->integrity_w_tfm, req->master_bio, digest);
			if (memcmp(mdev->int_dig_out, digest, dgs)) {
				dev_warn(DEV,
					"Digest mismatch, buffer modified by upper layers during write: %llus +%u\n",
					(unsigned long long)req->sector, req->size);
			}
		} /* else if (dgs > 64) {
		     ... Be noisy about digest too large ...
		} */
P
Philipp Reisner 已提交
2832 2833 2834
	}

	drbd_put_data_sock(mdev);
2835

P
Philipp Reisner 已提交
2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853
	return ok;
}

/* answer packet, used to send data back for read requests:
 *  Peer       -> (diskless) R_PRIMARY   (P_DATA_REPLY)
 *  C_SYNC_SOURCE -> C_SYNC_TARGET         (P_RS_DATA_REPLY)
 */
int drbd_send_block(struct drbd_conf *mdev, enum drbd_packets cmd,
		    struct drbd_epoch_entry *e)
{
	int ok;
	struct p_data p;
	void *dgb;
	int dgs;

	dgs = (mdev->agreed_pro_version >= 87 && mdev->integrity_w_tfm) ?
		crypto_hash_digestsize(mdev->integrity_w_tfm) : 0;

2854
	if (e->size <= DRBD_MAX_SIZE_H80_PACKET) {
2855 2856 2857 2858 2859 2860 2861 2862 2863 2864
		p.head.h80.magic   = BE_DRBD_MAGIC;
		p.head.h80.command = cpu_to_be16(cmd);
		p.head.h80.length  =
			cpu_to_be16(sizeof(p) - sizeof(struct p_header80) + dgs + e->size);
	} else {
		p.head.h95.magic   = BE_DRBD_MAGIC_BIG;
		p.head.h95.command = cpu_to_be16(cmd);
		p.head.h95.length  =
			cpu_to_be32(sizeof(p) - sizeof(struct p_header80) + dgs + e->size);
	}
P
Philipp Reisner 已提交
2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876

	p.sector   = cpu_to_be64(e->sector);
	p.block_id = e->block_id;
	/* p.seq_num  = 0;    No sequence numbers here.. */

	/* Only called by our kernel thread.
	 * This one may be interrupted by DRBD_SIG and/or DRBD_SIGKILL
	 * in response to admin command or module unload.
	 */
	if (!drbd_get_data_sock(mdev))
		return 0;

2877
	ok = sizeof(p) == drbd_send(mdev, mdev->data.socket, &p, sizeof(p), dgs ? MSG_MORE : 0);
P
Philipp Reisner 已提交
2878 2879
	if (ok && dgs) {
		dgb = mdev->int_dig_out;
2880
		drbd_csum_ee(mdev, mdev->integrity_w_tfm, e, dgb);
2881
		ok = dgs == drbd_send(mdev, mdev->data.socket, dgb, dgs, 0);
P
Philipp Reisner 已提交
2882 2883
	}
	if (ok)
2884
		ok = _drbd_send_zc_ee(mdev, e);
P
Philipp Reisner 已提交
2885 2886

	drbd_put_data_sock(mdev);
2887

P
Philipp Reisner 已提交
2888 2889 2890
	return ok;
}

2891 2892 2893 2894 2895 2896 2897 2898 2899 2900
int drbd_send_oos(struct drbd_conf *mdev, struct drbd_request *req)
{
	struct p_block_desc p;

	p.sector  = cpu_to_be64(req->sector);
	p.blksize = cpu_to_be32(req->size);

	return drbd_send_cmd(mdev, USE_DATA_SOCKET, P_OUT_OF_SYNC, &p.head, sizeof(p));
}

P
Philipp Reisner 已提交
2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992
/*
  drbd_send distinguishes two cases:

  Packets sent via the data socket "sock"
  and packets sent via the meta data socket "msock"

		    sock                      msock
  -----------------+-------------------------+------------------------------
  timeout           conf.timeout / 2          conf.timeout / 2
  timeout action    send a ping via msock     Abort communication
					      and close all sockets
*/

/*
 * you must have down()ed the appropriate [m]sock_mutex elsewhere!
 */
int drbd_send(struct drbd_conf *mdev, struct socket *sock,
	      void *buf, size_t size, unsigned msg_flags)
{
	struct kvec iov;
	struct msghdr msg;
	int rv, sent = 0;

	if (!sock)
		return -1000;

	/* THINK  if (signal_pending) return ... ? */

	iov.iov_base = buf;
	iov.iov_len  = size;

	msg.msg_name       = NULL;
	msg.msg_namelen    = 0;
	msg.msg_control    = NULL;
	msg.msg_controllen = 0;
	msg.msg_flags      = msg_flags | MSG_NOSIGNAL;

	if (sock == mdev->data.socket) {
		mdev->ko_count = mdev->net_conf->ko_count;
		drbd_update_congested(mdev);
	}
	do {
		/* STRANGE
		 * tcp_sendmsg does _not_ use its size parameter at all ?
		 *
		 * -EAGAIN on timeout, -EINTR on signal.
		 */
/* THINK
 * do we need to block DRBD_SIG if sock == &meta.socket ??
 * otherwise wake_asender() might interrupt some send_*Ack !
 */
		rv = kernel_sendmsg(sock, &msg, &iov, 1, size);
		if (rv == -EAGAIN) {
			if (we_should_drop_the_connection(mdev, sock))
				break;
			else
				continue;
		}
		D_ASSERT(rv != 0);
		if (rv == -EINTR) {
			flush_signals(current);
			rv = 0;
		}
		if (rv < 0)
			break;
		sent += rv;
		iov.iov_base += rv;
		iov.iov_len  -= rv;
	} while (sent < size);

	if (sock == mdev->data.socket)
		clear_bit(NET_CONGESTED, &mdev->flags);

	if (rv <= 0) {
		if (rv != -EAGAIN) {
			dev_err(DEV, "%s_sendmsg returned %d\n",
			    sock == mdev->meta.socket ? "msock" : "sock",
			    rv);
			drbd_force_state(mdev, NS(conn, C_BROKEN_PIPE));
		} else
			drbd_force_state(mdev, NS(conn, C_TIMEOUT));
	}

	return sent;
}

static int drbd_open(struct block_device *bdev, fmode_t mode)
{
	struct drbd_conf *mdev = bdev->bd_disk->private_data;
	unsigned long flags;
	int rv = 0;

2993
	mutex_lock(&drbd_main_mutex);
P
Philipp Reisner 已提交
2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007
	spin_lock_irqsave(&mdev->req_lock, flags);
	/* to have a stable mdev->state.role
	 * and no race with updating open_cnt */

	if (mdev->state.role != R_PRIMARY) {
		if (mode & FMODE_WRITE)
			rv = -EROFS;
		else if (!allow_oos)
			rv = -EMEDIUMTYPE;
	}

	if (!rv)
		mdev->open_cnt++;
	spin_unlock_irqrestore(&mdev->req_lock, flags);
3008
	mutex_unlock(&drbd_main_mutex);
P
Philipp Reisner 已提交
3009 3010 3011 3012 3013 3014 3015

	return rv;
}

static int drbd_release(struct gendisk *gd, fmode_t mode)
{
	struct drbd_conf *mdev = gd->private_data;
3016
	mutex_lock(&drbd_main_mutex);
P
Philipp Reisner 已提交
3017
	mdev->open_cnt--;
3018
	mutex_unlock(&drbd_main_mutex);
P
Philipp Reisner 已提交
3019 3020 3021 3022 3023
	return 0;
}

static void drbd_set_defaults(struct drbd_conf *mdev)
{
3024 3025 3026 3027 3028 3029 3030 3031 3032
	/* This way we get a compile error when sync_conf grows,
	   and we forgot to initialize it here */
	mdev->sync_conf = (struct syncer_conf) {
		/* .rate = */		DRBD_RATE_DEF,
		/* .after = */		DRBD_AFTER_DEF,
		/* .al_extents = */	DRBD_AL_EXTENTS_DEF,
		/* .verify_alg = */	{}, 0,
		/* .cpu_mask = */	{}, 0,
		/* .csums_alg = */	{}, 0,
3033
		/* .use_rle = */	0,
3034 3035 3036 3037
		/* .on_no_data = */	DRBD_ON_NO_DATA_DEF,
		/* .c_plan_ahead = */	DRBD_C_PLAN_AHEAD_DEF,
		/* .c_delay_target = */	DRBD_C_DELAY_TARGET_DEF,
		/* .c_fill_target = */	DRBD_C_FILL_TARGET_DEF,
3038 3039
		/* .c_max_rate = */	DRBD_C_MAX_RATE_DEF,
		/* .c_min_rate = */	DRBD_C_MIN_RATE_DEF
3040 3041 3042 3043
	};

	/* Have to use that way, because the layout differs between
	   big endian and little endian */
P
Philipp Reisner 已提交
3044 3045 3046 3047 3048 3049
	mdev->state = (union drbd_state) {
		{ .role = R_SECONDARY,
		  .peer = R_UNKNOWN,
		  .conn = C_STANDALONE,
		  .disk = D_DISKLESS,
		  .pdsk = D_UNKNOWN,
3050 3051 3052
		  .susp = 0,
		  .susp_nod = 0,
		  .susp_fen = 0
P
Philipp Reisner 已提交
3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070
		} };
}

void drbd_init_set_defaults(struct drbd_conf *mdev)
{
	/* the memset(,0,) did most of this.
	 * note: only assignments, no allocation in here */

	drbd_set_defaults(mdev);

	atomic_set(&mdev->ap_bio_cnt, 0);
	atomic_set(&mdev->ap_pending_cnt, 0);
	atomic_set(&mdev->rs_pending_cnt, 0);
	atomic_set(&mdev->unacked_cnt, 0);
	atomic_set(&mdev->local_cnt, 0);
	atomic_set(&mdev->net_cnt, 0);
	atomic_set(&mdev->packet_seq, 0);
	atomic_set(&mdev->pp_in_use, 0);
3071
	atomic_set(&mdev->pp_in_use_by_net, 0);
3072
	atomic_set(&mdev->rs_sect_in, 0);
3073
	atomic_set(&mdev->rs_sect_ev, 0);
3074
	atomic_set(&mdev->ap_in_flight, 0);
3075
	atomic_set(&mdev->md_io_in_use, 0);
P
Philipp Reisner 已提交
3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100

	mutex_init(&mdev->data.mutex);
	mutex_init(&mdev->meta.mutex);
	sema_init(&mdev->data.work.s, 0);
	sema_init(&mdev->meta.work.s, 0);
	mutex_init(&mdev->state_mutex);

	spin_lock_init(&mdev->data.work.q_lock);
	spin_lock_init(&mdev->meta.work.q_lock);

	spin_lock_init(&mdev->al_lock);
	spin_lock_init(&mdev->req_lock);
	spin_lock_init(&mdev->peer_seq_lock);
	spin_lock_init(&mdev->epoch_lock);

	INIT_LIST_HEAD(&mdev->active_ee);
	INIT_LIST_HEAD(&mdev->sync_ee);
	INIT_LIST_HEAD(&mdev->done_ee);
	INIT_LIST_HEAD(&mdev->read_ee);
	INIT_LIST_HEAD(&mdev->net_ee);
	INIT_LIST_HEAD(&mdev->resync_reads);
	INIT_LIST_HEAD(&mdev->data.work.q);
	INIT_LIST_HEAD(&mdev->meta.work.q);
	INIT_LIST_HEAD(&mdev->resync_work.list);
	INIT_LIST_HEAD(&mdev->unplug_work.list);
3101
	INIT_LIST_HEAD(&mdev->go_diskless.list);
P
Philipp Reisner 已提交
3102
	INIT_LIST_HEAD(&mdev->md_sync_work.list);
3103
	INIT_LIST_HEAD(&mdev->start_resync_work.list);
P
Philipp Reisner 已提交
3104
	INIT_LIST_HEAD(&mdev->bm_io_work.w.list);
3105

3106
	mdev->resync_work.cb  = w_resync_timer;
P
Philipp Reisner 已提交
3107
	mdev->unplug_work.cb  = w_send_write_hint;
3108
	mdev->go_diskless.cb  = w_go_diskless;
P
Philipp Reisner 已提交
3109 3110
	mdev->md_sync_work.cb = w_md_sync;
	mdev->bm_io_work.w.cb = w_bitmap_io;
3111
	mdev->start_resync_work.cb = w_start_resync;
P
Philipp Reisner 已提交
3112 3113
	init_timer(&mdev->resync_timer);
	init_timer(&mdev->md_sync_timer);
3114
	init_timer(&mdev->start_resync_timer);
3115
	init_timer(&mdev->request_timer);
P
Philipp Reisner 已提交
3116 3117 3118 3119
	mdev->resync_timer.function = resync_timer_fn;
	mdev->resync_timer.data = (unsigned long) mdev;
	mdev->md_sync_timer.function = md_sync_timer_fn;
	mdev->md_sync_timer.data = (unsigned long) mdev;
3120 3121
	mdev->start_resync_timer.function = start_resync_timer_fn;
	mdev->start_resync_timer.data = (unsigned long) mdev;
3122 3123
	mdev->request_timer.function = request_timer_fn;
	mdev->request_timer.data = (unsigned long) mdev;
P
Philipp Reisner 已提交
3124 3125 3126

	init_waitqueue_head(&mdev->misc_wait);
	init_waitqueue_head(&mdev->state_wait);
3127
	init_waitqueue_head(&mdev->net_cnt_wait);
P
Philipp Reisner 已提交
3128 3129 3130 3131 3132 3133 3134 3135 3136
	init_waitqueue_head(&mdev->ee_wait);
	init_waitqueue_head(&mdev->al_wait);
	init_waitqueue_head(&mdev->seq_wait);

	drbd_thread_init(mdev, &mdev->receiver, drbdd_init);
	drbd_thread_init(mdev, &mdev->worker, drbd_worker);
	drbd_thread_init(mdev, &mdev->asender, drbd_asender);

	mdev->agreed_pro_version = PRO_VERSION_MAX;
3137
	mdev->write_ordering = WO_bdev_flush;
P
Philipp Reisner 已提交
3138
	mdev->resync_wenr = LC_FREE;
3139 3140
	mdev->peer_max_bio_size = DRBD_MAX_BIO_SIZE_SAFE;
	mdev->local_max_bio_size = DRBD_MAX_BIO_SIZE_SAFE;
P
Philipp Reisner 已提交
3141 3142 3143 3144
}

void drbd_mdev_cleanup(struct drbd_conf *mdev)
{
3145
	int i;
P
Philipp Reisner 已提交
3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161
	if (mdev->receiver.t_state != None)
		dev_err(DEV, "ASSERT FAILED: receiver t_state == %d expected 0.\n",
				mdev->receiver.t_state);

	/* no need to lock it, I'm the only thread alive */
	if (atomic_read(&mdev->current_epoch->epoch_size) !=  0)
		dev_err(DEV, "epoch_size:%d\n", atomic_read(&mdev->current_epoch->epoch_size));
	mdev->al_writ_cnt  =
	mdev->bm_writ_cnt  =
	mdev->read_cnt     =
	mdev->recv_cnt     =
	mdev->send_cnt     =
	mdev->writ_cnt     =
	mdev->p_size       =
	mdev->rs_start     =
	mdev->rs_total     =
3162 3163
	mdev->rs_failed    = 0;
	mdev->rs_last_events = 0;
3164
	mdev->rs_last_sect_ev = 0;
3165 3166 3167 3168
	for (i = 0; i < DRBD_SYNC_MARKS; i++) {
		mdev->rs_mark_left[i] = 0;
		mdev->rs_mark_time[i] = 0;
	}
P
Philipp Reisner 已提交
3169 3170 3171 3172 3173
	D_ASSERT(mdev->net_conf == NULL);

	drbd_set_my_capacity(mdev, 0);
	if (mdev->bitmap) {
		/* maybe never allocated. */
3174
		drbd_bm_resize(mdev, 0, 1);
P
Philipp Reisner 已提交
3175 3176 3177 3178
		drbd_bm_cleanup(mdev);
	}

	drbd_free_resources(mdev);
3179
	clear_bit(AL_SUSPENDED, &mdev->flags);
P
Philipp Reisner 已提交
3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194

	/*
	 * currently we drbd_init_ee only on module load, so
	 * we may do drbd_release_ee only on module unload!
	 */
	D_ASSERT(list_empty(&mdev->active_ee));
	D_ASSERT(list_empty(&mdev->sync_ee));
	D_ASSERT(list_empty(&mdev->done_ee));
	D_ASSERT(list_empty(&mdev->read_ee));
	D_ASSERT(list_empty(&mdev->net_ee));
	D_ASSERT(list_empty(&mdev->resync_reads));
	D_ASSERT(list_empty(&mdev->data.work.q));
	D_ASSERT(list_empty(&mdev->meta.work.q));
	D_ASSERT(list_empty(&mdev->resync_work.list));
	D_ASSERT(list_empty(&mdev->unplug_work.list));
3195
	D_ASSERT(list_empty(&mdev->go_diskless.list));
3196 3197

	drbd_set_defaults(mdev);
P
Philipp Reisner 已提交
3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239
}


static void drbd_destroy_mempools(void)
{
	struct page *page;

	while (drbd_pp_pool) {
		page = drbd_pp_pool;
		drbd_pp_pool = (struct page *)page_private(page);
		__free_page(page);
		drbd_pp_vacant--;
	}

	/* D_ASSERT(atomic_read(&drbd_pp_vacant)==0); */

	if (drbd_ee_mempool)
		mempool_destroy(drbd_ee_mempool);
	if (drbd_request_mempool)
		mempool_destroy(drbd_request_mempool);
	if (drbd_ee_cache)
		kmem_cache_destroy(drbd_ee_cache);
	if (drbd_request_cache)
		kmem_cache_destroy(drbd_request_cache);
	if (drbd_bm_ext_cache)
		kmem_cache_destroy(drbd_bm_ext_cache);
	if (drbd_al_ext_cache)
		kmem_cache_destroy(drbd_al_ext_cache);

	drbd_ee_mempool      = NULL;
	drbd_request_mempool = NULL;
	drbd_ee_cache        = NULL;
	drbd_request_cache   = NULL;
	drbd_bm_ext_cache    = NULL;
	drbd_al_ext_cache    = NULL;

	return;
}

static int drbd_create_mempools(void)
{
	struct page *page;
3240
	const int number = (DRBD_MAX_BIO_SIZE/PAGE_SIZE) * minor_count;
P
Philipp Reisner 已提交
3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279
	int i;

	/* prepare our caches and mempools */
	drbd_request_mempool = NULL;
	drbd_ee_cache        = NULL;
	drbd_request_cache   = NULL;
	drbd_bm_ext_cache    = NULL;
	drbd_al_ext_cache    = NULL;
	drbd_pp_pool         = NULL;

	/* caches */
	drbd_request_cache = kmem_cache_create(
		"drbd_req", sizeof(struct drbd_request), 0, 0, NULL);
	if (drbd_request_cache == NULL)
		goto Enomem;

	drbd_ee_cache = kmem_cache_create(
		"drbd_ee", sizeof(struct drbd_epoch_entry), 0, 0, NULL);
	if (drbd_ee_cache == NULL)
		goto Enomem;

	drbd_bm_ext_cache = kmem_cache_create(
		"drbd_bm", sizeof(struct bm_extent), 0, 0, NULL);
	if (drbd_bm_ext_cache == NULL)
		goto Enomem;

	drbd_al_ext_cache = kmem_cache_create(
		"drbd_al", sizeof(struct lc_element), 0, 0, NULL);
	if (drbd_al_ext_cache == NULL)
		goto Enomem;

	/* mempools */
	drbd_request_mempool = mempool_create(number,
		mempool_alloc_slab, mempool_free_slab, drbd_request_cache);
	if (drbd_request_mempool == NULL)
		goto Enomem;

	drbd_ee_mempool = mempool_create(number,
		mempool_alloc_slab, mempool_free_slab, drbd_ee_cache);
3280
	if (drbd_ee_mempool == NULL)
P
Philipp Reisner 已提交
3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349
		goto Enomem;

	/* drbd's page pool */
	spin_lock_init(&drbd_pp_lock);

	for (i = 0; i < number; i++) {
		page = alloc_page(GFP_HIGHUSER);
		if (!page)
			goto Enomem;
		set_page_private(page, (unsigned long)drbd_pp_pool);
		drbd_pp_pool = page;
	}
	drbd_pp_vacant = number;

	return 0;

Enomem:
	drbd_destroy_mempools(); /* in case we allocated some */
	return -ENOMEM;
}

static int drbd_notify_sys(struct notifier_block *this, unsigned long code,
	void *unused)
{
	/* just so we have it.  you never know what interesting things we
	 * might want to do here some day...
	 */

	return NOTIFY_DONE;
}

static struct notifier_block drbd_notifier = {
	.notifier_call = drbd_notify_sys,
};

static void drbd_release_ee_lists(struct drbd_conf *mdev)
{
	int rr;

	rr = drbd_release_ee(mdev, &mdev->active_ee);
	if (rr)
		dev_err(DEV, "%d EEs in active list found!\n", rr);

	rr = drbd_release_ee(mdev, &mdev->sync_ee);
	if (rr)
		dev_err(DEV, "%d EEs in sync list found!\n", rr);

	rr = drbd_release_ee(mdev, &mdev->read_ee);
	if (rr)
		dev_err(DEV, "%d EEs in read list found!\n", rr);

	rr = drbd_release_ee(mdev, &mdev->done_ee);
	if (rr)
		dev_err(DEV, "%d EEs in done list found!\n", rr);

	rr = drbd_release_ee(mdev, &mdev->net_ee);
	if (rr)
		dev_err(DEV, "%d EEs in net list found!\n", rr);
}

/* caution. no locking.
 * currently only used from module cleanup code. */
static void drbd_delete_device(unsigned int minor)
{
	struct drbd_conf *mdev = minor_to_mdev(minor);

	if (!mdev)
		return;

3350 3351
	del_timer_sync(&mdev->request_timer);

P
Philipp Reisner 已提交
3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376
	/* paranoia asserts */
	if (mdev->open_cnt != 0)
		dev_err(DEV, "open_cnt = %d in %s:%u", mdev->open_cnt,
				__FILE__ , __LINE__);

	ERR_IF (!list_empty(&mdev->data.work.q)) {
		struct list_head *lp;
		list_for_each(lp, &mdev->data.work.q) {
			dev_err(DEV, "lp = %p\n", lp);
		}
	};
	/* end paranoia asserts */

	del_gendisk(mdev->vdisk);

	/* cleanup stuff that may have been allocated during
	 * device (re-)configuration or state changes */

	if (mdev->this_bdev)
		bdput(mdev->this_bdev);

	drbd_free_resources(mdev);

	drbd_release_ee_lists(mdev);

B
Bart Van Assche 已提交
3377
	/* should be freed on disconnect? */
P
Philipp Reisner 已提交
3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405
	kfree(mdev->ee_hash);
	/*
	mdev->ee_hash_s = 0;
	mdev->ee_hash = NULL;
	*/

	lc_destroy(mdev->act_log);
	lc_destroy(mdev->resync);

	kfree(mdev->p_uuid);
	/* mdev->p_uuid = NULL; */

	kfree(mdev->int_dig_out);
	kfree(mdev->int_dig_in);
	kfree(mdev->int_dig_vv);

	/* cleanup the rest that has been
	 * allocated from drbd_new_device
	 * and actually free the mdev itself */
	drbd_free_mdev(mdev);
}

static void drbd_cleanup(void)
{
	unsigned int i;

	unregister_reboot_notifier(&drbd_notifier);

3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416
	/* first remove proc,
	 * drbdsetup uses it's presence to detect
	 * whether DRBD is loaded.
	 * If we would get stuck in proc removal,
	 * but have netlink already deregistered,
	 * some drbdsetup commands may wait forever
	 * for an answer.
	 */
	if (drbd_proc)
		remove_proc_entry("drbd", NULL);

P
Philipp Reisner 已提交
3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446
	drbd_nl_cleanup();

	if (minor_table) {
		i = minor_count;
		while (i--)
			drbd_delete_device(i);
		drbd_destroy_mempools();
	}

	kfree(minor_table);

	unregister_blkdev(DRBD_MAJOR, "drbd");

	printk(KERN_INFO "drbd: module cleanup done.\n");
}

/**
 * drbd_congested() - Callback for pdflush
 * @congested_data:	User data
 * @bdi_bits:		Bits pdflush is currently interested in
 *
 * Returns 1<<BDI_async_congested and/or 1<<BDI_sync_congested if we are congested.
 */
static int drbd_congested(void *congested_data, int bdi_bits)
{
	struct drbd_conf *mdev = congested_data;
	struct request_queue *q;
	char reason = '-';
	int r = 0;

3447
	if (!may_inc_ap_bio(mdev)) {
P
Philipp Reisner 已提交
3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499
		/* DRBD has frozen IO */
		r = bdi_bits;
		reason = 'd';
		goto out;
	}

	if (get_ldev(mdev)) {
		q = bdev_get_queue(mdev->ldev->backing_bdev);
		r = bdi_congested(&q->backing_dev_info, bdi_bits);
		put_ldev(mdev);
		if (r)
			reason = 'b';
	}

	if (bdi_bits & (1 << BDI_async_congested) && test_bit(NET_CONGESTED, &mdev->flags)) {
		r |= (1 << BDI_async_congested);
		reason = reason == 'b' ? 'a' : 'n';
	}

out:
	mdev->congestion_reason = reason;
	return r;
}

struct drbd_conf *drbd_new_device(unsigned int minor)
{
	struct drbd_conf *mdev;
	struct gendisk *disk;
	struct request_queue *q;

	/* GFP_KERNEL, we are outside of all write-out paths */
	mdev = kzalloc(sizeof(struct drbd_conf), GFP_KERNEL);
	if (!mdev)
		return NULL;
	if (!zalloc_cpumask_var(&mdev->cpu_mask, GFP_KERNEL))
		goto out_no_cpumask;

	mdev->minor = minor;

	drbd_init_set_defaults(mdev);

	q = blk_alloc_queue(GFP_KERNEL);
	if (!q)
		goto out_no_q;
	mdev->rq_queue = q;
	q->queuedata   = mdev;

	disk = alloc_disk(1);
	if (!disk)
		goto out_no_disk;
	mdev->vdisk = disk;

3500
	set_disk_ro(disk, true);
P
Philipp Reisner 已提交
3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515

	disk->queue = q;
	disk->major = DRBD_MAJOR;
	disk->first_minor = minor;
	disk->fops = &drbd_ops;
	sprintf(disk->disk_name, "drbd%d", minor);
	disk->private_data = mdev;

	mdev->this_bdev = bdget(MKDEV(DRBD_MAJOR, minor));
	/* we have no partitions. we contain only ourselves. */
	mdev->this_bdev->bd_contains = mdev->this_bdev;

	q->backing_dev_info.congested_fn = drbd_congested;
	q->backing_dev_info.congested_data = mdev;

3516
	blk_queue_make_request(q, drbd_make_request);
3517 3518 3519
	/* Setting the max_hw_sectors to an odd value of 8kibyte here
	   This triggers a max_bio_size message upon first attach or connect */
	blk_queue_max_hw_sectors(q, DRBD_MAX_BIO_SIZE_SAFE >> 8);
P
Philipp Reisner 已提交
3520 3521
	blk_queue_bounce_limit(q, BLK_BOUNCE_ANY);
	blk_queue_merge_bvec(q, drbd_merge_bvec);
J
Jens Axboe 已提交
3522
	q->queue_lock = &mdev->req_lock;
P
Philipp Reisner 已提交
3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580

	mdev->md_io_page = alloc_page(GFP_KERNEL);
	if (!mdev->md_io_page)
		goto out_no_io_page;

	if (drbd_bm_init(mdev))
		goto out_no_bitmap;
	/* no need to lock access, we are still initializing this minor device. */
	if (!tl_init(mdev))
		goto out_no_tl;

	mdev->app_reads_hash = kzalloc(APP_R_HSIZE*sizeof(void *), GFP_KERNEL);
	if (!mdev->app_reads_hash)
		goto out_no_app_reads;

	mdev->current_epoch = kzalloc(sizeof(struct drbd_epoch), GFP_KERNEL);
	if (!mdev->current_epoch)
		goto out_no_epoch;

	INIT_LIST_HEAD(&mdev->current_epoch->list);
	mdev->epochs = 1;

	return mdev;

/* out_whatever_else:
	kfree(mdev->current_epoch); */
out_no_epoch:
	kfree(mdev->app_reads_hash);
out_no_app_reads:
	tl_cleanup(mdev);
out_no_tl:
	drbd_bm_cleanup(mdev);
out_no_bitmap:
	__free_page(mdev->md_io_page);
out_no_io_page:
	put_disk(disk);
out_no_disk:
	blk_cleanup_queue(q);
out_no_q:
	free_cpumask_var(mdev->cpu_mask);
out_no_cpumask:
	kfree(mdev);
	return NULL;
}

/* counterpart of drbd_new_device.
 * last part of drbd_delete_device. */
void drbd_free_mdev(struct drbd_conf *mdev)
{
	kfree(mdev->current_epoch);
	kfree(mdev->app_reads_hash);
	tl_cleanup(mdev);
	if (mdev->bitmap) /* should no longer be there. */
		drbd_bm_cleanup(mdev);
	__free_page(mdev->md_io_page);
	put_disk(mdev->vdisk);
	blk_cleanup_queue(mdev->rq_queue);
	free_cpumask_var(mdev->cpu_mask);
3581
	drbd_free_tl_hash(mdev);
P
Philipp Reisner 已提交
3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596
	kfree(mdev);
}


int __init drbd_init(void)
{
	int err;

	if (sizeof(struct p_handshake) != 80) {
		printk(KERN_ERR
		       "drbd: never change the size or layout "
		       "of the HandShake packet.\n");
		return -EINVAL;
	}

3597
	if (minor_count < DRBD_MINOR_COUNT_MIN || minor_count > DRBD_MINOR_COUNT_MAX) {
P
Philipp Reisner 已提交
3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637
		printk(KERN_ERR
			"drbd: invalid minor_count (%d)\n", minor_count);
#ifdef MODULE
		return -EINVAL;
#else
		minor_count = 8;
#endif
	}

	err = drbd_nl_init();
	if (err)
		return err;

	err = register_blkdev(DRBD_MAJOR, "drbd");
	if (err) {
		printk(KERN_ERR
		       "drbd: unable to register block device major %d\n",
		       DRBD_MAJOR);
		return err;
	}

	register_reboot_notifier(&drbd_notifier);

	/*
	 * allocate all necessary structs
	 */
	err = -ENOMEM;

	init_waitqueue_head(&drbd_pp_wait);

	drbd_proc = NULL; /* play safe for drbd_cleanup */
	minor_table = kzalloc(sizeof(struct drbd_conf *)*minor_count,
				GFP_KERNEL);
	if (!minor_table)
		goto Enomem;

	err = drbd_create_mempools();
	if (err)
		goto Enomem;

3638
	drbd_proc = proc_create_data("drbd", S_IFREG | S_IRUGO , NULL, &drbd_proc_fops, NULL);
P
Philipp Reisner 已提交
3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670
	if (!drbd_proc)	{
		printk(KERN_ERR "drbd: unable to register proc file\n");
		goto Enomem;
	}

	rwlock_init(&global_state_lock);

	printk(KERN_INFO "drbd: initialized. "
	       "Version: " REL_VERSION " (api:%d/proto:%d-%d)\n",
	       API_VERSION, PRO_VERSION_MIN, PRO_VERSION_MAX);
	printk(KERN_INFO "drbd: %s\n", drbd_buildtag());
	printk(KERN_INFO "drbd: registered as block device major %d\n",
		DRBD_MAJOR);
	printk(KERN_INFO "drbd: minor_table @ 0x%p\n", minor_table);

	return 0; /* Success! */

Enomem:
	drbd_cleanup();
	if (err == -ENOMEM)
		/* currently always the case */
		printk(KERN_ERR "drbd: ran out of memory\n");
	else
		printk(KERN_ERR "drbd: initialization failure\n");
	return err;
}

void drbd_free_bc(struct drbd_backing_dev *ldev)
{
	if (ldev == NULL)
		return;

3671 3672
	blkdev_put(ldev->backing_bdev, FMODE_READ | FMODE_WRITE | FMODE_EXCL);
	blkdev_put(ldev->md_bdev, FMODE_READ | FMODE_WRITE | FMODE_EXCL);
P
Philipp Reisner 已提交
3673 3674 3675 3676 3677 3678 3679

	kfree(ldev);
}

void drbd_free_sock(struct drbd_conf *mdev)
{
	if (mdev->data.socket) {
3680
		mutex_lock(&mdev->data.mutex);
P
Philipp Reisner 已提交
3681 3682 3683
		kernel_sock_shutdown(mdev->data.socket, SHUT_RDWR);
		sock_release(mdev->data.socket);
		mdev->data.socket = NULL;
3684
		mutex_unlock(&mdev->data.mutex);
P
Philipp Reisner 已提交
3685 3686
	}
	if (mdev->meta.socket) {
3687
		mutex_lock(&mdev->meta.mutex);
P
Philipp Reisner 已提交
3688 3689 3690
		kernel_sock_shutdown(mdev->meta.socket, SHUT_RDWR);
		sock_release(mdev->meta.socket);
		mdev->meta.socket = NULL;
3691
		mutex_unlock(&mdev->meta.mutex);
P
Philipp Reisner 已提交
3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730
	}
}


void drbd_free_resources(struct drbd_conf *mdev)
{
	crypto_free_hash(mdev->csums_tfm);
	mdev->csums_tfm = NULL;
	crypto_free_hash(mdev->verify_tfm);
	mdev->verify_tfm = NULL;
	crypto_free_hash(mdev->cram_hmac_tfm);
	mdev->cram_hmac_tfm = NULL;
	crypto_free_hash(mdev->integrity_w_tfm);
	mdev->integrity_w_tfm = NULL;
	crypto_free_hash(mdev->integrity_r_tfm);
	mdev->integrity_r_tfm = NULL;

	drbd_free_sock(mdev);

	__no_warn(local,
		  drbd_free_bc(mdev->ldev);
		  mdev->ldev = NULL;);
}

/* meta data management */

struct meta_data_on_disk {
	u64 la_size;           /* last agreed size. */
	u64 uuid[UI_SIZE];   /* UUIDs. */
	u64 device_uuid;
	u64 reserved_u64_1;
	u32 flags;             /* MDF */
	u32 magic;
	u32 md_size_sect;
	u32 al_offset;         /* offset to this block */
	u32 al_nr_extents;     /* important for restoring the AL */
	      /* `-- act_log->nr_elements <-- sync_conf.al_extents */
	u32 bm_offset;         /* offset to the bitmap, from here */
	u32 bm_bytes_per_bit;  /* BM_BLOCK_SIZE */
3731 3732
	u32 la_peer_max_bio_size;   /* last peer max_bio_size */
	u32 reserved_u32[3];
P
Philipp Reisner 已提交
3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745

} __packed;

/**
 * drbd_md_sync() - Writes the meta data super block if the MD_DIRTY flag bit is set
 * @mdev:	DRBD device.
 */
void drbd_md_sync(struct drbd_conf *mdev)
{
	struct meta_data_on_disk *buffer;
	sector_t sector;
	int i;

3746 3747
	del_timer(&mdev->md_sync_timer);
	/* timer may be rearmed by drbd_md_mark_dirty() now. */
P
Philipp Reisner 已提交
3748 3749 3750 3751 3752 3753 3754 3755
	if (!test_and_clear_bit(MD_DIRTY, &mdev->flags))
		return;

	/* We use here D_FAILED and not D_ATTACHING because we try to write
	 * metadata even if we detach due to a disk failure! */
	if (!get_ldev_if_state(mdev, D_FAILED))
		return;

3756 3757 3758 3759
	buffer = drbd_md_get_buffer(mdev);
	if (!buffer)
		goto out;

P
Philipp Reisner 已提交
3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774
	memset(buffer, 0, 512);

	buffer->la_size = cpu_to_be64(drbd_get_capacity(mdev->this_bdev));
	for (i = UI_CURRENT; i < UI_SIZE; i++)
		buffer->uuid[i] = cpu_to_be64(mdev->ldev->md.uuid[i]);
	buffer->flags = cpu_to_be32(mdev->ldev->md.flags);
	buffer->magic = cpu_to_be32(DRBD_MD_MAGIC);

	buffer->md_size_sect  = cpu_to_be32(mdev->ldev->md.md_size_sect);
	buffer->al_offset     = cpu_to_be32(mdev->ldev->md.al_offset);
	buffer->al_nr_extents = cpu_to_be32(mdev->act_log->nr_elements);
	buffer->bm_bytes_per_bit = cpu_to_be32(BM_BLOCK_SIZE);
	buffer->device_uuid = cpu_to_be64(mdev->ldev->md.device_uuid);

	buffer->bm_offset = cpu_to_be32(mdev->ldev->md.bm_offset);
3775
	buffer->la_peer_max_bio_size = cpu_to_be32(mdev->peer_max_bio_size);
P
Philipp Reisner 已提交
3776 3777 3778 3779

	D_ASSERT(drbd_md_ss__(mdev, mdev->ldev) == mdev->ldev->md.md_offset);
	sector = mdev->ldev->md.md_offset;

3780
	if (!drbd_md_sync_page_io(mdev, mdev->ldev, sector, WRITE)) {
P
Philipp Reisner 已提交
3781 3782
		/* this was a try anyways ... */
		dev_err(DEV, "meta data update failed!\n");
3783
		drbd_chk_io_error(mdev, 1, true);
P
Philipp Reisner 已提交
3784 3785 3786 3787 3788 3789
	}

	/* Update mdev->ldev->md.la_size_sect,
	 * since we updated it on metadata. */
	mdev->ldev->md.la_size_sect = drbd_get_capacity(mdev->this_bdev);

3790 3791
	drbd_md_put_buffer(mdev);
out:
P
Philipp Reisner 已提交
3792 3793 3794 3795 3796 3797 3798 3799
	put_ldev(mdev);
}

/**
 * drbd_md_read() - Reads in the meta data super block
 * @mdev:	DRBD device.
 * @bdev:	Device from which the meta data should be read in.
 *
3800
 * Return 0 (NO_ERROR) on success, and an enum drbd_ret_code in case
P
Philipp Reisner 已提交
3801 3802 3803 3804 3805 3806 3807 3808 3809 3810
 * something goes wrong.  Currently only: ERR_IO_MD_DISK, ERR_MD_INVALID.
 */
int drbd_md_read(struct drbd_conf *mdev, struct drbd_backing_dev *bdev)
{
	struct meta_data_on_disk *buffer;
	int i, rv = NO_ERROR;

	if (!get_ldev_if_state(mdev, D_ATTACHING))
		return ERR_IO_MD_DISK;

3811 3812 3813
	buffer = drbd_md_get_buffer(mdev);
	if (!buffer)
		goto out;
P
Philipp Reisner 已提交
3814 3815

	if (!drbd_md_sync_page_io(mdev, bdev, bdev->md.md_offset, READ)) {
L
Lucas De Marchi 已提交
3816
		/* NOTE: can't do normal error processing here as this is
P
Philipp Reisner 已提交
3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860
		   called BEFORE disk is attached */
		dev_err(DEV, "Error while reading metadata.\n");
		rv = ERR_IO_MD_DISK;
		goto err;
	}

	if (be32_to_cpu(buffer->magic) != DRBD_MD_MAGIC) {
		dev_err(DEV, "Error while reading metadata, magic not found.\n");
		rv = ERR_MD_INVALID;
		goto err;
	}
	if (be32_to_cpu(buffer->al_offset) != bdev->md.al_offset) {
		dev_err(DEV, "unexpected al_offset: %d (expected %d)\n",
		    be32_to_cpu(buffer->al_offset), bdev->md.al_offset);
		rv = ERR_MD_INVALID;
		goto err;
	}
	if (be32_to_cpu(buffer->bm_offset) != bdev->md.bm_offset) {
		dev_err(DEV, "unexpected bm_offset: %d (expected %d)\n",
		    be32_to_cpu(buffer->bm_offset), bdev->md.bm_offset);
		rv = ERR_MD_INVALID;
		goto err;
	}
	if (be32_to_cpu(buffer->md_size_sect) != bdev->md.md_size_sect) {
		dev_err(DEV, "unexpected md_size: %u (expected %u)\n",
		    be32_to_cpu(buffer->md_size_sect), bdev->md.md_size_sect);
		rv = ERR_MD_INVALID;
		goto err;
	}

	if (be32_to_cpu(buffer->bm_bytes_per_bit) != BM_BLOCK_SIZE) {
		dev_err(DEV, "unexpected bm_bytes_per_bit: %u (expected %u)\n",
		    be32_to_cpu(buffer->bm_bytes_per_bit), BM_BLOCK_SIZE);
		rv = ERR_MD_INVALID;
		goto err;
	}

	bdev->md.la_size_sect = be64_to_cpu(buffer->la_size);
	for (i = UI_CURRENT; i < UI_SIZE; i++)
		bdev->md.uuid[i] = be64_to_cpu(buffer->uuid[i]);
	bdev->md.flags = be32_to_cpu(buffer->flags);
	mdev->sync_conf.al_extents = be32_to_cpu(buffer->al_nr_extents);
	bdev->md.device_uuid = be64_to_cpu(buffer->device_uuid);

3861 3862 3863 3864 3865 3866 3867 3868 3869
	spin_lock_irq(&mdev->req_lock);
	if (mdev->state.conn < C_CONNECTED) {
		int peer;
		peer = be32_to_cpu(buffer->la_peer_max_bio_size);
		peer = max_t(int, peer, DRBD_MAX_BIO_SIZE_SAFE);
		mdev->peer_max_bio_size = peer;
	}
	spin_unlock_irq(&mdev->req_lock);

P
Philipp Reisner 已提交
3870 3871 3872 3873
	if (mdev->sync_conf.al_extents < 7)
		mdev->sync_conf.al_extents = 127;

 err:
3874 3875
	drbd_md_put_buffer(mdev);
 out:
P
Philipp Reisner 已提交
3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888
	put_ldev(mdev);

	return rv;
}

/**
 * drbd_md_mark_dirty() - Mark meta data super block as dirty
 * @mdev:	DRBD device.
 *
 * Call this function if you change anything that should be written to
 * the meta-data super block. This function sets MD_DIRTY, and starts a
 * timer that ensures that within five seconds you have to call drbd_md_sync().
 */
3889
#ifdef DEBUG
3890 3891 3892 3893 3894 3895 3896 3897 3898
void drbd_md_mark_dirty_(struct drbd_conf *mdev, unsigned int line, const char *func)
{
	if (!test_and_set_bit(MD_DIRTY, &mdev->flags)) {
		mod_timer(&mdev->md_sync_timer, jiffies + HZ);
		mdev->last_md_mark_dirty.line = line;
		mdev->last_md_mark_dirty.func = func;
	}
}
#else
P
Philipp Reisner 已提交
3899 3900
void drbd_md_mark_dirty(struct drbd_conf *mdev)
{
3901
	if (!test_and_set_bit(MD_DIRTY, &mdev->flags))
3902
		mod_timer(&mdev->md_sync_timer, jiffies + 5*HZ);
P
Philipp Reisner 已提交
3903
}
3904
#endif
P
Philipp Reisner 已提交
3905 3906 3907 3908 3909

static void drbd_uuid_move_history(struct drbd_conf *mdev) __must_hold(local)
{
	int i;

3910
	for (i = UI_HISTORY_START; i < UI_HISTORY_END; i++)
P
Philipp Reisner 已提交
3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948
		mdev->ldev->md.uuid[i+1] = mdev->ldev->md.uuid[i];
}

void _drbd_uuid_set(struct drbd_conf *mdev, int idx, u64 val) __must_hold(local)
{
	if (idx == UI_CURRENT) {
		if (mdev->state.role == R_PRIMARY)
			val |= 1;
		else
			val &= ~((u64)1);

		drbd_set_ed_uuid(mdev, val);
	}

	mdev->ldev->md.uuid[idx] = val;
	drbd_md_mark_dirty(mdev);
}


void drbd_uuid_set(struct drbd_conf *mdev, int idx, u64 val) __must_hold(local)
{
	if (mdev->ldev->md.uuid[idx]) {
		drbd_uuid_move_history(mdev);
		mdev->ldev->md.uuid[UI_HISTORY_START] = mdev->ldev->md.uuid[idx];
	}
	_drbd_uuid_set(mdev, idx, val);
}

/**
 * drbd_uuid_new_current() - Creates a new current UUID
 * @mdev:	DRBD device.
 *
 * Creates a new current UUID, and rotates the old current UUID into
 * the bitmap slot. Causes an incremental resync upon next connect.
 */
void drbd_uuid_new_current(struct drbd_conf *mdev) __must_hold(local)
{
	u64 val;
3949 3950 3951 3952
	unsigned long long bm_uuid = mdev->ldev->md.uuid[UI_BITMAP];

	if (bm_uuid)
		dev_warn(DEV, "bm UUID was already set: %llX\n", bm_uuid);
P
Philipp Reisner 已提交
3953 3954 3955 3956 3957

	mdev->ldev->md.uuid[UI_BITMAP] = mdev->ldev->md.uuid[UI_CURRENT];

	get_random_bytes(&val, sizeof(u64));
	_drbd_uuid_set(mdev, UI_CURRENT, val);
3958
	drbd_print_uuids(mdev, "new current UUID");
3959 3960
	/* get it to stable storage _now_ */
	drbd_md_sync(mdev);
P
Philipp Reisner 已提交
3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972
}

void drbd_uuid_set_bm(struct drbd_conf *mdev, u64 val) __must_hold(local)
{
	if (mdev->ldev->md.uuid[UI_BITMAP] == 0 && val == 0)
		return;

	if (val == 0) {
		drbd_uuid_move_history(mdev);
		mdev->ldev->md.uuid[UI_HISTORY_START] = mdev->ldev->md.uuid[UI_BITMAP];
		mdev->ldev->md.uuid[UI_BITMAP] = 0;
	} else {
3973 3974 3975
		unsigned long long bm_uuid = mdev->ldev->md.uuid[UI_BITMAP];
		if (bm_uuid)
			dev_warn(DEV, "bm UUID was already set: %llX\n", bm_uuid);
P
Philipp Reisner 已提交
3976

3977
		mdev->ldev->md.uuid[UI_BITMAP] = val & ~((u64)1);
P
Philipp Reisner 已提交
3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019
	}
	drbd_md_mark_dirty(mdev);
}

/**
 * drbd_bmio_set_n_write() - io_fn for drbd_queue_bitmap_io() or drbd_bitmap_io()
 * @mdev:	DRBD device.
 *
 * Sets all bits in the bitmap and writes the whole bitmap to stable storage.
 */
int drbd_bmio_set_n_write(struct drbd_conf *mdev)
{
	int rv = -EIO;

	if (get_ldev_if_state(mdev, D_ATTACHING)) {
		drbd_md_set_flag(mdev, MDF_FULL_SYNC);
		drbd_md_sync(mdev);
		drbd_bm_set_all(mdev);

		rv = drbd_bm_write(mdev);

		if (!rv) {
			drbd_md_clear_flag(mdev, MDF_FULL_SYNC);
			drbd_md_sync(mdev);
		}

		put_ldev(mdev);
	}

	return rv;
}

/**
 * drbd_bmio_clear_n_write() - io_fn for drbd_queue_bitmap_io() or drbd_bitmap_io()
 * @mdev:	DRBD device.
 *
 * Clears all bits in the bitmap and writes the whole bitmap to stable storage.
 */
int drbd_bmio_clear_n_write(struct drbd_conf *mdev)
{
	int rv = -EIO;

4020
	drbd_resume_al(mdev);
P
Philipp Reisner 已提交
4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032
	if (get_ldev_if_state(mdev, D_ATTACHING)) {
		drbd_bm_clear_all(mdev);
		rv = drbd_bm_write(mdev);
		put_ldev(mdev);
	}

	return rv;
}

static int w_bitmap_io(struct drbd_conf *mdev, struct drbd_work *w, int unused)
{
	struct bm_io_work *work = container_of(w, struct bm_io_work, w);
4033
	int rv = -EIO;
P
Philipp Reisner 已提交
4034 4035 4036

	D_ASSERT(atomic_read(&mdev->ap_bio_cnt) == 0);

4037
	if (get_ldev(mdev)) {
4038
		drbd_bm_lock(mdev, work->why, work->flags);
4039 4040 4041 4042
		rv = work->io_fn(mdev);
		drbd_bm_unlock(mdev);
		put_ldev(mdev);
	}
P
Philipp Reisner 已提交
4043 4044

	clear_bit(BITMAP_IO, &mdev->flags);
4045
	smp_mb__after_clear_bit();
P
Philipp Reisner 已提交
4046 4047 4048 4049 4050 4051 4052
	wake_up(&mdev->misc_wait);

	if (work->done)
		work->done(mdev, rv);

	clear_bit(BITMAP_IO_QUEUED, &mdev->flags);
	work->why = NULL;
4053
	work->flags = 0;
P
Philipp Reisner 已提交
4054 4055 4056 4057

	return 1;
}

4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074
void drbd_ldev_destroy(struct drbd_conf *mdev)
{
	lc_destroy(mdev->resync);
	mdev->resync = NULL;
	lc_destroy(mdev->act_log);
	mdev->act_log = NULL;
	__no_warn(local,
		drbd_free_bc(mdev->ldev);
		mdev->ldev = NULL;);

	if (mdev->md_io_tmpp) {
		__free_page(mdev->md_io_tmpp);
		mdev->md_io_tmpp = NULL;
	}
	clear_bit(GO_DISKLESS, &mdev->flags);
}

4075 4076 4077
static int w_go_diskless(struct drbd_conf *mdev, struct drbd_work *w, int unused)
{
	D_ASSERT(mdev->state.disk == D_FAILED);
4078 4079
	/* we cannot assert local_cnt == 0 here, as get_ldev_if_state will
	 * inc/dec it frequently. Once we are D_DISKLESS, no one will touch
4080 4081
	 * the protected members anymore, though, so once put_ldev reaches zero
	 * again, it will be safe to free them. */
4082 4083 4084 4085 4086 4087 4088 4089
	drbd_force_state(mdev, NS(disk, D_DISKLESS));
	return 1;
}

void drbd_go_diskless(struct drbd_conf *mdev)
{
	D_ASSERT(mdev->state.disk == D_FAILED);
	if (!test_and_set_bit(GO_DISKLESS, &mdev->flags))
4090
		drbd_queue_work(&mdev->data.work, &mdev->go_diskless);
4091 4092
}

P
Philipp Reisner 已提交
4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107
/**
 * drbd_queue_bitmap_io() - Queues an IO operation on the whole bitmap
 * @mdev:	DRBD device.
 * @io_fn:	IO callback to be called when bitmap IO is possible
 * @done:	callback to be called after the bitmap IO was performed
 * @why:	Descriptive text of the reason for doing the IO
 *
 * While IO on the bitmap happens we freeze application IO thus we ensure
 * that drbd_set_out_of_sync() can not be called. This function MAY ONLY be
 * called from worker context. It MUST NOT be used while a previous such
 * work is still pending!
 */
void drbd_queue_bitmap_io(struct drbd_conf *mdev,
			  int (*io_fn)(struct drbd_conf *),
			  void (*done)(struct drbd_conf *, int),
4108
			  char *why, enum bm_flag flags)
P
Philipp Reisner 已提交
4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121
{
	D_ASSERT(current == mdev->worker.task);

	D_ASSERT(!test_bit(BITMAP_IO_QUEUED, &mdev->flags));
	D_ASSERT(!test_bit(BITMAP_IO, &mdev->flags));
	D_ASSERT(list_empty(&mdev->bm_io_work.w.list));
	if (mdev->bm_io_work.why)
		dev_err(DEV, "FIXME going to queue '%s' but '%s' still pending?\n",
			why, mdev->bm_io_work.why);

	mdev->bm_io_work.io_fn = io_fn;
	mdev->bm_io_work.done = done;
	mdev->bm_io_work.why = why;
4122
	mdev->bm_io_work.flags = flags;
P
Philipp Reisner 已提交
4123

4124
	spin_lock_irq(&mdev->req_lock);
P
Philipp Reisner 已提交
4125 4126
	set_bit(BITMAP_IO, &mdev->flags);
	if (atomic_read(&mdev->ap_bio_cnt) == 0) {
4127
		if (!test_and_set_bit(BITMAP_IO_QUEUED, &mdev->flags))
P
Philipp Reisner 已提交
4128 4129
			drbd_queue_work(&mdev->data.work, &mdev->bm_io_work.w);
	}
4130
	spin_unlock_irq(&mdev->req_lock);
P
Philipp Reisner 已提交
4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141
}

/**
 * drbd_bitmap_io() -  Does an IO operation on the whole bitmap
 * @mdev:	DRBD device.
 * @io_fn:	IO callback to be called when bitmap IO is possible
 * @why:	Descriptive text of the reason for doing the IO
 *
 * freezes application IO while that the actual IO operations runs. This
 * functions MAY NOT be called from worker context.
 */
4142 4143
int drbd_bitmap_io(struct drbd_conf *mdev, int (*io_fn)(struct drbd_conf *),
		char *why, enum bm_flag flags)
P
Philipp Reisner 已提交
4144 4145 4146 4147 4148
{
	int rv;

	D_ASSERT(current != mdev->worker.task);

4149 4150
	if ((flags & BM_LOCKED_SET_ALLOWED) == 0)
		drbd_suspend_io(mdev);
P
Philipp Reisner 已提交
4151

4152
	drbd_bm_lock(mdev, why, flags);
P
Philipp Reisner 已提交
4153 4154 4155
	rv = io_fn(mdev);
	drbd_bm_unlock(mdev);

4156 4157
	if ((flags & BM_LOCKED_SET_ALLOWED) == 0)
		drbd_resume_io(mdev);
P
Philipp Reisner 已提交
4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191

	return rv;
}

void drbd_md_set_flag(struct drbd_conf *mdev, int flag) __must_hold(local)
{
	if ((mdev->ldev->md.flags & flag) != flag) {
		drbd_md_mark_dirty(mdev);
		mdev->ldev->md.flags |= flag;
	}
}

void drbd_md_clear_flag(struct drbd_conf *mdev, int flag) __must_hold(local)
{
	if ((mdev->ldev->md.flags & flag) != 0) {
		drbd_md_mark_dirty(mdev);
		mdev->ldev->md.flags &= ~flag;
	}
}
int drbd_md_test_flag(struct drbd_backing_dev *bdev, int flag)
{
	return (bdev->md.flags & flag) != 0;
}

static void md_sync_timer_fn(unsigned long data)
{
	struct drbd_conf *mdev = (struct drbd_conf *) data;

	drbd_queue_work_front(&mdev->data.work, &mdev->md_sync_work);
}

static int w_md_sync(struct drbd_conf *mdev, struct drbd_work *w, int unused)
{
	dev_warn(DEV, "md_sync_timer expired! Worker calls drbd_md_sync().\n");
4192 4193 4194 4195
#ifdef DEBUG
	dev_warn(DEV, "last md_mark_dirty: %s:%u\n",
		mdev->last_md_mark_dirty.func, mdev->last_md_mark_dirty.line);
#endif
P
Philipp Reisner 已提交
4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220
	drbd_md_sync(mdev);
	return 1;
}

#ifdef CONFIG_DRBD_FAULT_INJECTION
/* Fault insertion support including random number generator shamelessly
 * stolen from kernel/rcutorture.c */
struct fault_random_state {
	unsigned long state;
	unsigned long count;
};

#define FAULT_RANDOM_MULT 39916801  /* prime */
#define FAULT_RANDOM_ADD	479001701 /* prime */
#define FAULT_RANDOM_REFRESH 10000

/*
 * Crude but fast random-number generator.  Uses a linear congruential
 * generator, with occasional help from get_random_bytes().
 */
static unsigned long
_drbd_fault_random(struct fault_random_state *rsp)
{
	long refresh;

4221
	if (!rsp->count--) {
P
Philipp Reisner 已提交
4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240
		get_random_bytes(&refresh, sizeof(refresh));
		rsp->state += refresh;
		rsp->count = FAULT_RANDOM_REFRESH;
	}
	rsp->state = rsp->state * FAULT_RANDOM_MULT + FAULT_RANDOM_ADD;
	return swahw32(rsp->state);
}

static char *
_drbd_fault_str(unsigned int type) {
	static char *_faults[] = {
		[DRBD_FAULT_MD_WR] = "Meta-data write",
		[DRBD_FAULT_MD_RD] = "Meta-data read",
		[DRBD_FAULT_RS_WR] = "Resync write",
		[DRBD_FAULT_RS_RD] = "Resync read",
		[DRBD_FAULT_DT_WR] = "Data write",
		[DRBD_FAULT_DT_RD] = "Data read",
		[DRBD_FAULT_DT_RA] = "Data read ahead",
		[DRBD_FAULT_BM_ALLOC] = "BM allocation",
4241 4242
		[DRBD_FAULT_AL_EE] = "EE allocation",
		[DRBD_FAULT_RECEIVE] = "receive data corruption",
P
Philipp Reisner 已提交
4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260
	};

	return (type < DRBD_FAULT_MAX) ? _faults[type] : "**Unknown**";
}

unsigned int
_drbd_insert_fault(struct drbd_conf *mdev, unsigned int type)
{
	static struct fault_random_state rrs = {0, 0};

	unsigned int ret = (
		(fault_devs == 0 ||
			((1 << mdev_to_minor(mdev)) & fault_devs) != 0) &&
		(((_drbd_fault_random(&rrs) % 100) + 1) <= fault_rate));

	if (ret) {
		fault_count++;

4261
		if (__ratelimit(&drbd_ratelimit_state))
P
Philipp Reisner 已提交
4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295
			dev_warn(DEV, "***Simulating %s failure\n",
				_drbd_fault_str(type));
	}

	return ret;
}
#endif

const char *drbd_buildtag(void)
{
	/* DRBD built from external sources has here a reference to the
	   git hash of the source code. */

	static char buildtag[38] = "\0uilt-in";

	if (buildtag[0] == 0) {
#ifdef CONFIG_MODULES
		if (THIS_MODULE != NULL)
			sprintf(buildtag, "srcversion: %-24s", THIS_MODULE->srcversion);
		else
#endif
			buildtag[0] = 'b';
	}

	return buildtag;
}

module_init(drbd_init)
module_exit(drbd_cleanup)

EXPORT_SYMBOL(drbd_conn_str);
EXPORT_SYMBOL(drbd_role_str);
EXPORT_SYMBOL(drbd_disk_str);
EXPORT_SYMBOL(drbd_set_st_err_str);