drbd_receiver.c 130.1 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 35 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 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81
/*
   drbd_receiver.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>.

   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 <asm/uaccess.h>
#include <net/sock.h>

#include <linux/drbd.h>
#include <linux/fs.h>
#include <linux/file.h>
#include <linux/in.h>
#include <linux/mm.h>
#include <linux/memcontrol.h>
#include <linux/mm_inline.h>
#include <linux/slab.h>
#include <linux/smp_lock.h>
#include <linux/pkt_sched.h>
#define __KERNEL_SYSCALLS__
#include <linux/unistd.h>
#include <linux/vmalloc.h>
#include <linux/random.h>
#include <linux/string.h>
#include <linux/scatterlist.h>
#include "drbd_int.h"
#include "drbd_req.h"

#include "drbd_vli.h"

struct flush_work {
	struct drbd_work w;
	struct drbd_epoch *epoch;
};

enum finish_epoch {
	FE_STILL_LIVE,
	FE_DESTROYED,
	FE_RECYCLED,
};

static int drbd_do_handshake(struct drbd_conf *mdev);
static int drbd_do_auth(struct drbd_conf *mdev);

static enum finish_epoch drbd_may_finish_epoch(struct drbd_conf *, struct drbd_epoch *, enum epoch_event);
static int e_end_block(struct drbd_conf *, struct drbd_work *, int);

static struct drbd_epoch *previous_epoch(struct drbd_conf *mdev, struct drbd_epoch *epoch)
{
	struct drbd_epoch *prev;
	spin_lock(&mdev->epoch_lock);
	prev = list_entry(epoch->list.prev, struct drbd_epoch, list);
	if (prev == epoch || prev == mdev->current_epoch)
		prev = NULL;
	spin_unlock(&mdev->epoch_lock);
	return prev;
}

#define GFP_TRY	(__GFP_HIGHMEM | __GFP_NOWARN)

82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99
/*
 * some helper functions to deal with single linked page lists,
 * page->private being our "next" pointer.
 */

/* If at least n pages are linked at head, get n pages off.
 * Otherwise, don't modify head, and return NULL.
 * Locking is the responsibility of the caller.
 */
static struct page *page_chain_del(struct page **head, int n)
{
	struct page *page;
	struct page *tmp;

	BUG_ON(!n);
	BUG_ON(!head);

	page = *head;
100 101 102 103

	if (!page)
		return NULL;

104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161
	while (page) {
		tmp = page_chain_next(page);
		if (--n == 0)
			break; /* found sufficient pages */
		if (tmp == NULL)
			/* insufficient pages, don't use any of them. */
			return NULL;
		page = tmp;
	}

	/* add end of list marker for the returned list */
	set_page_private(page, 0);
	/* actual return value, and adjustment of head */
	page = *head;
	*head = tmp;
	return page;
}

/* may be used outside of locks to find the tail of a (usually short)
 * "private" page chain, before adding it back to a global chain head
 * with page_chain_add() under a spinlock. */
static struct page *page_chain_tail(struct page *page, int *len)
{
	struct page *tmp;
	int i = 1;
	while ((tmp = page_chain_next(page)))
		++i, page = tmp;
	if (len)
		*len = i;
	return page;
}

static int page_chain_free(struct page *page)
{
	struct page *tmp;
	int i = 0;
	page_chain_for_each_safe(page, tmp) {
		put_page(page);
		++i;
	}
	return i;
}

static void page_chain_add(struct page **head,
		struct page *chain_first, struct page *chain_last)
{
#if 1
	struct page *tmp;
	tmp = page_chain_tail(chain_first, NULL);
	BUG_ON(tmp != chain_last);
#endif

	/* add chain to head */
	set_page_private(chain_last, (unsigned long)*head);
	*head = chain_first;
}

static struct page *drbd_pp_first_pages_or_try_alloc(struct drbd_conf *mdev, int number)
P
Philipp Reisner 已提交
162 163
{
	struct page *page = NULL;
164 165
	struct page *tmp = NULL;
	int i = 0;
P
Philipp Reisner 已提交
166 167 168

	/* Yes, testing drbd_pp_vacant outside the lock is racy.
	 * So what. It saves a spin_lock. */
169
	if (drbd_pp_vacant >= number) {
P
Philipp Reisner 已提交
170
		spin_lock(&drbd_pp_lock);
171 172 173
		page = page_chain_del(&drbd_pp_pool, number);
		if (page)
			drbd_pp_vacant -= number;
P
Philipp Reisner 已提交
174
		spin_unlock(&drbd_pp_lock);
175 176
		if (page)
			return page;
P
Philipp Reisner 已提交
177
	}
178

P
Philipp Reisner 已提交
179 180 181
	/* GFP_TRY, because we must not cause arbitrary write-out: in a DRBD
	 * "criss-cross" setup, that might cause write-out on some other DRBD,
	 * which in turn might block on the other node at this very place.  */
182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203
	for (i = 0; i < number; i++) {
		tmp = alloc_page(GFP_TRY);
		if (!tmp)
			break;
		set_page_private(tmp, (unsigned long)page);
		page = tmp;
	}

	if (i == number)
		return page;

	/* Not enough pages immediately available this time.
	 * No need to jump around here, drbd_pp_alloc will retry this
	 * function "soon". */
	if (page) {
		tmp = page_chain_tail(page, NULL);
		spin_lock(&drbd_pp_lock);
		page_chain_add(&drbd_pp_pool, page, tmp);
		drbd_pp_vacant += i;
		spin_unlock(&drbd_pp_lock);
	}
	return NULL;
P
Philipp Reisner 已提交
204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226
}

/* kick lower level device, if we have more than (arbitrary number)
 * reference counts on it, which typically are locally submitted io
 * requests.  don't use unacked_cnt, so we speed up proto A and B, too. */
static void maybe_kick_lo(struct drbd_conf *mdev)
{
	if (atomic_read(&mdev->local_cnt) >= mdev->net_conf->unplug_watermark)
		drbd_kick_lo(mdev);
}

static void reclaim_net_ee(struct drbd_conf *mdev, struct list_head *to_be_freed)
{
	struct drbd_epoch_entry *e;
	struct list_head *le, *tle;

	/* The EEs are always appended to the end of the list. Since
	   they are sent in order over the wire, they have to finish
	   in order. As soon as we see the first not finished we can
	   stop to examine the list... */

	list_for_each_safe(le, tle, &mdev->net_ee) {
		e = list_entry(le, struct drbd_epoch_entry, w.list);
227
		if (drbd_ee_has_active_page(e))
P
Philipp Reisner 已提交
228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243
			break;
		list_move(le, to_be_freed);
	}
}

static void drbd_kick_lo_and_reclaim_net(struct drbd_conf *mdev)
{
	LIST_HEAD(reclaimed);
	struct drbd_epoch_entry *e, *t;

	maybe_kick_lo(mdev);
	spin_lock_irq(&mdev->req_lock);
	reclaim_net_ee(mdev, &reclaimed);
	spin_unlock_irq(&mdev->req_lock);

	list_for_each_entry_safe(e, t, &reclaimed, w.list)
244
		drbd_free_net_ee(mdev, e);
P
Philipp Reisner 已提交
245 246 247
}

/**
248
 * drbd_pp_alloc() - Returns @number pages, retries forever (or until signalled)
P
Philipp Reisner 已提交
249
 * @mdev:	DRBD device.
250 251 252 253 254 255
 * @number:	number of pages requested
 * @retry:	whether to retry, if not enough pages are available right now
 *
 * Tries to allocate number pages, first from our own page pool, then from
 * the kernel, unless this allocation would exceed the max_buffers setting.
 * Possibly retry until DRBD frees sufficient pages somewhere else.
P
Philipp Reisner 已提交
256
 *
257
 * Returns a page chain linked via page->private.
P
Philipp Reisner 已提交
258
 */
259
static struct page *drbd_pp_alloc(struct drbd_conf *mdev, unsigned number, bool retry)
P
Philipp Reisner 已提交
260 261 262 263
{
	struct page *page = NULL;
	DEFINE_WAIT(wait);

264 265 266 267
	/* Yes, we may run up to @number over max_buffers. If we
	 * follow it strictly, the admin will get it wrong anyways. */
	if (atomic_read(&mdev->pp_in_use) < mdev->net_conf->max_buffers)
		page = drbd_pp_first_pages_or_try_alloc(mdev, number);
P
Philipp Reisner 已提交
268

269
	while (page == NULL) {
P
Philipp Reisner 已提交
270 271 272 273 274
		prepare_to_wait(&drbd_pp_wait, &wait, TASK_INTERRUPTIBLE);

		drbd_kick_lo_and_reclaim_net(mdev);

		if (atomic_read(&mdev->pp_in_use) < mdev->net_conf->max_buffers) {
275
			page = drbd_pp_first_pages_or_try_alloc(mdev, number);
P
Philipp Reisner 已提交
276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291
			if (page)
				break;
		}

		if (!retry)
			break;

		if (signal_pending(current)) {
			dev_warn(DEV, "drbd_pp_alloc interrupted!\n");
			break;
		}

		schedule();
	}
	finish_wait(&drbd_pp_wait, &wait);

292 293
	if (page)
		atomic_add(number, &mdev->pp_in_use);
P
Philipp Reisner 已提交
294 295 296 297
	return page;
}

/* Must not be used from irq, as that may deadlock: see drbd_pp_alloc.
298 299 300
 * Is also used from inside an other spin_lock_irq(&mdev->req_lock);
 * Either links the page chain back to the global pool,
 * or returns all pages to the system. */
301
static void drbd_pp_free(struct drbd_conf *mdev, struct page *page, int is_net)
P
Philipp Reisner 已提交
302
{
303
	atomic_t *a = is_net ? &mdev->pp_in_use_by_net : &mdev->pp_in_use;
P
Philipp Reisner 已提交
304
	int i;
305

306 307 308 309 310 311 312 313 314
	if (drbd_pp_vacant > (DRBD_MAX_SEGMENT_SIZE/PAGE_SIZE)*minor_count)
		i = page_chain_free(page);
	else {
		struct page *tmp;
		tmp = page_chain_tail(page, &i);
		spin_lock(&drbd_pp_lock);
		page_chain_add(&drbd_pp_pool, page, tmp);
		drbd_pp_vacant += i;
		spin_unlock(&drbd_pp_lock);
P
Philipp Reisner 已提交
315
	}
316
	i = atomic_sub_return(i, a);
317
	if (i < 0)
318 319
		dev_warn(DEV, "ASSERTION FAILED: %s: %d < 0\n",
			is_net ? "pp_in_use_by_net" : "pp_in_use", i);
P
Philipp Reisner 已提交
320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345
	wake_up(&drbd_pp_wait);
}

/*
You need to hold the req_lock:
 _drbd_wait_ee_list_empty()

You must not have the req_lock:
 drbd_free_ee()
 drbd_alloc_ee()
 drbd_init_ee()
 drbd_release_ee()
 drbd_ee_fix_bhs()
 drbd_process_done_ee()
 drbd_clear_done_ee()
 drbd_wait_ee_list_empty()
*/

struct drbd_epoch_entry *drbd_alloc_ee(struct drbd_conf *mdev,
				     u64 id,
				     sector_t sector,
				     unsigned int data_size,
				     gfp_t gfp_mask) __must_hold(local)
{
	struct drbd_epoch_entry *e;
	struct page *page;
346
	unsigned nr_pages = (data_size + PAGE_SIZE -1) >> PAGE_SHIFT;
P
Philipp Reisner 已提交
347 348 349 350 351 352 353 354 355 356 357

	if (FAULT_ACTIVE(mdev, DRBD_FAULT_AL_EE))
		return NULL;

	e = mempool_alloc(drbd_ee_mempool, gfp_mask & ~__GFP_HIGHMEM);
	if (!e) {
		if (!(gfp_mask & __GFP_NOWARN))
			dev_err(DEV, "alloc_ee: Allocation of an EE failed\n");
		return NULL;
	}

358 359 360
	page = drbd_pp_alloc(mdev, nr_pages, (gfp_mask & __GFP_WAIT));
	if (!page)
		goto fail;
P
Philipp Reisner 已提交
361 362 363

	INIT_HLIST_NODE(&e->colision);
	e->epoch = NULL;
364 365 366 367
	e->mdev = mdev;
	e->pages = page;
	atomic_set(&e->pending_bios, 0);
	e->size = data_size;
P
Philipp Reisner 已提交
368
	e->flags = 0;
369 370
	e->sector = sector;
	e->block_id = id;
P
Philipp Reisner 已提交
371 372 373

	return e;

374
 fail:
P
Philipp Reisner 已提交
375 376 377 378
	mempool_free(e, drbd_ee_mempool);
	return NULL;
}

379
void drbd_free_some_ee(struct drbd_conf *mdev, struct drbd_epoch_entry *e, int is_net)
P
Philipp Reisner 已提交
380
{
381 382
	if (e->flags & EE_HAS_DIGEST)
		kfree(e->digest);
383
	drbd_pp_free(mdev, e->pages, is_net);
384
	D_ASSERT(atomic_read(&e->pending_bios) == 0);
P
Philipp Reisner 已提交
385 386 387 388 389 390 391 392 393
	D_ASSERT(hlist_unhashed(&e->colision));
	mempool_free(e, drbd_ee_mempool);
}

int drbd_release_ee(struct drbd_conf *mdev, struct list_head *list)
{
	LIST_HEAD(work_list);
	struct drbd_epoch_entry *e, *t;
	int count = 0;
394
	int is_net = list == &mdev->net_ee;
P
Philipp Reisner 已提交
395 396 397 398 399 400

	spin_lock_irq(&mdev->req_lock);
	list_splice_init(list, &work_list);
	spin_unlock_irq(&mdev->req_lock);

	list_for_each_entry_safe(e, t, &work_list, w.list) {
401
		drbd_free_some_ee(mdev, e, is_net);
P
Philipp Reisner 已提交
402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429
		count++;
	}
	return count;
}


/*
 * This function is called from _asender only_
 * but see also comments in _req_mod(,barrier_acked)
 * and receive_Barrier.
 *
 * Move entries from net_ee to done_ee, if ready.
 * Grab done_ee, call all callbacks, free the entries.
 * The callbacks typically send out ACKs.
 */
static int drbd_process_done_ee(struct drbd_conf *mdev)
{
	LIST_HEAD(work_list);
	LIST_HEAD(reclaimed);
	struct drbd_epoch_entry *e, *t;
	int ok = (mdev->state.conn >= C_WF_REPORT_PARAMS);

	spin_lock_irq(&mdev->req_lock);
	reclaim_net_ee(mdev, &reclaimed);
	list_splice_init(&mdev->done_ee, &work_list);
	spin_unlock_irq(&mdev->req_lock);

	list_for_each_entry_safe(e, t, &reclaimed, w.list)
430
		drbd_free_net_ee(mdev, e);
P
Philipp Reisner 已提交
431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576

	/* possible callbacks here:
	 * e_end_block, and e_end_resync_block, e_send_discard_ack.
	 * all ignore the last argument.
	 */
	list_for_each_entry_safe(e, t, &work_list, w.list) {
		/* list_del not necessary, next/prev members not touched */
		ok = e->w.cb(mdev, &e->w, !ok) && ok;
		drbd_free_ee(mdev, e);
	}
	wake_up(&mdev->ee_wait);

	return ok;
}

void _drbd_wait_ee_list_empty(struct drbd_conf *mdev, struct list_head *head)
{
	DEFINE_WAIT(wait);

	/* avoids spin_lock/unlock
	 * and calling prepare_to_wait in the fast path */
	while (!list_empty(head)) {
		prepare_to_wait(&mdev->ee_wait, &wait, TASK_UNINTERRUPTIBLE);
		spin_unlock_irq(&mdev->req_lock);
		drbd_kick_lo(mdev);
		schedule();
		finish_wait(&mdev->ee_wait, &wait);
		spin_lock_irq(&mdev->req_lock);
	}
}

void drbd_wait_ee_list_empty(struct drbd_conf *mdev, struct list_head *head)
{
	spin_lock_irq(&mdev->req_lock);
	_drbd_wait_ee_list_empty(mdev, head);
	spin_unlock_irq(&mdev->req_lock);
}

/* see also kernel_accept; which is only present since 2.6.18.
 * also we want to log which part of it failed, exactly */
static int drbd_accept(struct drbd_conf *mdev, const char **what,
		struct socket *sock, struct socket **newsock)
{
	struct sock *sk = sock->sk;
	int err = 0;

	*what = "listen";
	err = sock->ops->listen(sock, 5);
	if (err < 0)
		goto out;

	*what = "sock_create_lite";
	err = sock_create_lite(sk->sk_family, sk->sk_type, sk->sk_protocol,
			       newsock);
	if (err < 0)
		goto out;

	*what = "accept";
	err = sock->ops->accept(sock, *newsock, 0);
	if (err < 0) {
		sock_release(*newsock);
		*newsock = NULL;
		goto out;
	}
	(*newsock)->ops  = sock->ops;

out:
	return err;
}

static int drbd_recv_short(struct drbd_conf *mdev, struct socket *sock,
		    void *buf, size_t size, int flags)
{
	mm_segment_t oldfs;
	struct kvec iov = {
		.iov_base = buf,
		.iov_len = size,
	};
	struct msghdr msg = {
		.msg_iovlen = 1,
		.msg_iov = (struct iovec *)&iov,
		.msg_flags = (flags ? flags : MSG_WAITALL | MSG_NOSIGNAL)
	};
	int rv;

	oldfs = get_fs();
	set_fs(KERNEL_DS);
	rv = sock_recvmsg(sock, &msg, size, msg.msg_flags);
	set_fs(oldfs);

	return rv;
}

static int drbd_recv(struct drbd_conf *mdev, void *buf, size_t size)
{
	mm_segment_t oldfs;
	struct kvec iov = {
		.iov_base = buf,
		.iov_len = size,
	};
	struct msghdr msg = {
		.msg_iovlen = 1,
		.msg_iov = (struct iovec *)&iov,
		.msg_flags = MSG_WAITALL | MSG_NOSIGNAL
	};
	int rv;

	oldfs = get_fs();
	set_fs(KERNEL_DS);

	for (;;) {
		rv = sock_recvmsg(mdev->data.socket, &msg, size, msg.msg_flags);
		if (rv == size)
			break;

		/* Note:
		 * ECONNRESET	other side closed the connection
		 * ERESTARTSYS	(on  sock) we got a signal
		 */

		if (rv < 0) {
			if (rv == -ECONNRESET)
				dev_info(DEV, "sock was reset by peer\n");
			else if (rv != -ERESTARTSYS)
				dev_err(DEV, "sock_recvmsg returned %d\n", rv);
			break;
		} else if (rv == 0) {
			dev_info(DEV, "sock was shut down by peer\n");
			break;
		} else	{
			/* signal came in, or peer/link went down,
			 * after we read a partial message
			 */
			/* D_ASSERT(signal_pending(current)); */
			break;
		}
	};

	set_fs(oldfs);

	if (rv != size)
		drbd_force_state(mdev, NS(conn, C_BROKEN_PIPE));

	return rv;
}

577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595
/* quoting tcp(7):
 *   On individual connections, the socket buffer size must be set prior to the
 *   listen(2) or connect(2) calls in order to have it take effect.
 * This is our wrapper to do so.
 */
static void drbd_setbufsize(struct socket *sock, unsigned int snd,
		unsigned int rcv)
{
	/* open coded SO_SNDBUF, SO_RCVBUF */
	if (snd) {
		sock->sk->sk_sndbuf = snd;
		sock->sk->sk_userlocks |= SOCK_SNDBUF_LOCK;
	}
	if (rcv) {
		sock->sk->sk_rcvbuf = rcv;
		sock->sk->sk_userlocks |= SOCK_RCVBUF_LOCK;
	}
}

P
Philipp Reisner 已提交
596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616
static struct socket *drbd_try_connect(struct drbd_conf *mdev)
{
	const char *what;
	struct socket *sock;
	struct sockaddr_in6 src_in6;
	int err;
	int disconnect_on_error = 1;

	if (!get_net_conf(mdev))
		return NULL;

	what = "sock_create_kern";
	err = sock_create_kern(((struct sockaddr *)mdev->net_conf->my_addr)->sa_family,
		SOCK_STREAM, IPPROTO_TCP, &sock);
	if (err < 0) {
		sock = NULL;
		goto out;
	}

	sock->sk->sk_rcvtimeo =
	sock->sk->sk_sndtimeo =  mdev->net_conf->try_connect_int*HZ;
617 618
	drbd_setbufsize(sock, mdev->net_conf->sndbuf_size,
			mdev->net_conf->rcvbuf_size);
P
Philipp Reisner 已提交
619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696

       /* explicitly bind to the configured IP as source IP
	*  for the outgoing connections.
	*  This is needed for multihomed hosts and to be
	*  able to use lo: interfaces for drbd.
	* Make sure to use 0 as port number, so linux selects
	*  a free one dynamically.
	*/
	memcpy(&src_in6, mdev->net_conf->my_addr,
	       min_t(int, mdev->net_conf->my_addr_len, sizeof(src_in6)));
	if (((struct sockaddr *)mdev->net_conf->my_addr)->sa_family == AF_INET6)
		src_in6.sin6_port = 0;
	else
		((struct sockaddr_in *)&src_in6)->sin_port = 0; /* AF_INET & AF_SCI */

	what = "bind before connect";
	err = sock->ops->bind(sock,
			      (struct sockaddr *) &src_in6,
			      mdev->net_conf->my_addr_len);
	if (err < 0)
		goto out;

	/* connect may fail, peer not yet available.
	 * stay C_WF_CONNECTION, don't go Disconnecting! */
	disconnect_on_error = 0;
	what = "connect";
	err = sock->ops->connect(sock,
				 (struct sockaddr *)mdev->net_conf->peer_addr,
				 mdev->net_conf->peer_addr_len, 0);

out:
	if (err < 0) {
		if (sock) {
			sock_release(sock);
			sock = NULL;
		}
		switch (-err) {
			/* timeout, busy, signal pending */
		case ETIMEDOUT: case EAGAIN: case EINPROGRESS:
		case EINTR: case ERESTARTSYS:
			/* peer not (yet) available, network problem */
		case ECONNREFUSED: case ENETUNREACH:
		case EHOSTDOWN:    case EHOSTUNREACH:
			disconnect_on_error = 0;
			break;
		default:
			dev_err(DEV, "%s failed, err = %d\n", what, err);
		}
		if (disconnect_on_error)
			drbd_force_state(mdev, NS(conn, C_DISCONNECTING));
	}
	put_net_conf(mdev);
	return sock;
}

static struct socket *drbd_wait_for_connect(struct drbd_conf *mdev)
{
	int timeo, err;
	struct socket *s_estab = NULL, *s_listen;
	const char *what;

	if (!get_net_conf(mdev))
		return NULL;

	what = "sock_create_kern";
	err = sock_create_kern(((struct sockaddr *)mdev->net_conf->my_addr)->sa_family,
		SOCK_STREAM, IPPROTO_TCP, &s_listen);
	if (err) {
		s_listen = NULL;
		goto out;
	}

	timeo = mdev->net_conf->try_connect_int * HZ;
	timeo += (random32() & 1) ? timeo / 7 : -timeo / 7; /* 28.5% random jitter */

	s_listen->sk->sk_reuse    = 1; /* SO_REUSEADDR */
	s_listen->sk->sk_rcvtimeo = timeo;
	s_listen->sk->sk_sndtimeo = timeo;
697 698
	drbd_setbufsize(s_listen, mdev->net_conf->sndbuf_size,
			mdev->net_conf->rcvbuf_size);
P
Philipp Reisner 已提交
699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725

	what = "bind before listen";
	err = s_listen->ops->bind(s_listen,
			      (struct sockaddr *) mdev->net_conf->my_addr,
			      mdev->net_conf->my_addr_len);
	if (err < 0)
		goto out;

	err = drbd_accept(mdev, &what, s_listen, &s_estab);

out:
	if (s_listen)
		sock_release(s_listen);
	if (err < 0) {
		if (err != -EAGAIN && err != -EINTR && err != -ERESTARTSYS) {
			dev_err(DEV, "%s failed, err = %d\n", what, err);
			drbd_force_state(mdev, NS(conn, C_DISCONNECTING));
		}
	}
	put_net_conf(mdev);

	return s_estab;
}

static int drbd_send_fp(struct drbd_conf *mdev,
	struct socket *sock, enum drbd_packets cmd)
{
726
	struct p_header80 *h = &mdev->data.sbuf.header.h80;
P
Philipp Reisner 已提交
727 728 729 730 731 732

	return _drbd_send_cmd(mdev, sock, cmd, h, sizeof(*h), 0);
}

static enum drbd_packets drbd_recv_fp(struct drbd_conf *mdev, struct socket *sock)
{
733
	struct p_header80 *h = &mdev->data.rbuf.header.h80;
P
Philipp Reisner 已提交
734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909
	int rr;

	rr = drbd_recv_short(mdev, sock, h, sizeof(*h), 0);

	if (rr == sizeof(*h) && h->magic == BE_DRBD_MAGIC)
		return be16_to_cpu(h->command);

	return 0xffff;
}

/**
 * drbd_socket_okay() - Free the socket if its connection is not okay
 * @mdev:	DRBD device.
 * @sock:	pointer to the pointer to the socket.
 */
static int drbd_socket_okay(struct drbd_conf *mdev, struct socket **sock)
{
	int rr;
	char tb[4];

	if (!*sock)
		return FALSE;

	rr = drbd_recv_short(mdev, *sock, tb, 4, MSG_DONTWAIT | MSG_PEEK);

	if (rr > 0 || rr == -EAGAIN) {
		return TRUE;
	} else {
		sock_release(*sock);
		*sock = NULL;
		return FALSE;
	}
}

/*
 * return values:
 *   1 yes, we have a valid connection
 *   0 oops, did not work out, please try again
 *  -1 peer talks different language,
 *     no point in trying again, please go standalone.
 *  -2 We do not have a network config...
 */
static int drbd_connect(struct drbd_conf *mdev)
{
	struct socket *s, *sock, *msock;
	int try, h, ok;

	D_ASSERT(!mdev->data.socket);

	if (drbd_request_state(mdev, NS(conn, C_WF_CONNECTION)) < SS_SUCCESS)
		return -2;

	clear_bit(DISCARD_CONCURRENT, &mdev->flags);

	sock  = NULL;
	msock = NULL;

	do {
		for (try = 0;;) {
			/* 3 tries, this should take less than a second! */
			s = drbd_try_connect(mdev);
			if (s || ++try >= 3)
				break;
			/* give the other side time to call bind() & listen() */
			__set_current_state(TASK_INTERRUPTIBLE);
			schedule_timeout(HZ / 10);
		}

		if (s) {
			if (!sock) {
				drbd_send_fp(mdev, s, P_HAND_SHAKE_S);
				sock = s;
				s = NULL;
			} else if (!msock) {
				drbd_send_fp(mdev, s, P_HAND_SHAKE_M);
				msock = s;
				s = NULL;
			} else {
				dev_err(DEV, "Logic error in drbd_connect()\n");
				goto out_release_sockets;
			}
		}

		if (sock && msock) {
			__set_current_state(TASK_INTERRUPTIBLE);
			schedule_timeout(HZ / 10);
			ok = drbd_socket_okay(mdev, &sock);
			ok = drbd_socket_okay(mdev, &msock) && ok;
			if (ok)
				break;
		}

retry:
		s = drbd_wait_for_connect(mdev);
		if (s) {
			try = drbd_recv_fp(mdev, s);
			drbd_socket_okay(mdev, &sock);
			drbd_socket_okay(mdev, &msock);
			switch (try) {
			case P_HAND_SHAKE_S:
				if (sock) {
					dev_warn(DEV, "initial packet S crossed\n");
					sock_release(sock);
				}
				sock = s;
				break;
			case P_HAND_SHAKE_M:
				if (msock) {
					dev_warn(DEV, "initial packet M crossed\n");
					sock_release(msock);
				}
				msock = s;
				set_bit(DISCARD_CONCURRENT, &mdev->flags);
				break;
			default:
				dev_warn(DEV, "Error receiving initial packet\n");
				sock_release(s);
				if (random32() & 1)
					goto retry;
			}
		}

		if (mdev->state.conn <= C_DISCONNECTING)
			goto out_release_sockets;
		if (signal_pending(current)) {
			flush_signals(current);
			smp_rmb();
			if (get_t_state(&mdev->receiver) == Exiting)
				goto out_release_sockets;
		}

		if (sock && msock) {
			ok = drbd_socket_okay(mdev, &sock);
			ok = drbd_socket_okay(mdev, &msock) && ok;
			if (ok)
				break;
		}
	} while (1);

	msock->sk->sk_reuse = 1; /* SO_REUSEADDR */
	sock->sk->sk_reuse = 1; /* SO_REUSEADDR */

	sock->sk->sk_allocation = GFP_NOIO;
	msock->sk->sk_allocation = GFP_NOIO;

	sock->sk->sk_priority = TC_PRIO_INTERACTIVE_BULK;
	msock->sk->sk_priority = TC_PRIO_INTERACTIVE;

	/* NOT YET ...
	 * sock->sk->sk_sndtimeo = mdev->net_conf->timeout*HZ/10;
	 * sock->sk->sk_rcvtimeo = MAX_SCHEDULE_TIMEOUT;
	 * first set it to the P_HAND_SHAKE timeout,
	 * which we set to 4x the configured ping_timeout. */
	sock->sk->sk_sndtimeo =
	sock->sk->sk_rcvtimeo = mdev->net_conf->ping_timeo*4*HZ/10;

	msock->sk->sk_sndtimeo = mdev->net_conf->timeout*HZ/10;
	msock->sk->sk_rcvtimeo = mdev->net_conf->ping_int*HZ;

	/* we don't want delays.
	 * we use TCP_CORK where apropriate, though */
	drbd_tcp_nodelay(sock);
	drbd_tcp_nodelay(msock);

	mdev->data.socket = sock;
	mdev->meta.socket = msock;
	mdev->last_received = jiffies;

	D_ASSERT(mdev->asender.task == NULL);

	h = drbd_do_handshake(mdev);
	if (h <= 0)
		return h;

	if (mdev->cram_hmac_tfm) {
		/* drbd_request_state(mdev, NS(conn, WFAuth)); */
910 911
		switch (drbd_do_auth(mdev)) {
		case -1:
P
Philipp Reisner 已提交
912 913
			dev_err(DEV, "Authentication of peer failed\n");
			return -1;
914 915 916
		case 0:
			dev_err(DEV, "Authentication of peer failed, trying again.\n");
			return 0;
P
Philipp Reisner 已提交
917 918 919 920 921 922 923 924 925 926 927 928 929 930
		}
	}

	if (drbd_request_state(mdev, NS(conn, C_WF_REPORT_PARAMS)) < SS_SUCCESS)
		return 0;

	sock->sk->sk_sndtimeo = mdev->net_conf->timeout*HZ/10;
	sock->sk->sk_rcvtimeo = MAX_SCHEDULE_TIMEOUT;

	atomic_set(&mdev->packet_seq, 0);
	mdev->peer_seq = 0;

	drbd_thread_start(&mdev->asender);

931 932 933 934 935
	if (mdev->agreed_pro_version < 95 && get_ldev(mdev)) {
		drbd_setup_queue_param(mdev, DRBD_MAX_SIZE_H80_PACKET);
		put_ldev(mdev);
	}

936 937
	if (!drbd_send_protocol(mdev))
		return -1;
P
Philipp Reisner 已提交
938
	drbd_send_sync_param(mdev, &mdev->sync_conf);
939
	drbd_send_sizes(mdev, 0, 0);
P
Philipp Reisner 已提交
940 941 942 943 944 945 946 947 948 949 950 951 952 953 954
	drbd_send_uuids(mdev);
	drbd_send_state(mdev);
	clear_bit(USE_DEGR_WFC_T, &mdev->flags);
	clear_bit(RESIZE_PENDING, &mdev->flags);

	return 1;

out_release_sockets:
	if (sock)
		sock_release(sock);
	if (msock)
		sock_release(msock);
	return -1;
}

955
static int drbd_recv_header(struct drbd_conf *mdev, enum drbd_packets *cmd, unsigned int *packet_size)
P
Philipp Reisner 已提交
956
{
957
	union p_header *h = &mdev->data.rbuf.header;
P
Philipp Reisner 已提交
958 959 960 961 962 963
	int r;

	r = drbd_recv(mdev, h, sizeof(*h));
	if (unlikely(r != sizeof(*h))) {
		dev_err(DEV, "short read expecting header on sock: r=%d\n", r);
		return FALSE;
964 965 966 967 968 969 970 971 972
	}

	if (likely(h->h80.magic == BE_DRBD_MAGIC)) {
		*cmd = be16_to_cpu(h->h80.command);
		*packet_size = be16_to_cpu(h->h80.length);
	} else if (h->h95.magic == BE_DRBD_MAGIC_BIG) {
		*cmd = be16_to_cpu(h->h95.command);
		*packet_size = be32_to_cpu(h->h95.length);
	} else {
973 974 975 976
		dev_err(DEV, "magic?? on data m: 0x%08x c: %d l: %d\n",
		    be32_to_cpu(h->h80.magic),
		    be16_to_cpu(h->h80.command),
		    be16_to_cpu(h->h80.length));
P
Philipp Reisner 已提交
977 978 979 980 981 982 983 984 985 986 987 988
		return FALSE;
	}
	mdev->last_received = jiffies;

	return TRUE;
}

static enum finish_epoch drbd_flush_after_epoch(struct drbd_conf *mdev, struct drbd_epoch *epoch)
{
	int rv;

	if (mdev->write_ordering >= WO_bdev_flush && get_ldev(mdev)) {
989 990
		rv = blkdev_issue_flush(mdev->ldev->backing_bdev, GFP_KERNEL,
					NULL, BLKDEV_IFL_WAIT);
P
Philipp Reisner 已提交
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 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101
		if (rv) {
			dev_err(DEV, "local disk flush failed with status %d\n", rv);
			/* would rather check on EOPNOTSUPP, but that is not reliable.
			 * don't try again for ANY return value != 0
			 * if (rv == -EOPNOTSUPP) */
			drbd_bump_write_ordering(mdev, WO_drain_io);
		}
		put_ldev(mdev);
	}

	return drbd_may_finish_epoch(mdev, epoch, EV_BARRIER_DONE);
}

static int w_flush(struct drbd_conf *mdev, struct drbd_work *w, int cancel)
{
	struct flush_work *fw = (struct flush_work *)w;
	struct drbd_epoch *epoch = fw->epoch;

	kfree(w);

	if (!test_and_set_bit(DE_BARRIER_IN_NEXT_EPOCH_ISSUED, &epoch->flags))
		drbd_flush_after_epoch(mdev, epoch);

	drbd_may_finish_epoch(mdev, epoch, EV_PUT |
			      (mdev->state.conn < C_CONNECTED ? EV_CLEANUP : 0));

	return 1;
}

/**
 * drbd_may_finish_epoch() - Applies an epoch_event to the epoch's state, eventually finishes it.
 * @mdev:	DRBD device.
 * @epoch:	Epoch object.
 * @ev:		Epoch event.
 */
static enum finish_epoch drbd_may_finish_epoch(struct drbd_conf *mdev,
					       struct drbd_epoch *epoch,
					       enum epoch_event ev)
{
	int finish, epoch_size;
	struct drbd_epoch *next_epoch;
	int schedule_flush = 0;
	enum finish_epoch rv = FE_STILL_LIVE;

	spin_lock(&mdev->epoch_lock);
	do {
		next_epoch = NULL;
		finish = 0;

		epoch_size = atomic_read(&epoch->epoch_size);

		switch (ev & ~EV_CLEANUP) {
		case EV_PUT:
			atomic_dec(&epoch->active);
			break;
		case EV_GOT_BARRIER_NR:
			set_bit(DE_HAVE_BARRIER_NUMBER, &epoch->flags);

			/* Special case: If we just switched from WO_bio_barrier to
			   WO_bdev_flush we should not finish the current epoch */
			if (test_bit(DE_CONTAINS_A_BARRIER, &epoch->flags) && epoch_size == 1 &&
			    mdev->write_ordering != WO_bio_barrier &&
			    epoch == mdev->current_epoch)
				clear_bit(DE_CONTAINS_A_BARRIER, &epoch->flags);
			break;
		case EV_BARRIER_DONE:
			set_bit(DE_BARRIER_IN_NEXT_EPOCH_DONE, &epoch->flags);
			break;
		case EV_BECAME_LAST:
			/* nothing to do*/
			break;
		}

		if (epoch_size != 0 &&
		    atomic_read(&epoch->active) == 0 &&
		    test_bit(DE_HAVE_BARRIER_NUMBER, &epoch->flags) &&
		    epoch->list.prev == &mdev->current_epoch->list &&
		    !test_bit(DE_IS_FINISHING, &epoch->flags)) {
			/* Nearly all conditions are met to finish that epoch... */
			if (test_bit(DE_BARRIER_IN_NEXT_EPOCH_DONE, &epoch->flags) ||
			    mdev->write_ordering == WO_none ||
			    (epoch_size == 1 && test_bit(DE_CONTAINS_A_BARRIER, &epoch->flags)) ||
			    ev & EV_CLEANUP) {
				finish = 1;
				set_bit(DE_IS_FINISHING, &epoch->flags);
			} else if (!test_bit(DE_BARRIER_IN_NEXT_EPOCH_ISSUED, &epoch->flags) &&
				 mdev->write_ordering == WO_bio_barrier) {
				atomic_inc(&epoch->active);
				schedule_flush = 1;
			}
		}
		if (finish) {
			if (!(ev & EV_CLEANUP)) {
				spin_unlock(&mdev->epoch_lock);
				drbd_send_b_ack(mdev, epoch->barrier_nr, epoch_size);
				spin_lock(&mdev->epoch_lock);
			}
			dec_unacked(mdev);

			if (mdev->current_epoch != epoch) {
				next_epoch = list_entry(epoch->list.next, struct drbd_epoch, list);
				list_del(&epoch->list);
				ev = EV_BECAME_LAST | (ev & EV_CLEANUP);
				mdev->epochs--;
				kfree(epoch);

				if (rv == FE_STILL_LIVE)
					rv = FE_DESTROYED;
			} else {
				epoch->flags = 0;
				atomic_set(&epoch->epoch_size, 0);
1102
				/* atomic_set(&epoch->active, 0); is already zero */
P
Philipp Reisner 已提交
1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162
				if (rv == FE_STILL_LIVE)
					rv = FE_RECYCLED;
			}
		}

		if (!next_epoch)
			break;

		epoch = next_epoch;
	} while (1);

	spin_unlock(&mdev->epoch_lock);

	if (schedule_flush) {
		struct flush_work *fw;
		fw = kmalloc(sizeof(*fw), GFP_ATOMIC);
		if (fw) {
			fw->w.cb = w_flush;
			fw->epoch = epoch;
			drbd_queue_work(&mdev->data.work, &fw->w);
		} else {
			dev_warn(DEV, "Could not kmalloc a flush_work obj\n");
			set_bit(DE_BARRIER_IN_NEXT_EPOCH_ISSUED, &epoch->flags);
			/* That is not a recursion, only one level */
			drbd_may_finish_epoch(mdev, epoch, EV_BARRIER_DONE);
			drbd_may_finish_epoch(mdev, epoch, EV_PUT);
		}
	}

	return rv;
}

/**
 * drbd_bump_write_ordering() - Fall back to an other write ordering method
 * @mdev:	DRBD device.
 * @wo:		Write ordering method to try.
 */
void drbd_bump_write_ordering(struct drbd_conf *mdev, enum write_ordering_e wo) __must_hold(local)
{
	enum write_ordering_e pwo;
	static char *write_ordering_str[] = {
		[WO_none] = "none",
		[WO_drain_io] = "drain",
		[WO_bdev_flush] = "flush",
		[WO_bio_barrier] = "barrier",
	};

	pwo = mdev->write_ordering;
	wo = min(pwo, wo);
	if (wo == WO_bio_barrier && mdev->ldev->dc.no_disk_barrier)
		wo = WO_bdev_flush;
	if (wo == WO_bdev_flush && mdev->ldev->dc.no_disk_flush)
		wo = WO_drain_io;
	if (wo == WO_drain_io && mdev->ldev->dc.no_disk_drain)
		wo = WO_none;
	mdev->write_ordering = wo;
	if (pwo != mdev->write_ordering || wo == WO_bio_barrier)
		dev_info(DEV, "Method to ensure write ordering: %s\n", write_ordering_str[mdev->write_ordering]);
}

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
/**
 * drbd_submit_ee()
 * @mdev:	DRBD device.
 * @e:		epoch entry
 * @rw:		flag field, see bio->bi_rw
 */
/* TODO allocate from our own bio_set. */
int drbd_submit_ee(struct drbd_conf *mdev, struct drbd_epoch_entry *e,
		const unsigned rw, const int fault_type)
{
	struct bio *bios = NULL;
	struct bio *bio;
	struct page *page = e->pages;
	sector_t sector = e->sector;
	unsigned ds = e->size;
	unsigned n_bios = 0;
	unsigned nr_pages = (ds + PAGE_SIZE -1) >> PAGE_SHIFT;

	/* In most cases, we will only need one bio.  But in case the lower
	 * level restrictions happen to be different at this offset on this
	 * side than those of the sending peer, we may need to submit the
	 * request in more than one bio. */
next_bio:
	bio = bio_alloc(GFP_NOIO, nr_pages);
	if (!bio) {
		dev_err(DEV, "submit_ee: Allocation of a bio failed\n");
		goto fail;
	}
	/* > e->sector, unless this is the first bio */
	bio->bi_sector = sector;
	bio->bi_bdev = mdev->ldev->backing_bdev;
	/* we special case some flags in the multi-bio case, see below
1195
	 * (REQ_UNPLUG, REQ_HARDBARRIER) */
1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223
	bio->bi_rw = rw;
	bio->bi_private = e;
	bio->bi_end_io = drbd_endio_sec;

	bio->bi_next = bios;
	bios = bio;
	++n_bios;

	page_chain_for_each(page) {
		unsigned len = min_t(unsigned, ds, PAGE_SIZE);
		if (!bio_add_page(bio, page, len, 0)) {
			/* a single page must always be possible! */
			BUG_ON(bio->bi_vcnt == 0);
			goto next_bio;
		}
		ds -= len;
		sector += len >> 9;
		--nr_pages;
	}
	D_ASSERT(page == NULL);
	D_ASSERT(ds == 0);

	atomic_set(&e->pending_bios, n_bios);
	do {
		bio = bios;
		bios = bios->bi_next;
		bio->bi_next = NULL;

1224
		/* strip off REQ_UNPLUG unless it is the last bio */
1225
		if (bios)
1226
			bio->bi_rw &= ~REQ_UNPLUG;
1227 1228 1229

		drbd_generic_make_request(mdev, fault_type, bio);

1230
		/* strip off REQ_HARDBARRIER,
1231 1232
		 * unless it is the first or last bio */
		if (bios && bios->bi_next)
1233
			bios->bi_rw &= ~REQ_HARDBARRIER;
1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246
	} while (bios);
	maybe_kick_lo(mdev);
	return 0;

fail:
	while (bios) {
		bio = bios;
		bios = bios->bi_next;
		bio_put(bio);
	}
	return -ENOMEM;
}

P
Philipp Reisner 已提交
1247
/**
1248
 * w_e_reissue() - Worker callback; Resubmit a bio, without REQ_HARDBARRIER set
P
Philipp Reisner 已提交
1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259
 * @mdev:	DRBD device.
 * @w:		work object.
 * @cancel:	The connection will be closed anyways (unused in this callback)
 */
int w_e_reissue(struct drbd_conf *mdev, struct drbd_work *w, int cancel) __releases(local)
{
	struct drbd_epoch_entry *e = (struct drbd_epoch_entry *)w;
	/* We leave DE_CONTAINS_A_BARRIER and EE_IS_BARRIER in place,
	   (and DE_BARRIER_IN_NEXT_EPOCH_ISSUED in the previous Epoch)
	   so that we can finish that epoch in drbd_may_finish_epoch().
	   That is necessary if we already have a long chain of Epochs, before
1260
	   we realize that REQ_HARDBARRIER is actually not supported */
P
Philipp Reisner 已提交
1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272

	/* As long as the -ENOTSUPP on the barrier is reported immediately
	   that will never trigger. If it is reported late, we will just
	   print that warning and continue correctly for all future requests
	   with WO_bdev_flush */
	if (previous_epoch(mdev, e->epoch))
		dev_warn(DEV, "Write ordering was not enforced (one time event)\n");

	/* we still have a local reference,
	 * get_ldev was done in receive_Data. */

	e->w.cb = e_end_block;
1273 1274 1275 1276 1277 1278 1279
	if (drbd_submit_ee(mdev, e, WRITE, DRBD_FAULT_DT_WR) != 0) {
		/* drbd_submit_ee fails for one reason only:
		 * if was not able to allocate sufficient bios.
		 * requeue, try again later. */
		e->w.cb = w_e_reissue;
		drbd_queue_work(&mdev->data.work, &e->w);
	}
P
Philipp Reisner 已提交
1280 1281 1282
	return 1;
}

1283
static int receive_Barrier(struct drbd_conf *mdev, enum drbd_packets cmd, unsigned int data_size)
P
Philipp Reisner 已提交
1284 1285
{
	int rv, issue_flush;
1286
	struct p_barrier *p = &mdev->data.rbuf.barrier;
P
Philipp Reisner 已提交
1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310
	struct drbd_epoch *epoch;

	inc_unacked(mdev);

	if (mdev->net_conf->wire_protocol != DRBD_PROT_C)
		drbd_kick_lo(mdev);

	mdev->current_epoch->barrier_nr = p->barrier;
	rv = drbd_may_finish_epoch(mdev, mdev->current_epoch, EV_GOT_BARRIER_NR);

	/* P_BARRIER_ACK may imply that the corresponding extent is dropped from
	 * the activity log, which means it would not be resynced in case the
	 * R_PRIMARY crashes now.
	 * Therefore we must send the barrier_ack after the barrier request was
	 * completed. */
	switch (mdev->write_ordering) {
	case WO_bio_barrier:
	case WO_none:
		if (rv == FE_RECYCLED)
			return TRUE;
		break;

	case WO_bdev_flush:
	case WO_drain_io:
1311 1312 1313 1314 1315
		if (rv == FE_STILL_LIVE) {
			set_bit(DE_BARRIER_IN_NEXT_EPOCH_ISSUED, &mdev->current_epoch->flags);
			drbd_wait_ee_list_empty(mdev, &mdev->active_ee);
			rv = drbd_flush_after_epoch(mdev, mdev->current_epoch);
		}
P
Philipp Reisner 已提交
1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329
		if (rv == FE_RECYCLED)
			return TRUE;

		/* The asender will send all the ACKs and barrier ACKs out, since
		   all EEs moved from the active_ee to the done_ee. We need to
		   provide a new epoch object for the EEs that come in soon */
		break;
	}

	/* receiver context, in the writeout path of the other node.
	 * avoid potential distributed deadlock */
	epoch = kmalloc(sizeof(struct drbd_epoch), GFP_NOIO);
	if (!epoch) {
		dev_warn(DEV, "Allocation of an epoch failed, slowing down\n");
D
Dan Carpenter 已提交
1330
		issue_flush = !test_and_set_bit(DE_BARRIER_IN_NEXT_EPOCH_ISSUED, &mdev->current_epoch->flags);
P
Philipp Reisner 已提交
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
		drbd_wait_ee_list_empty(mdev, &mdev->active_ee);
		if (issue_flush) {
			rv = drbd_flush_after_epoch(mdev, mdev->current_epoch);
			if (rv == FE_RECYCLED)
				return TRUE;
		}

		drbd_wait_ee_list_empty(mdev, &mdev->done_ee);

		return TRUE;
	}

	epoch->flags = 0;
	atomic_set(&epoch->epoch_size, 0);
	atomic_set(&epoch->active, 0);

	spin_lock(&mdev->epoch_lock);
	if (atomic_read(&mdev->current_epoch->epoch_size)) {
		list_add(&epoch->list, &mdev->current_epoch->list);
		mdev->current_epoch = epoch;
		mdev->epochs++;
	} else {
		/* The current_epoch got recycled while we allocated this one... */
		kfree(epoch);
	}
	spin_unlock(&mdev->epoch_lock);

	return TRUE;
}

/* used from receive_RSDataReply (recv_resync_read)
 * and from receive_Data */
static struct drbd_epoch_entry *
read_in_block(struct drbd_conf *mdev, u64 id, sector_t sector, int data_size) __must_hold(local)
{
1366
	const sector_t capacity = drbd_get_capacity(mdev->this_bdev);
P
Philipp Reisner 已提交
1367 1368
	struct drbd_epoch_entry *e;
	struct page *page;
1369
	int dgs, ds, rr;
P
Philipp Reisner 已提交
1370 1371
	void *dig_in = mdev->int_dig_in;
	void *dig_vv = mdev->int_dig_vv;
1372
	unsigned long *data;
P
Philipp Reisner 已提交
1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390

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

	if (dgs) {
		rr = drbd_recv(mdev, dig_in, dgs);
		if (rr != dgs) {
			dev_warn(DEV, "short read receiving data digest: read %d expected %d\n",
			     rr, dgs);
			return NULL;
		}
	}

	data_size -= dgs;

	ERR_IF(data_size &  0x1ff) return NULL;
	ERR_IF(data_size >  DRBD_MAX_SEGMENT_SIZE) return NULL;

1391 1392 1393 1394 1395 1396 1397 1398 1399
	/* even though we trust out peer,
	 * we sometimes have to double check. */
	if (sector + (data_size>>9) > capacity) {
		dev_err(DEV, "capacity: %llus < sector: %llus + size: %u\n",
			(unsigned long long)capacity,
			(unsigned long long)sector, data_size);
		return NULL;
	}

P
Philipp Reisner 已提交
1400 1401 1402 1403 1404 1405
	/* GFP_NOIO, because we must not cause arbitrary write-out: in a DRBD
	 * "criss-cross" setup, that might cause write-out on some other DRBD,
	 * which in turn might block on the other node at this very place.  */
	e = drbd_alloc_ee(mdev, id, sector, data_size, GFP_NOIO);
	if (!e)
		return NULL;
1406

P
Philipp Reisner 已提交
1407
	ds = data_size;
1408 1409 1410
	page = e->pages;
	page_chain_for_each(page) {
		unsigned len = min_t(int, ds, PAGE_SIZE);
1411
		data = kmap(page);
1412
		rr = drbd_recv(mdev, data, len);
1413 1414 1415 1416
		if (FAULT_ACTIVE(mdev, DRBD_FAULT_RECEIVE)) {
			dev_err(DEV, "Fault injection: Corrupting data on receive\n");
			data[0] = data[0] ^ (unsigned long)-1;
		}
P
Philipp Reisner 已提交
1417
		kunmap(page);
1418
		if (rr != len) {
P
Philipp Reisner 已提交
1419 1420
			drbd_free_ee(mdev, e);
			dev_warn(DEV, "short read receiving data: read %d expected %d\n",
1421
			     rr, len);
P
Philipp Reisner 已提交
1422 1423 1424 1425 1426 1427
			return NULL;
		}
		ds -= rr;
	}

	if (dgs) {
1428
		drbd_csum_ee(mdev, mdev->integrity_r_tfm, e, dig_vv);
P
Philipp Reisner 已提交
1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449
		if (memcmp(dig_in, dig_vv, dgs)) {
			dev_err(DEV, "Digest integrity check FAILED.\n");
			drbd_bcast_ee(mdev, "digest failed",
					dgs, dig_in, dig_vv, e);
			drbd_free_ee(mdev, e);
			return NULL;
		}
	}
	mdev->recv_cnt += data_size>>9;
	return e;
}

/* drbd_drain_block() just takes a data block
 * out of the socket input buffer, and discards it.
 */
static int drbd_drain_block(struct drbd_conf *mdev, int data_size)
{
	struct page *page;
	int rr, rv = 1;
	void *data;

1450 1451 1452
	if (!data_size)
		return TRUE;

1453
	page = drbd_pp_alloc(mdev, 1, 1);
P
Philipp Reisner 已提交
1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466

	data = kmap(page);
	while (data_size) {
		rr = drbd_recv(mdev, data, min_t(int, data_size, PAGE_SIZE));
		if (rr != min_t(int, data_size, PAGE_SIZE)) {
			rv = 0;
			dev_warn(DEV, "short read receiving data: read %d expected %d\n",
			     rr, min_t(int, data_size, PAGE_SIZE));
			break;
		}
		data_size -= rr;
	}
	kunmap(page);
1467
	drbd_pp_free(mdev, page, 0);
P
Philipp Reisner 已提交
1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516
	return rv;
}

static int recv_dless_read(struct drbd_conf *mdev, struct drbd_request *req,
			   sector_t sector, int data_size)
{
	struct bio_vec *bvec;
	struct bio *bio;
	int dgs, rr, i, expect;
	void *dig_in = mdev->int_dig_in;
	void *dig_vv = mdev->int_dig_vv;

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

	if (dgs) {
		rr = drbd_recv(mdev, dig_in, dgs);
		if (rr != dgs) {
			dev_warn(DEV, "short read receiving data reply digest: read %d expected %d\n",
			     rr, dgs);
			return 0;
		}
	}

	data_size -= dgs;

	/* optimistically update recv_cnt.  if receiving fails below,
	 * we disconnect anyways, and counters will be reset. */
	mdev->recv_cnt += data_size>>9;

	bio = req->master_bio;
	D_ASSERT(sector == bio->bi_sector);

	bio_for_each_segment(bvec, bio, i) {
		expect = min_t(int, data_size, bvec->bv_len);
		rr = drbd_recv(mdev,
			     kmap(bvec->bv_page)+bvec->bv_offset,
			     expect);
		kunmap(bvec->bv_page);
		if (rr != expect) {
			dev_warn(DEV, "short read receiving data reply: "
			     "read %d expected %d\n",
			     rr, expect);
			return 0;
		}
		data_size -= rr;
	}

	if (dgs) {
1517
		drbd_csum_bio(mdev, mdev->integrity_r_tfm, bio, dig_vv);
P
Philipp Reisner 已提交
1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537
		if (memcmp(dig_in, dig_vv, dgs)) {
			dev_err(DEV, "Digest integrity check FAILED. Broken NICs?\n");
			return 0;
		}
	}

	D_ASSERT(data_size == 0);
	return 1;
}

/* e_end_resync_block() is called via
 * drbd_process_done_ee() by asender only */
static int e_end_resync_block(struct drbd_conf *mdev, struct drbd_work *w, int unused)
{
	struct drbd_epoch_entry *e = (struct drbd_epoch_entry *)w;
	sector_t sector = e->sector;
	int ok;

	D_ASSERT(hlist_unhashed(&e->colision));

1538
	if (likely((e->flags & EE_WAS_ERROR) == 0)) {
P
Philipp Reisner 已提交
1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556
		drbd_set_in_sync(mdev, sector, e->size);
		ok = drbd_send_ack(mdev, P_RS_WRITE_ACK, e);
	} else {
		/* Record failure to sync */
		drbd_rs_failed_io(mdev, sector, e->size);

		ok  = drbd_send_ack(mdev, P_NEG_ACK, e);
	}
	dec_unacked(mdev);

	return ok;
}

static int recv_resync_read(struct drbd_conf *mdev, sector_t sector, int data_size) __releases(local)
{
	struct drbd_epoch_entry *e;

	e = read_in_block(mdev, ID_SYNCER, sector, data_size);
1557 1558
	if (!e)
		goto fail;
P
Philipp Reisner 已提交
1559 1560 1561 1562 1563 1564 1565

	dec_rs_pending(mdev);

	inc_unacked(mdev);
	/* corresponding dec_unacked() in e_end_resync_block()
	 * respective _drbd_clear_done_ee */

1566 1567
	e->w.cb = e_end_resync_block;

P
Philipp Reisner 已提交
1568 1569 1570 1571
	spin_lock_irq(&mdev->req_lock);
	list_add(&e->w.list, &mdev->sync_ee);
	spin_unlock_irq(&mdev->req_lock);

1572
	atomic_add(data_size >> 9, &mdev->rs_sect_ev);
1573 1574
	if (drbd_submit_ee(mdev, e, WRITE, DRBD_FAULT_RS_WR) == 0)
		return TRUE;
P
Philipp Reisner 已提交
1575

1576 1577 1578 1579 1580 1581 1582
	/* drbd_submit_ee currently fails for one reason only:
	 * not being able to allocate enough bios.
	 * Is dropping the connection going to help? */
	spin_lock_irq(&mdev->req_lock);
	list_del(&e->w.list);
	spin_unlock_irq(&mdev->req_lock);

1583 1584 1585 1586
	drbd_free_ee(mdev, e);
fail:
	put_ldev(mdev);
	return FALSE;
P
Philipp Reisner 已提交
1587 1588
}

1589
static int receive_DataReply(struct drbd_conf *mdev, enum drbd_packets cmd, unsigned int data_size)
P
Philipp Reisner 已提交
1590 1591 1592 1593
{
	struct drbd_request *req;
	sector_t sector;
	int ok;
1594
	struct p_data *p = &mdev->data.rbuf.data;
P
Philipp Reisner 已提交
1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619

	sector = be64_to_cpu(p->sector);

	spin_lock_irq(&mdev->req_lock);
	req = _ar_id_to_req(mdev, p->block_id, sector);
	spin_unlock_irq(&mdev->req_lock);
	if (unlikely(!req)) {
		dev_err(DEV, "Got a corrupt block_id/sector pair(1).\n");
		return FALSE;
	}

	/* hlist_del(&req->colision) is done in _req_may_be_done, to avoid
	 * special casing it there for the various failure cases.
	 * still no race with drbd_fail_pending_reads */
	ok = recv_dless_read(mdev, req, sector, data_size);

	if (ok)
		req_mod(req, data_received);
	/* else: nothing. handled from drbd_disconnect...
	 * I don't think we may complete this just yet
	 * in case we are "on-disconnect: freeze" */

	return ok;
}

1620
static int receive_RSDataReply(struct drbd_conf *mdev, enum drbd_packets cmd, unsigned int data_size)
P
Philipp Reisner 已提交
1621 1622 1623
{
	sector_t sector;
	int ok;
1624
	struct p_data *p = &mdev->data.rbuf.data;
P
Philipp Reisner 已提交
1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639

	sector = be64_to_cpu(p->sector);
	D_ASSERT(p->block_id == ID_SYNCER);

	if (get_ldev(mdev)) {
		/* data is submitted to disk within recv_resync_read.
		 * corresponding put_ldev done below on error,
		 * or in drbd_endio_write_sec. */
		ok = recv_resync_read(mdev, sector, data_size);
	} else {
		if (__ratelimit(&drbd_ratelimit_state))
			dev_err(DEV, "Can not write resync data to local disk.\n");

		ok = drbd_drain_block(mdev, data_size);

1640
		drbd_send_ack_dp(mdev, P_NEG_ACK, p, data_size);
P
Philipp Reisner 已提交
1641 1642
	}

1643 1644
	atomic_add(data_size >> 9, &mdev->rs_sect_in);

P
Philipp Reisner 已提交
1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664
	return ok;
}

/* e_end_block() is called via drbd_process_done_ee().
 * this means this function only runs in the asender thread
 */
static int e_end_block(struct drbd_conf *mdev, struct drbd_work *w, int cancel)
{
	struct drbd_epoch_entry *e = (struct drbd_epoch_entry *)w;
	sector_t sector = e->sector;
	struct drbd_epoch *epoch;
	int ok = 1, pcmd;

	if (e->flags & EE_IS_BARRIER) {
		epoch = previous_epoch(mdev, e->epoch);
		if (epoch)
			drbd_may_finish_epoch(mdev, epoch, EV_BARRIER_DONE + (cancel ? EV_CLEANUP : 0));
	}

	if (mdev->net_conf->wire_protocol == DRBD_PROT_C) {
1665
		if (likely((e->flags & EE_WAS_ERROR) == 0)) {
P
Philipp Reisner 已提交
1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 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
			pcmd = (mdev->state.conn >= C_SYNC_SOURCE &&
				mdev->state.conn <= C_PAUSED_SYNC_T &&
				e->flags & EE_MAY_SET_IN_SYNC) ?
				P_RS_WRITE_ACK : P_WRITE_ACK;
			ok &= drbd_send_ack(mdev, pcmd, e);
			if (pcmd == P_RS_WRITE_ACK)
				drbd_set_in_sync(mdev, sector, e->size);
		} else {
			ok  = drbd_send_ack(mdev, P_NEG_ACK, e);
			/* we expect it to be marked out of sync anyways...
			 * maybe assert this?  */
		}
		dec_unacked(mdev);
	}
	/* we delete from the conflict detection hash _after_ we sent out the
	 * P_WRITE_ACK / P_NEG_ACK, to get the sequence number right.  */
	if (mdev->net_conf->two_primaries) {
		spin_lock_irq(&mdev->req_lock);
		D_ASSERT(!hlist_unhashed(&e->colision));
		hlist_del_init(&e->colision);
		spin_unlock_irq(&mdev->req_lock);
	} else {
		D_ASSERT(hlist_unhashed(&e->colision));
	}

	drbd_may_finish_epoch(mdev, e->epoch, EV_PUT + (cancel ? EV_CLEANUP : 0));

	return ok;
}

static int e_send_discard_ack(struct drbd_conf *mdev, struct drbd_work *w, int unused)
{
	struct drbd_epoch_entry *e = (struct drbd_epoch_entry *)w;
	int ok = 1;

	D_ASSERT(mdev->net_conf->wire_protocol == DRBD_PROT_C);
	ok = drbd_send_ack(mdev, P_DISCARD_ACK, e);

	spin_lock_irq(&mdev->req_lock);
	D_ASSERT(!hlist_unhashed(&e->colision));
	hlist_del_init(&e->colision);
	spin_unlock_irq(&mdev->req_lock);

	dec_unacked(mdev);

	return ok;
}

/* Called from receive_Data.
 * Synchronize packets on sock with packets on msock.
 *
 * This is here so even when a P_DATA packet traveling via sock overtook an Ack
 * packet traveling on msock, they are still processed in the order they have
 * been sent.
 *
 * Note: we don't care for Ack packets overtaking P_DATA packets.
 *
 * In case packet_seq is larger than mdev->peer_seq number, there are
 * outstanding packets on the msock. We wait for them to arrive.
 * In case we are the logically next packet, we update mdev->peer_seq
 * ourselves. Correctly handles 32bit wrap around.
 *
 * Assume we have a 10 GBit connection, that is about 1<<30 byte per second,
 * about 1<<21 sectors per second. So "worst" case, we have 1<<3 == 8 seconds
 * for the 24bit wrap (historical atomic_t guarantee on some archs), and we have
 * 1<<9 == 512 seconds aka ages for the 32bit wrap around...
 *
 * returns 0 if we may process the packet,
 * -ERESTARTSYS if we were interrupted (by disconnect signal). */
static int drbd_wait_peer_seq(struct drbd_conf *mdev, const u32 packet_seq)
{
	DEFINE_WAIT(wait);
	unsigned int p_seq;
	long timeout;
	int ret = 0;
	spin_lock(&mdev->peer_seq_lock);
	for (;;) {
		prepare_to_wait(&mdev->seq_wait, &wait, TASK_INTERRUPTIBLE);
		if (seq_le(packet_seq, mdev->peer_seq+1))
			break;
		if (signal_pending(current)) {
			ret = -ERESTARTSYS;
			break;
		}
		p_seq = mdev->peer_seq;
		spin_unlock(&mdev->peer_seq_lock);
		timeout = schedule_timeout(30*HZ);
		spin_lock(&mdev->peer_seq_lock);
		if (timeout == 0 && p_seq == mdev->peer_seq) {
			ret = -ETIMEDOUT;
			dev_err(DEV, "ASSERT FAILED waited 30 seconds for sequence update, forcing reconnect\n");
			break;
		}
	}
	finish_wait(&mdev->seq_wait, &wait);
	if (mdev->peer_seq+1 == packet_seq)
		mdev->peer_seq++;
	spin_unlock(&mdev->peer_seq_lock);
	return ret;
}

1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778
static unsigned long write_flags_to_bio(struct drbd_conf *mdev, u32 dpf)
{
	if (mdev->agreed_pro_version >= 95)
		return  (dpf & DP_RW_SYNC ? REQ_SYNC : 0) |
			(dpf & DP_UNPLUG ? REQ_UNPLUG : 0) |
			(dpf & DP_FUA ? REQ_FUA : 0) |
			(dpf & DP_FLUSH ? REQ_FUA : 0) |
			(dpf & DP_DISCARD ? REQ_DISCARD : 0);
	else
		return dpf & DP_RW_SYNC ? (REQ_SYNC | REQ_UNPLUG) : 0;
}

P
Philipp Reisner 已提交
1779
/* mirrored write */
1780
static int receive_Data(struct drbd_conf *mdev, enum drbd_packets cmd, unsigned int data_size)
P
Philipp Reisner 已提交
1781 1782 1783
{
	sector_t sector;
	struct drbd_epoch_entry *e;
1784
	struct p_data *p = &mdev->data.rbuf.data;
P
Philipp Reisner 已提交
1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796
	int rw = WRITE;
	u32 dp_flags;

	if (!get_ldev(mdev)) {
		if (__ratelimit(&drbd_ratelimit_state))
			dev_err(DEV, "Can not write mirrored data block "
			    "to local disk.\n");
		spin_lock(&mdev->peer_seq_lock);
		if (mdev->peer_seq+1 == be32_to_cpu(p->seq_num))
			mdev->peer_seq++;
		spin_unlock(&mdev->peer_seq_lock);

1797
		drbd_send_ack_dp(mdev, P_NEG_ACK, p, data_size);
P
Philipp Reisner 已提交
1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828
		atomic_inc(&mdev->current_epoch->epoch_size);
		return drbd_drain_block(mdev, data_size);
	}

	/* get_ldev(mdev) successful.
	 * Corresponding put_ldev done either below (on various errors),
	 * or in drbd_endio_write_sec, if we successfully submit the data at
	 * the end of this function. */

	sector = be64_to_cpu(p->sector);
	e = read_in_block(mdev, p->block_id, sector, data_size);
	if (!e) {
		put_ldev(mdev);
		return FALSE;
	}

	e->w.cb = e_end_block;

	spin_lock(&mdev->epoch_lock);
	e->epoch = mdev->current_epoch;
	atomic_inc(&e->epoch->epoch_size);
	atomic_inc(&e->epoch->active);

	if (mdev->write_ordering == WO_bio_barrier && atomic_read(&e->epoch->epoch_size) == 1) {
		struct drbd_epoch *epoch;
		/* Issue a barrier if we start a new epoch, and the previous epoch
		   was not a epoch containing a single request which already was
		   a Barrier. */
		epoch = list_entry(e->epoch->list.prev, struct drbd_epoch, list);
		if (epoch == e->epoch) {
			set_bit(DE_CONTAINS_A_BARRIER, &e->epoch->flags);
1829
			rw |= REQ_HARDBARRIER;
P
Philipp Reisner 已提交
1830 1831 1832 1833 1834 1835
			e->flags |= EE_IS_BARRIER;
		} else {
			if (atomic_read(&epoch->epoch_size) > 1 ||
			    !test_bit(DE_CONTAINS_A_BARRIER, &epoch->flags)) {
				set_bit(DE_BARRIER_IN_NEXT_EPOCH_ISSUED, &epoch->flags);
				set_bit(DE_CONTAINS_A_BARRIER, &e->epoch->flags);
1836
				rw |= REQ_HARDBARRIER;
P
Philipp Reisner 已提交
1837 1838 1839 1840 1841 1842 1843
				e->flags |= EE_IS_BARRIER;
			}
		}
	}
	spin_unlock(&mdev->epoch_lock);

	dp_flags = be32_to_cpu(p->dp_flags);
1844 1845
	rw |= write_flags_to_bio(mdev, dp_flags);

P
Philipp Reisner 已提交
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 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 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 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997
	if (dp_flags & DP_MAY_SET_IN_SYNC)
		e->flags |= EE_MAY_SET_IN_SYNC;

	/* I'm the receiver, I do hold a net_cnt reference. */
	if (!mdev->net_conf->two_primaries) {
		spin_lock_irq(&mdev->req_lock);
	} else {
		/* don't get the req_lock yet,
		 * we may sleep in drbd_wait_peer_seq */
		const int size = e->size;
		const int discard = test_bit(DISCARD_CONCURRENT, &mdev->flags);
		DEFINE_WAIT(wait);
		struct drbd_request *i;
		struct hlist_node *n;
		struct hlist_head *slot;
		int first;

		D_ASSERT(mdev->net_conf->wire_protocol == DRBD_PROT_C);
		BUG_ON(mdev->ee_hash == NULL);
		BUG_ON(mdev->tl_hash == NULL);

		/* conflict detection and handling:
		 * 1. wait on the sequence number,
		 *    in case this data packet overtook ACK packets.
		 * 2. check our hash tables for conflicting requests.
		 *    we only need to walk the tl_hash, since an ee can not
		 *    have a conflict with an other ee: on the submitting
		 *    node, the corresponding req had already been conflicting,
		 *    and a conflicting req is never sent.
		 *
		 * Note: for two_primaries, we are protocol C,
		 * so there cannot be any request that is DONE
		 * but still on the transfer log.
		 *
		 * unconditionally add to the ee_hash.
		 *
		 * if no conflicting request is found:
		 *    submit.
		 *
		 * if any conflicting request is found
		 * that has not yet been acked,
		 * AND I have the "discard concurrent writes" flag:
		 *	 queue (via done_ee) the P_DISCARD_ACK; OUT.
		 *
		 * if any conflicting request is found:
		 *	 block the receiver, waiting on misc_wait
		 *	 until no more conflicting requests are there,
		 *	 or we get interrupted (disconnect).
		 *
		 *	 we do not just write after local io completion of those
		 *	 requests, but only after req is done completely, i.e.
		 *	 we wait for the P_DISCARD_ACK to arrive!
		 *
		 *	 then proceed normally, i.e. submit.
		 */
		if (drbd_wait_peer_seq(mdev, be32_to_cpu(p->seq_num)))
			goto out_interrupted;

		spin_lock_irq(&mdev->req_lock);

		hlist_add_head(&e->colision, ee_hash_slot(mdev, sector));

#define OVERLAPS overlaps(i->sector, i->size, sector, size)
		slot = tl_hash_slot(mdev, sector);
		first = 1;
		for (;;) {
			int have_unacked = 0;
			int have_conflict = 0;
			prepare_to_wait(&mdev->misc_wait, &wait,
				TASK_INTERRUPTIBLE);
			hlist_for_each_entry(i, n, slot, colision) {
				if (OVERLAPS) {
					/* only ALERT on first iteration,
					 * we may be woken up early... */
					if (first)
						dev_alert(DEV, "%s[%u] Concurrent local write detected!"
						      "	new: %llus +%u; pending: %llus +%u\n",
						      current->comm, current->pid,
						      (unsigned long long)sector, size,
						      (unsigned long long)i->sector, i->size);
					if (i->rq_state & RQ_NET_PENDING)
						++have_unacked;
					++have_conflict;
				}
			}
#undef OVERLAPS
			if (!have_conflict)
				break;

			/* Discard Ack only for the _first_ iteration */
			if (first && discard && have_unacked) {
				dev_alert(DEV, "Concurrent write! [DISCARD BY FLAG] sec=%llus\n",
				     (unsigned long long)sector);
				inc_unacked(mdev);
				e->w.cb = e_send_discard_ack;
				list_add_tail(&e->w.list, &mdev->done_ee);

				spin_unlock_irq(&mdev->req_lock);

				/* we could probably send that P_DISCARD_ACK ourselves,
				 * but I don't like the receiver using the msock */

				put_ldev(mdev);
				wake_asender(mdev);
				finish_wait(&mdev->misc_wait, &wait);
				return TRUE;
			}

			if (signal_pending(current)) {
				hlist_del_init(&e->colision);

				spin_unlock_irq(&mdev->req_lock);

				finish_wait(&mdev->misc_wait, &wait);
				goto out_interrupted;
			}

			spin_unlock_irq(&mdev->req_lock);
			if (first) {
				first = 0;
				dev_alert(DEV, "Concurrent write! [W AFTERWARDS] "
				     "sec=%llus\n", (unsigned long long)sector);
			} else if (discard) {
				/* we had none on the first iteration.
				 * there must be none now. */
				D_ASSERT(have_unacked == 0);
			}
			schedule();
			spin_lock_irq(&mdev->req_lock);
		}
		finish_wait(&mdev->misc_wait, &wait);
	}

	list_add(&e->w.list, &mdev->active_ee);
	spin_unlock_irq(&mdev->req_lock);

	switch (mdev->net_conf->wire_protocol) {
	case DRBD_PROT_C:
		inc_unacked(mdev);
		/* corresponding dec_unacked() in e_end_block()
		 * respective _drbd_clear_done_ee */
		break;
	case DRBD_PROT_B:
		/* I really don't like it that the receiver thread
		 * sends on the msock, but anyways */
		drbd_send_ack(mdev, P_RECV_ACK, e);
		break;
	case DRBD_PROT_A:
		/* nothing to do */
		break;
	}

1998
	if (mdev->state.pdsk < D_INCONSISTENT) {
P
Philipp Reisner 已提交
1999 2000 2001
		/* In case we have the only disk of the cluster, */
		drbd_set_out_of_sync(mdev, e->sector, e->size);
		e->flags |= EE_CALL_AL_COMPLETE_IO;
2002
		e->flags &= ~EE_MAY_SET_IN_SYNC;
P
Philipp Reisner 已提交
2003 2004 2005
		drbd_al_begin_io(mdev, e->sector);
	}

2006 2007
	if (drbd_submit_ee(mdev, e, rw, DRBD_FAULT_DT_WR) == 0)
		return TRUE;
P
Philipp Reisner 已提交
2008

2009 2010 2011 2012 2013 2014 2015 2016 2017 2018
	/* drbd_submit_ee currently fails for one reason only:
	 * not being able to allocate enough bios.
	 * Is dropping the connection going to help? */
	spin_lock_irq(&mdev->req_lock);
	list_del(&e->w.list);
	hlist_del_init(&e->colision);
	spin_unlock_irq(&mdev->req_lock);
	if (e->flags & EE_CALL_AL_COMPLETE_IO)
		drbd_al_complete_io(mdev, e->sector);

P
Philipp Reisner 已提交
2019 2020 2021 2022 2023 2024 2025 2026 2027
out_interrupted:
	/* yes, the epoch_size now is imbalanced.
	 * but we drop the connection anyways, so we don't have a chance to
	 * receive a barrier... atomic_inc(&mdev->epoch_size); */
	put_ldev(mdev);
	drbd_free_ee(mdev, e);
	return FALSE;
}

2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076
/* We may throttle resync, if the lower device seems to be busy,
 * and current sync rate is above c_min_rate.
 *
 * To decide whether or not the lower device is busy, we use a scheme similar
 * to MD RAID is_mddev_idle(): if the partition stats reveal "significant"
 * (more than 64 sectors) of activity we cannot account for with our own resync
 * activity, it obviously is "busy".
 *
 * The current sync rate used here uses only the most recent two step marks,
 * to have a short time average so we can react faster.
 */
int drbd_rs_should_slow_down(struct drbd_conf *mdev)
{
	struct gendisk *disk = mdev->ldev->backing_bdev->bd_contains->bd_disk;
	unsigned long db, dt, dbdt;
	int curr_events;
	int throttle = 0;

	/* feature disabled? */
	if (mdev->sync_conf.c_min_rate == 0)
		return 0;

	curr_events = (int)part_stat_read(&disk->part0, sectors[0]) +
		      (int)part_stat_read(&disk->part0, sectors[1]) -
			atomic_read(&mdev->rs_sect_ev);
	if (!mdev->rs_last_events || curr_events - mdev->rs_last_events > 64) {
		unsigned long rs_left;
		int i;

		mdev->rs_last_events = curr_events;

		/* sync speed average over the last 2*DRBD_SYNC_MARK_STEP,
		 * approx. */
		i = (mdev->rs_last_mark + DRBD_SYNC_MARKS-2) % DRBD_SYNC_MARKS;
		rs_left = drbd_bm_total_weight(mdev) - mdev->rs_failed;

		dt = ((long)jiffies - (long)mdev->rs_mark_time[i]) / HZ;
		if (!dt)
			dt++;
		db = mdev->rs_mark_left[i] - rs_left;
		dbdt = Bit2KB(db/dt);

		if (dbdt > mdev->sync_conf.c_min_rate)
			throttle = 1;
	}
	return throttle;
}


2077
static int receive_DataRequest(struct drbd_conf *mdev, enum drbd_packets cmd, unsigned int digest_size)
P
Philipp Reisner 已提交
2078 2079 2080 2081 2082
{
	sector_t sector;
	const sector_t capacity = drbd_get_capacity(mdev->this_bdev);
	struct drbd_epoch_entry *e;
	struct digest_info *di = NULL;
2083
	int size, verb;
P
Philipp Reisner 已提交
2084
	unsigned int fault_type;
2085
	struct p_block_req *p =	&mdev->data.rbuf.block_req;
P
Philipp Reisner 已提交
2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101

	sector = be64_to_cpu(p->sector);
	size   = be32_to_cpu(p->blksize);

	if (size <= 0 || (size & 0x1ff) != 0 || size > DRBD_MAX_SEGMENT_SIZE) {
		dev_err(DEV, "%s:%d: sector: %llus, size: %u\n", __FILE__, __LINE__,
				(unsigned long long)sector, size);
		return FALSE;
	}
	if (sector + (size>>9) > capacity) {
		dev_err(DEV, "%s:%d: sector: %llus, size: %u\n", __FILE__, __LINE__,
				(unsigned long long)sector, size);
		return FALSE;
	}

	if (!get_ldev_if_state(mdev, D_UP_TO_DATE)) {
2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121
		verb = 1;
		switch (cmd) {
		case P_DATA_REQUEST:
			drbd_send_ack_rp(mdev, P_NEG_DREPLY, p);
			break;
		case P_RS_DATA_REQUEST:
		case P_CSUM_RS_REQUEST:
		case P_OV_REQUEST:
			drbd_send_ack_rp(mdev, P_NEG_RS_DREPLY , p);
			break;
		case P_OV_REPLY:
			verb = 0;
			dec_rs_pending(mdev);
			drbd_send_ack_ex(mdev, P_OV_RESULT, sector, size, ID_IN_SYNC);
			break;
		default:
			dev_err(DEV, "unexpected command (%s) in receive_DataRequest\n",
				cmdname(cmd));
		}
		if (verb && __ratelimit(&drbd_ratelimit_state))
P
Philipp Reisner 已提交
2122 2123
			dev_err(DEV, "Can not satisfy peer's read request, "
			    "no local data.\n");
2124

L
Lars Ellenberg 已提交
2125 2126
		/* drain possibly payload */
		return drbd_drain_block(mdev, digest_size);
P
Philipp Reisner 已提交
2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137
	}

	/* GFP_NOIO, because we must not cause arbitrary write-out: in a DRBD
	 * "criss-cross" setup, that might cause write-out on some other DRBD,
	 * which in turn might block on the other node at this very place.  */
	e = drbd_alloc_ee(mdev, p->block_id, sector, size, GFP_NOIO);
	if (!e) {
		put_ldev(mdev);
		return FALSE;
	}

2138
	switch (cmd) {
P
Philipp Reisner 已提交
2139 2140 2141
	case P_DATA_REQUEST:
		e->w.cb = w_e_end_data_req;
		fault_type = DRBD_FAULT_DT_RD;
2142 2143 2144
		/* application IO, don't drbd_rs_begin_io */
		goto submit;

P
Philipp Reisner 已提交
2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159
	case P_RS_DATA_REQUEST:
		e->w.cb = w_e_end_rsdata_req;
		fault_type = DRBD_FAULT_RS_RD;
		break;

	case P_OV_REPLY:
	case P_CSUM_RS_REQUEST:
		fault_type = DRBD_FAULT_RS_RD;
		di = kmalloc(sizeof(*di) + digest_size, GFP_NOIO);
		if (!di)
			goto out_free_e;

		di->digest_size = digest_size;
		di->digest = (((char *)di)+sizeof(struct digest_info));

2160 2161 2162
		e->digest = di;
		e->flags |= EE_HAS_DIGEST;

P
Philipp Reisner 已提交
2163 2164 2165
		if (drbd_recv(mdev, di->digest, digest_size) != digest_size)
			goto out_free_e;

2166
		if (cmd == P_CSUM_RS_REQUEST) {
P
Philipp Reisner 已提交
2167 2168
			D_ASSERT(mdev->agreed_pro_version >= 89);
			e->w.cb = w_e_end_csum_rs_req;
2169
		} else if (cmd == P_OV_REPLY) {
P
Philipp Reisner 已提交
2170 2171
			e->w.cb = w_e_end_ov_reply;
			dec_rs_pending(mdev);
2172 2173 2174
			/* drbd_rs_begin_io done when we sent this request,
			 * but accounting still needs to be done. */
			goto submit_for_resync;
P
Philipp Reisner 已提交
2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192
		}
		break;

	case P_OV_REQUEST:
		if (mdev->ov_start_sector == ~(sector_t)0 &&
		    mdev->agreed_pro_version >= 90) {
			mdev->ov_start_sector = sector;
			mdev->ov_position = sector;
			mdev->ov_left = mdev->rs_total - BM_SECT_TO_BIT(sector);
			dev_info(DEV, "Online Verify start sector: %llu\n",
					(unsigned long long)sector);
		}
		e->w.cb = w_e_end_ov_req;
		fault_type = DRBD_FAULT_RS_RD;
		break;

	default:
		dev_err(DEV, "unexpected command (%s) in receive_DataRequest\n",
2193
		    cmdname(cmd));
P
Philipp Reisner 已提交
2194
		fault_type = DRBD_FAULT_MAX;
2195
		goto out_free_e;
P
Philipp Reisner 已提交
2196 2197
	}

2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221
	/* Throttle, drbd_rs_begin_io and submit should become asynchronous
	 * wrt the receiver, but it is not as straightforward as it may seem.
	 * Various places in the resync start and stop logic assume resync
	 * requests are processed in order, requeuing this on the worker thread
	 * introduces a bunch of new code for synchronization between threads.
	 *
	 * Unlimited throttling before drbd_rs_begin_io may stall the resync
	 * "forever", throttling after drbd_rs_begin_io will lock that extent
	 * for application writes for the same time.  For now, just throttle
	 * here, where the rest of the code expects the receiver to sleep for
	 * a while, anyways.
	 */

	/* Throttle before drbd_rs_begin_io, as that locks out application IO;
	 * this defers syncer requests for some time, before letting at least
	 * on request through.  The resync controller on the receiving side
	 * will adapt to the incoming rate accordingly.
	 *
	 * We cannot throttle here if remote is Primary/SyncTarget:
	 * we would also throttle its application reads.
	 * In that case, throttling is done on the SyncTarget only.
	 */
	if (mdev->state.peer != R_PRIMARY && drbd_rs_should_slow_down(mdev))
		msleep(100);
2222 2223
	if (drbd_rs_begin_io(mdev, e->sector))
		goto out_free_e;
P
Philipp Reisner 已提交
2224

2225 2226 2227
submit_for_resync:
	atomic_add(size >> 9, &mdev->rs_sect_ev);

2228
submit:
P
Philipp Reisner 已提交
2229
	inc_unacked(mdev);
2230 2231 2232
	spin_lock_irq(&mdev->req_lock);
	list_add_tail(&e->w.list, &mdev->read_ee);
	spin_unlock_irq(&mdev->req_lock);
P
Philipp Reisner 已提交
2233

2234 2235
	if (drbd_submit_ee(mdev, e, READ, fault_type) == 0)
		return TRUE;
P
Philipp Reisner 已提交
2236

2237 2238 2239 2240 2241 2242 2243 2244
	/* drbd_submit_ee currently fails for one reason only:
	 * not being able to allocate enough bios.
	 * Is dropping the connection going to help? */
	spin_lock_irq(&mdev->req_lock);
	list_del(&e->w.list);
	spin_unlock_irq(&mdev->req_lock);
	/* no drbd_rs_complete_io(), we are dropping the connection anyways */

P
Philipp Reisner 已提交
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
out_free_e:
	put_ldev(mdev);
	drbd_free_ee(mdev, e);
	return FALSE;
}

static int drbd_asb_recover_0p(struct drbd_conf *mdev) __must_hold(local)
{
	int self, peer, rv = -100;
	unsigned long ch_self, ch_peer;

	self = mdev->ldev->md.uuid[UI_BITMAP] & 1;
	peer = mdev->p_uuid[UI_BITMAP] & 1;

	ch_peer = mdev->p_uuid[UI_SIZE];
	ch_self = mdev->comm_bm_set;

	switch (mdev->net_conf->after_sb_0p) {
	case ASB_CONSENSUS:
	case ASB_DISCARD_SECONDARY:
	case ASB_CALL_HELPER:
		dev_err(DEV, "Configuration error.\n");
		break;
	case ASB_DISCONNECT:
		break;
	case ASB_DISCARD_YOUNGER_PRI:
		if (self == 0 && peer == 1) {
			rv = -1;
			break;
		}
		if (self == 1 && peer == 0) {
			rv =  1;
			break;
		}
		/* Else fall through to one of the other strategies... */
	case ASB_DISCARD_OLDER_PRI:
		if (self == 0 && peer == 1) {
			rv = 1;
			break;
		}
		if (self == 1 && peer == 0) {
			rv = -1;
			break;
		}
		/* Else fall through to one of the other strategies... */
L
Lars Ellenberg 已提交
2290
		dev_warn(DEV, "Discard younger/older primary did not find a decision\n"
P
Philipp Reisner 已提交
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 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 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 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 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 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 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 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590
		     "Using discard-least-changes instead\n");
	case ASB_DISCARD_ZERO_CHG:
		if (ch_peer == 0 && ch_self == 0) {
			rv = test_bit(DISCARD_CONCURRENT, &mdev->flags)
				? -1 : 1;
			break;
		} else {
			if (ch_peer == 0) { rv =  1; break; }
			if (ch_self == 0) { rv = -1; break; }
		}
		if (mdev->net_conf->after_sb_0p == ASB_DISCARD_ZERO_CHG)
			break;
	case ASB_DISCARD_LEAST_CHG:
		if	(ch_self < ch_peer)
			rv = -1;
		else if (ch_self > ch_peer)
			rv =  1;
		else /* ( ch_self == ch_peer ) */
		     /* Well, then use something else. */
			rv = test_bit(DISCARD_CONCURRENT, &mdev->flags)
				? -1 : 1;
		break;
	case ASB_DISCARD_LOCAL:
		rv = -1;
		break;
	case ASB_DISCARD_REMOTE:
		rv =  1;
	}

	return rv;
}

static int drbd_asb_recover_1p(struct drbd_conf *mdev) __must_hold(local)
{
	int self, peer, hg, rv = -100;

	self = mdev->ldev->md.uuid[UI_BITMAP] & 1;
	peer = mdev->p_uuid[UI_BITMAP] & 1;

	switch (mdev->net_conf->after_sb_1p) {
	case ASB_DISCARD_YOUNGER_PRI:
	case ASB_DISCARD_OLDER_PRI:
	case ASB_DISCARD_LEAST_CHG:
	case ASB_DISCARD_LOCAL:
	case ASB_DISCARD_REMOTE:
		dev_err(DEV, "Configuration error.\n");
		break;
	case ASB_DISCONNECT:
		break;
	case ASB_CONSENSUS:
		hg = drbd_asb_recover_0p(mdev);
		if (hg == -1 && mdev->state.role == R_SECONDARY)
			rv = hg;
		if (hg == 1  && mdev->state.role == R_PRIMARY)
			rv = hg;
		break;
	case ASB_VIOLENTLY:
		rv = drbd_asb_recover_0p(mdev);
		break;
	case ASB_DISCARD_SECONDARY:
		return mdev->state.role == R_PRIMARY ? 1 : -1;
	case ASB_CALL_HELPER:
		hg = drbd_asb_recover_0p(mdev);
		if (hg == -1 && mdev->state.role == R_PRIMARY) {
			self = drbd_set_role(mdev, R_SECONDARY, 0);
			 /* drbd_change_state() does not sleep while in SS_IN_TRANSIENT_STATE,
			  * we might be here in C_WF_REPORT_PARAMS which is transient.
			  * we do not need to wait for the after state change work either. */
			self = drbd_change_state(mdev, CS_VERBOSE, NS(role, R_SECONDARY));
			if (self != SS_SUCCESS) {
				drbd_khelper(mdev, "pri-lost-after-sb");
			} else {
				dev_warn(DEV, "Successfully gave up primary role.\n");
				rv = hg;
			}
		} else
			rv = hg;
	}

	return rv;
}

static int drbd_asb_recover_2p(struct drbd_conf *mdev) __must_hold(local)
{
	int self, peer, hg, rv = -100;

	self = mdev->ldev->md.uuid[UI_BITMAP] & 1;
	peer = mdev->p_uuid[UI_BITMAP] & 1;

	switch (mdev->net_conf->after_sb_2p) {
	case ASB_DISCARD_YOUNGER_PRI:
	case ASB_DISCARD_OLDER_PRI:
	case ASB_DISCARD_LEAST_CHG:
	case ASB_DISCARD_LOCAL:
	case ASB_DISCARD_REMOTE:
	case ASB_CONSENSUS:
	case ASB_DISCARD_SECONDARY:
		dev_err(DEV, "Configuration error.\n");
		break;
	case ASB_VIOLENTLY:
		rv = drbd_asb_recover_0p(mdev);
		break;
	case ASB_DISCONNECT:
		break;
	case ASB_CALL_HELPER:
		hg = drbd_asb_recover_0p(mdev);
		if (hg == -1) {
			 /* drbd_change_state() does not sleep while in SS_IN_TRANSIENT_STATE,
			  * we might be here in C_WF_REPORT_PARAMS which is transient.
			  * we do not need to wait for the after state change work either. */
			self = drbd_change_state(mdev, CS_VERBOSE, NS(role, R_SECONDARY));
			if (self != SS_SUCCESS) {
				drbd_khelper(mdev, "pri-lost-after-sb");
			} else {
				dev_warn(DEV, "Successfully gave up primary role.\n");
				rv = hg;
			}
		} else
			rv = hg;
	}

	return rv;
}

static void drbd_uuid_dump(struct drbd_conf *mdev, char *text, u64 *uuid,
			   u64 bits, u64 flags)
{
	if (!uuid) {
		dev_info(DEV, "%s uuid info vanished while I was looking!\n", text);
		return;
	}
	dev_info(DEV, "%s %016llX:%016llX:%016llX:%016llX bits:%llu flags:%llX\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],
	     (unsigned long long)bits,
	     (unsigned long long)flags);
}

/*
  100	after split brain try auto recover
    2	C_SYNC_SOURCE set BitMap
    1	C_SYNC_SOURCE use BitMap
    0	no Sync
   -1	C_SYNC_TARGET use BitMap
   -2	C_SYNC_TARGET set BitMap
 -100	after split brain, disconnect
-1000	unrelated data
 */
static int drbd_uuid_compare(struct drbd_conf *mdev, int *rule_nr) __must_hold(local)
{
	u64 self, peer;
	int i, j;

	self = mdev->ldev->md.uuid[UI_CURRENT] & ~((u64)1);
	peer = mdev->p_uuid[UI_CURRENT] & ~((u64)1);

	*rule_nr = 10;
	if (self == UUID_JUST_CREATED && peer == UUID_JUST_CREATED)
		return 0;

	*rule_nr = 20;
	if ((self == UUID_JUST_CREATED || self == (u64)0) &&
	     peer != UUID_JUST_CREATED)
		return -2;

	*rule_nr = 30;
	if (self != UUID_JUST_CREATED &&
	    (peer == UUID_JUST_CREATED || peer == (u64)0))
		return 2;

	if (self == peer) {
		int rct, dc; /* roles at crash time */

		if (mdev->p_uuid[UI_BITMAP] == (u64)0 && mdev->ldev->md.uuid[UI_BITMAP] != (u64)0) {

			if (mdev->agreed_pro_version < 91)
				return -1001;

			if ((mdev->ldev->md.uuid[UI_BITMAP] & ~((u64)1)) == (mdev->p_uuid[UI_HISTORY_START] & ~((u64)1)) &&
			    (mdev->ldev->md.uuid[UI_HISTORY_START] & ~((u64)1)) == (mdev->p_uuid[UI_HISTORY_START + 1] & ~((u64)1))) {
				dev_info(DEV, "was SyncSource, missed the resync finished event, corrected myself:\n");
				drbd_uuid_set_bm(mdev, 0UL);

				drbd_uuid_dump(mdev, "self", mdev->ldev->md.uuid,
					       mdev->state.disk >= D_NEGOTIATING ? drbd_bm_total_weight(mdev) : 0, 0);
				*rule_nr = 34;
			} else {
				dev_info(DEV, "was SyncSource (peer failed to write sync_uuid)\n");
				*rule_nr = 36;
			}

			return 1;
		}

		if (mdev->ldev->md.uuid[UI_BITMAP] == (u64)0 && mdev->p_uuid[UI_BITMAP] != (u64)0) {

			if (mdev->agreed_pro_version < 91)
				return -1001;

			if ((mdev->ldev->md.uuid[UI_HISTORY_START] & ~((u64)1)) == (mdev->p_uuid[UI_BITMAP] & ~((u64)1)) &&
			    (mdev->ldev->md.uuid[UI_HISTORY_START + 1] & ~((u64)1)) == (mdev->p_uuid[UI_HISTORY_START] & ~((u64)1))) {
				dev_info(DEV, "was SyncTarget, peer missed the resync finished event, corrected peer:\n");

				mdev->p_uuid[UI_HISTORY_START + 1] = mdev->p_uuid[UI_HISTORY_START];
				mdev->p_uuid[UI_HISTORY_START] = mdev->p_uuid[UI_BITMAP];
				mdev->p_uuid[UI_BITMAP] = 0UL;

				drbd_uuid_dump(mdev, "peer", mdev->p_uuid, mdev->p_uuid[UI_SIZE], mdev->p_uuid[UI_FLAGS]);
				*rule_nr = 35;
			} else {
				dev_info(DEV, "was SyncTarget (failed to write sync_uuid)\n");
				*rule_nr = 37;
			}

			return -1;
		}

		/* Common power [off|failure] */
		rct = (test_bit(CRASHED_PRIMARY, &mdev->flags) ? 1 : 0) +
			(mdev->p_uuid[UI_FLAGS] & 2);
		/* lowest bit is set when we were primary,
		 * next bit (weight 2) is set when peer was primary */
		*rule_nr = 40;

		switch (rct) {
		case 0: /* !self_pri && !peer_pri */ return 0;
		case 1: /*  self_pri && !peer_pri */ return 1;
		case 2: /* !self_pri &&  peer_pri */ return -1;
		case 3: /*  self_pri &&  peer_pri */
			dc = test_bit(DISCARD_CONCURRENT, &mdev->flags);
			return dc ? -1 : 1;
		}
	}

	*rule_nr = 50;
	peer = mdev->p_uuid[UI_BITMAP] & ~((u64)1);
	if (self == peer)
		return -1;

	*rule_nr = 51;
	peer = mdev->p_uuid[UI_HISTORY_START] & ~((u64)1);
	if (self == peer) {
		self = mdev->ldev->md.uuid[UI_HISTORY_START] & ~((u64)1);
		peer = mdev->p_uuid[UI_HISTORY_START + 1] & ~((u64)1);
		if (self == peer) {
			/* The last P_SYNC_UUID did not get though. Undo the last start of
			   resync as sync source modifications of the peer's UUIDs. */

			if (mdev->agreed_pro_version < 91)
				return -1001;

			mdev->p_uuid[UI_BITMAP] = mdev->p_uuid[UI_HISTORY_START];
			mdev->p_uuid[UI_HISTORY_START] = mdev->p_uuid[UI_HISTORY_START + 1];
			return -1;
		}
	}

	*rule_nr = 60;
	self = mdev->ldev->md.uuid[UI_CURRENT] & ~((u64)1);
	for (i = UI_HISTORY_START; i <= UI_HISTORY_END; i++) {
		peer = mdev->p_uuid[i] & ~((u64)1);
		if (self == peer)
			return -2;
	}

	*rule_nr = 70;
	self = mdev->ldev->md.uuid[UI_BITMAP] & ~((u64)1);
	peer = mdev->p_uuid[UI_CURRENT] & ~((u64)1);
	if (self == peer)
		return 1;

	*rule_nr = 71;
	self = mdev->ldev->md.uuid[UI_HISTORY_START] & ~((u64)1);
	if (self == peer) {
		self = mdev->ldev->md.uuid[UI_HISTORY_START + 1] & ~((u64)1);
		peer = mdev->p_uuid[UI_HISTORY_START] & ~((u64)1);
		if (self == peer) {
			/* The last P_SYNC_UUID did not get though. Undo the last start of
			   resync as sync source modifications of our UUIDs. */

			if (mdev->agreed_pro_version < 91)
				return -1001;

			_drbd_uuid_set(mdev, UI_BITMAP, mdev->ldev->md.uuid[UI_HISTORY_START]);
			_drbd_uuid_set(mdev, UI_HISTORY_START, mdev->ldev->md.uuid[UI_HISTORY_START + 1]);

			dev_info(DEV, "Undid last start of resync:\n");

			drbd_uuid_dump(mdev, "self", mdev->ldev->md.uuid,
				       mdev->state.disk >= D_NEGOTIATING ? drbd_bm_total_weight(mdev) : 0, 0);

			return 1;
		}
	}


	*rule_nr = 80;
2591
	peer = mdev->p_uuid[UI_CURRENT] & ~((u64)1);
P
Philipp Reisner 已提交
2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 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 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658
	for (i = UI_HISTORY_START; i <= UI_HISTORY_END; i++) {
		self = mdev->ldev->md.uuid[i] & ~((u64)1);
		if (self == peer)
			return 2;
	}

	*rule_nr = 90;
	self = mdev->ldev->md.uuid[UI_BITMAP] & ~((u64)1);
	peer = mdev->p_uuid[UI_BITMAP] & ~((u64)1);
	if (self == peer && self != ((u64)0))
		return 100;

	*rule_nr = 100;
	for (i = UI_HISTORY_START; i <= UI_HISTORY_END; i++) {
		self = mdev->ldev->md.uuid[i] & ~((u64)1);
		for (j = UI_HISTORY_START; j <= UI_HISTORY_END; j++) {
			peer = mdev->p_uuid[j] & ~((u64)1);
			if (self == peer)
				return -100;
		}
	}

	return -1000;
}

/* drbd_sync_handshake() returns the new conn state on success, or
   CONN_MASK (-1) on failure.
 */
static enum drbd_conns drbd_sync_handshake(struct drbd_conf *mdev, enum drbd_role peer_role,
					   enum drbd_disk_state peer_disk) __must_hold(local)
{
	int hg, rule_nr;
	enum drbd_conns rv = C_MASK;
	enum drbd_disk_state mydisk;

	mydisk = mdev->state.disk;
	if (mydisk == D_NEGOTIATING)
		mydisk = mdev->new_state_tmp.disk;

	dev_info(DEV, "drbd_sync_handshake:\n");
	drbd_uuid_dump(mdev, "self", mdev->ldev->md.uuid, mdev->comm_bm_set, 0);
	drbd_uuid_dump(mdev, "peer", mdev->p_uuid,
		       mdev->p_uuid[UI_SIZE], mdev->p_uuid[UI_FLAGS]);

	hg = drbd_uuid_compare(mdev, &rule_nr);

	dev_info(DEV, "uuid_compare()=%d by rule %d\n", hg, rule_nr);

	if (hg == -1000) {
		dev_alert(DEV, "Unrelated data, aborting!\n");
		return C_MASK;
	}
	if (hg == -1001) {
		dev_alert(DEV, "To resolve this both sides have to support at least protocol\n");
		return C_MASK;
	}

	if    ((mydisk == D_INCONSISTENT && peer_disk > D_INCONSISTENT) ||
	    (peer_disk == D_INCONSISTENT && mydisk    > D_INCONSISTENT)) {
		int f = (hg == -100) || abs(hg) == 2;
		hg = mydisk > D_INCONSISTENT ? 1 : -1;
		if (f)
			hg = hg*2;
		dev_info(DEV, "Becoming sync %s due to disk states.\n",
		     hg > 0 ? "source" : "target");
	}

2659 2660 2661
	if (abs(hg) == 100)
		drbd_khelper(mdev, "initial-split-brain");

P
Philipp Reisner 已提交
2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 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 2702
	if (hg == 100 || (hg == -100 && mdev->net_conf->always_asbp)) {
		int pcount = (mdev->state.role == R_PRIMARY)
			   + (peer_role == R_PRIMARY);
		int forced = (hg == -100);

		switch (pcount) {
		case 0:
			hg = drbd_asb_recover_0p(mdev);
			break;
		case 1:
			hg = drbd_asb_recover_1p(mdev);
			break;
		case 2:
			hg = drbd_asb_recover_2p(mdev);
			break;
		}
		if (abs(hg) < 100) {
			dev_warn(DEV, "Split-Brain detected, %d primaries, "
			     "automatically solved. Sync from %s node\n",
			     pcount, (hg < 0) ? "peer" : "this");
			if (forced) {
				dev_warn(DEV, "Doing a full sync, since"
				     " UUIDs where ambiguous.\n");
				hg = hg*2;
			}
		}
	}

	if (hg == -100) {
		if (mdev->net_conf->want_lose && !(mdev->p_uuid[UI_FLAGS]&1))
			hg = -1;
		if (!mdev->net_conf->want_lose && (mdev->p_uuid[UI_FLAGS]&1))
			hg = 1;

		if (abs(hg) < 100)
			dev_warn(DEV, "Split-Brain detected, manually solved. "
			     "Sync from %s node\n",
			     (hg < 0) ? "peer" : "this");
	}

	if (hg == -100) {
2703 2704 2705 2706
		/* FIXME this log message is not correct if we end up here
		 * after an attempted attach on a diskless node.
		 * We just refuse to attach -- well, we drop the "connection"
		 * to that disk, in a way... */
2707
		dev_alert(DEV, "Split-Brain detected but unresolved, dropping connection!\n");
P
Philipp Reisner 已提交
2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731
		drbd_khelper(mdev, "split-brain");
		return C_MASK;
	}

	if (hg > 0 && mydisk <= D_INCONSISTENT) {
		dev_err(DEV, "I shall become SyncSource, but I am inconsistent!\n");
		return C_MASK;
	}

	if (hg < 0 && /* by intention we do not use mydisk here. */
	    mdev->state.role == R_PRIMARY && mdev->state.disk >= D_CONSISTENT) {
		switch (mdev->net_conf->rr_conflict) {
		case ASB_CALL_HELPER:
			drbd_khelper(mdev, "pri-lost");
			/* fall through */
		case ASB_DISCONNECT:
			dev_err(DEV, "I shall become SyncTarget, but I am primary!\n");
			return C_MASK;
		case ASB_VIOLENTLY:
			dev_warn(DEV, "Becoming SyncTarget, violating the stable-data"
			     "assumption\n");
		}
	}

2732 2733 2734 2735 2736 2737 2738 2739 2740 2741
	if (mdev->net_conf->dry_run || test_bit(CONN_DRY_RUN, &mdev->flags)) {
		if (hg == 0)
			dev_info(DEV, "dry-run connect: No resync, would become Connected immediately.\n");
		else
			dev_info(DEV, "dry-run connect: Would become %s, doing a %s resync.",
				 drbd_conn_str(hg > 0 ? C_SYNC_SOURCE : C_SYNC_TARGET),
				 abs(hg) >= 2 ? "full" : "bit-map based");
		return C_MASK;
	}

P
Philipp Reisner 已提交
2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783
	if (abs(hg) >= 2) {
		dev_info(DEV, "Writing the whole bitmap, full sync required after drbd_sync_handshake.\n");
		if (drbd_bitmap_io(mdev, &drbd_bmio_set_n_write, "set_n_write from sync_handshake"))
			return C_MASK;
	}

	if (hg > 0) { /* become sync source. */
		rv = C_WF_BITMAP_S;
	} else if (hg < 0) { /* become sync target */
		rv = C_WF_BITMAP_T;
	} else {
		rv = C_CONNECTED;
		if (drbd_bm_total_weight(mdev)) {
			dev_info(DEV, "No resync, but %lu bits in bitmap!\n",
			     drbd_bm_total_weight(mdev));
		}
	}

	return rv;
}

/* returns 1 if invalid */
static int cmp_after_sb(enum drbd_after_sb_p peer, enum drbd_after_sb_p self)
{
	/* ASB_DISCARD_REMOTE - ASB_DISCARD_LOCAL is valid */
	if ((peer == ASB_DISCARD_REMOTE && self == ASB_DISCARD_LOCAL) ||
	    (self == ASB_DISCARD_REMOTE && peer == ASB_DISCARD_LOCAL))
		return 0;

	/* any other things with ASB_DISCARD_REMOTE or ASB_DISCARD_LOCAL are invalid */
	if (peer == ASB_DISCARD_REMOTE || peer == ASB_DISCARD_LOCAL ||
	    self == ASB_DISCARD_REMOTE || self == ASB_DISCARD_LOCAL)
		return 1;

	/* everything else is valid if they are equal on both sides. */
	if (peer == self)
		return 0;

	/* everything es is invalid. */
	return 1;
}

2784
static int receive_protocol(struct drbd_conf *mdev, enum drbd_packets cmd, unsigned int data_size)
P
Philipp Reisner 已提交
2785
{
2786
	struct p_protocol *p = &mdev->data.rbuf.protocol;
P
Philipp Reisner 已提交
2787
	int p_proto, p_after_sb_0p, p_after_sb_1p, p_after_sb_2p;
2788
	int p_want_lose, p_two_primaries, cf;
P
Philipp Reisner 已提交
2789 2790 2791 2792 2793 2794 2795
	char p_integrity_alg[SHARED_SECRET_MAX] = "";

	p_proto		= be32_to_cpu(p->protocol);
	p_after_sb_0p	= be32_to_cpu(p->after_sb_0p);
	p_after_sb_1p	= be32_to_cpu(p->after_sb_1p);
	p_after_sb_2p	= be32_to_cpu(p->after_sb_2p);
	p_two_primaries = be32_to_cpu(p->two_primaries);
2796 2797 2798 2799 2800 2801 2802
	cf		= be32_to_cpu(p->conn_flags);
	p_want_lose = cf & CF_WANT_LOSE;

	clear_bit(CONN_DRY_RUN, &mdev->flags);

	if (cf & CF_DRY_RUN)
		set_bit(CONN_DRY_RUN, &mdev->flags);
P
Philipp Reisner 已提交
2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882

	if (p_proto != mdev->net_conf->wire_protocol) {
		dev_err(DEV, "incompatible communication protocols\n");
		goto disconnect;
	}

	if (cmp_after_sb(p_after_sb_0p, mdev->net_conf->after_sb_0p)) {
		dev_err(DEV, "incompatible after-sb-0pri settings\n");
		goto disconnect;
	}

	if (cmp_after_sb(p_after_sb_1p, mdev->net_conf->after_sb_1p)) {
		dev_err(DEV, "incompatible after-sb-1pri settings\n");
		goto disconnect;
	}

	if (cmp_after_sb(p_after_sb_2p, mdev->net_conf->after_sb_2p)) {
		dev_err(DEV, "incompatible after-sb-2pri settings\n");
		goto disconnect;
	}

	if (p_want_lose && mdev->net_conf->want_lose) {
		dev_err(DEV, "both sides have the 'want_lose' flag set\n");
		goto disconnect;
	}

	if (p_two_primaries != mdev->net_conf->two_primaries) {
		dev_err(DEV, "incompatible setting of the two-primaries options\n");
		goto disconnect;
	}

	if (mdev->agreed_pro_version >= 87) {
		unsigned char *my_alg = mdev->net_conf->integrity_alg;

		if (drbd_recv(mdev, p_integrity_alg, data_size) != data_size)
			return FALSE;

		p_integrity_alg[SHARED_SECRET_MAX-1] = 0;
		if (strcmp(p_integrity_alg, my_alg)) {
			dev_err(DEV, "incompatible setting of the data-integrity-alg\n");
			goto disconnect;
		}
		dev_info(DEV, "data-integrity-alg: %s\n",
		     my_alg[0] ? my_alg : (unsigned char *)"<not-used>");
	}

	return TRUE;

disconnect:
	drbd_force_state(mdev, NS(conn, C_DISCONNECTING));
	return FALSE;
}

/* helper function
 * input: alg name, feature name
 * return: NULL (alg name was "")
 *         ERR_PTR(error) if something goes wrong
 *         or the crypto hash ptr, if it worked out ok. */
struct crypto_hash *drbd_crypto_alloc_digest_safe(const struct drbd_conf *mdev,
		const char *alg, const char *name)
{
	struct crypto_hash *tfm;

	if (!alg[0])
		return NULL;

	tfm = crypto_alloc_hash(alg, 0, CRYPTO_ALG_ASYNC);
	if (IS_ERR(tfm)) {
		dev_err(DEV, "Can not allocate \"%s\" as %s (reason: %ld)\n",
			alg, name, PTR_ERR(tfm));
		return tfm;
	}
	if (!drbd_crypto_is_hash(crypto_hash_tfm(tfm))) {
		crypto_free_hash(tfm);
		dev_err(DEV, "\"%s\" is not a digest (%s)\n", alg, name);
		return ERR_PTR(-EINVAL);
	}
	return tfm;
}

2883
static int receive_SyncParam(struct drbd_conf *mdev, enum drbd_packets cmd, unsigned int packet_size)
P
Philipp Reisner 已提交
2884 2885
{
	int ok = TRUE;
2886
	struct p_rs_param_95 *p = &mdev->data.rbuf.rs_param_95;
P
Philipp Reisner 已提交
2887 2888 2889 2890
	unsigned int header_size, data_size, exp_max_sz;
	struct crypto_hash *verify_tfm = NULL;
	struct crypto_hash *csums_tfm = NULL;
	const int apv = mdev->agreed_pro_version;
2891 2892
	int *rs_plan_s = NULL;
	int fifo_size = 0;
P
Philipp Reisner 已提交
2893 2894 2895 2896

	exp_max_sz  = apv <= 87 ? sizeof(struct p_rs_param)
		    : apv == 88 ? sizeof(struct p_rs_param)
					+ SHARED_SECRET_MAX
2897 2898
		    : apv <= 94 ? sizeof(struct p_rs_param_89)
		    : /* apv >= 95 */ sizeof(struct p_rs_param_95);
P
Philipp Reisner 已提交
2899

2900
	if (packet_size > exp_max_sz) {
P
Philipp Reisner 已提交
2901
		dev_err(DEV, "SyncParam packet too long: received %u, expected <= %u bytes\n",
2902
		    packet_size, exp_max_sz);
P
Philipp Reisner 已提交
2903 2904 2905 2906
		return FALSE;
	}

	if (apv <= 88) {
2907 2908
		header_size = sizeof(struct p_rs_param) - sizeof(struct p_header80);
		data_size   = packet_size  - header_size;
2909
	} else if (apv <= 94) {
2910 2911
		header_size = sizeof(struct p_rs_param_89) - sizeof(struct p_header80);
		data_size   = packet_size  - header_size;
P
Philipp Reisner 已提交
2912
		D_ASSERT(data_size == 0);
2913
	} else {
2914 2915
		header_size = sizeof(struct p_rs_param_95) - sizeof(struct p_header80);
		data_size   = packet_size  - header_size;
2916
		D_ASSERT(data_size == 0);
P
Philipp Reisner 已提交
2917 2918 2919 2920 2921
	}

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

2922
	if (drbd_recv(mdev, &p->head.payload, header_size) != header_size)
P
Philipp Reisner 已提交
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
		return FALSE;

	mdev->sync_conf.rate	  = be32_to_cpu(p->rate);

	if (apv >= 88) {
		if (apv == 88) {
			if (data_size > SHARED_SECRET_MAX) {
				dev_err(DEV, "verify-alg too long, "
				    "peer wants %u, accepting only %u byte\n",
						data_size, SHARED_SECRET_MAX);
				return FALSE;
			}

			if (drbd_recv(mdev, p->verify_alg, data_size) != data_size)
				return FALSE;

			/* we expect NUL terminated string */
			/* but just in case someone tries to be evil */
			D_ASSERT(p->verify_alg[data_size-1] == 0);
			p->verify_alg[data_size-1] = 0;

		} else /* apv >= 89 */ {
			/* we still expect NUL terminated strings */
			/* but just in case someone tries to be evil */
			D_ASSERT(p->verify_alg[SHARED_SECRET_MAX-1] == 0);
			D_ASSERT(p->csums_alg[SHARED_SECRET_MAX-1] == 0);
			p->verify_alg[SHARED_SECRET_MAX-1] = 0;
			p->csums_alg[SHARED_SECRET_MAX-1] = 0;
		}

		if (strcmp(mdev->sync_conf.verify_alg, p->verify_alg)) {
			if (mdev->state.conn == C_WF_REPORT_PARAMS) {
				dev_err(DEV, "Different verify-alg settings. me=\"%s\" peer=\"%s\"\n",
				    mdev->sync_conf.verify_alg, p->verify_alg);
				goto disconnect;
			}
			verify_tfm = drbd_crypto_alloc_digest_safe(mdev,
					p->verify_alg, "verify-alg");
			if (IS_ERR(verify_tfm)) {
				verify_tfm = NULL;
				goto disconnect;
			}
		}

		if (apv >= 89 && strcmp(mdev->sync_conf.csums_alg, p->csums_alg)) {
			if (mdev->state.conn == C_WF_REPORT_PARAMS) {
				dev_err(DEV, "Different csums-alg settings. me=\"%s\" peer=\"%s\"\n",
				    mdev->sync_conf.csums_alg, p->csums_alg);
				goto disconnect;
			}
			csums_tfm = drbd_crypto_alloc_digest_safe(mdev,
					p->csums_alg, "csums-alg");
			if (IS_ERR(csums_tfm)) {
				csums_tfm = NULL;
				goto disconnect;
			}
		}

2981 2982 2983 2984 2985 2986
		if (apv > 94) {
			mdev->sync_conf.rate	  = be32_to_cpu(p->rate);
			mdev->sync_conf.c_plan_ahead = be32_to_cpu(p->c_plan_ahead);
			mdev->sync_conf.c_delay_target = be32_to_cpu(p->c_delay_target);
			mdev->sync_conf.c_fill_target = be32_to_cpu(p->c_fill_target);
			mdev->sync_conf.c_max_rate = be32_to_cpu(p->c_max_rate);
2987 2988 2989 2990 2991 2992 2993 2994 2995

			fifo_size = (mdev->sync_conf.c_plan_ahead * 10 * SLEEP_TIME) / HZ;
			if (fifo_size != mdev->rs_plan_s.size && fifo_size > 0) {
				rs_plan_s   = kzalloc(sizeof(int) * fifo_size, GFP_KERNEL);
				if (!rs_plan_s) {
					dev_err(DEV, "kmalloc of fifo_buffer failed");
					goto disconnect;
				}
			}
2996
		}
P
Philipp Reisner 已提交
2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013

		spin_lock(&mdev->peer_seq_lock);
		/* lock against drbd_nl_syncer_conf() */
		if (verify_tfm) {
			strcpy(mdev->sync_conf.verify_alg, p->verify_alg);
			mdev->sync_conf.verify_alg_len = strlen(p->verify_alg) + 1;
			crypto_free_hash(mdev->verify_tfm);
			mdev->verify_tfm = verify_tfm;
			dev_info(DEV, "using verify-alg: \"%s\"\n", p->verify_alg);
		}
		if (csums_tfm) {
			strcpy(mdev->sync_conf.csums_alg, p->csums_alg);
			mdev->sync_conf.csums_alg_len = strlen(p->csums_alg) + 1;
			crypto_free_hash(mdev->csums_tfm);
			mdev->csums_tfm = csums_tfm;
			dev_info(DEV, "using csums-alg: \"%s\"\n", p->csums_alg);
		}
3014 3015 3016 3017 3018 3019
		if (fifo_size != mdev->rs_plan_s.size) {
			kfree(mdev->rs_plan_s.values);
			mdev->rs_plan_s.values = rs_plan_s;
			mdev->rs_plan_s.size   = fifo_size;
			mdev->rs_planed = 0;
		}
P
Philipp Reisner 已提交
3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052
		spin_unlock(&mdev->peer_seq_lock);
	}

	return ok;
disconnect:
	/* just for completeness: actually not needed,
	 * as this is not reached if csums_tfm was ok. */
	crypto_free_hash(csums_tfm);
	/* but free the verify_tfm again, if csums_tfm did not work out */
	crypto_free_hash(verify_tfm);
	drbd_force_state(mdev, NS(conn, C_DISCONNECTING));
	return FALSE;
}

static void drbd_setup_order_type(struct drbd_conf *mdev, int peer)
{
	/* sorry, we currently have no working implementation
	 * of distributed TCQ */
}

/* warn if the arguments differ by more than 12.5% */
static void warn_if_differ_considerably(struct drbd_conf *mdev,
	const char *s, sector_t a, sector_t b)
{
	sector_t d;
	if (a == 0 || b == 0)
		return;
	d = (a > b) ? (a - b) : (b - a);
	if (d > (a>>3) || d > (b>>3))
		dev_warn(DEV, "Considerable difference in %s: %llus vs. %llus\n", s,
		     (unsigned long long)a, (unsigned long long)b);
}

3053
static int receive_sizes(struct drbd_conf *mdev, enum drbd_packets cmd, unsigned int data_size)
P
Philipp Reisner 已提交
3054
{
3055
	struct p_sizes *p = &mdev->data.rbuf.sizes;
P
Philipp Reisner 已提交
3056 3057 3058 3059
	enum determine_dev_size dd = unchanged;
	unsigned int max_seg_s;
	sector_t p_size, p_usize, my_usize;
	int ldsc = 0; /* local disk size changed */
3060
	enum dds_flags ddsf;
P
Philipp Reisner 已提交
3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097

	p_size = be64_to_cpu(p->d_size);
	p_usize = be64_to_cpu(p->u_size);

	if (p_size == 0 && mdev->state.disk == D_DISKLESS) {
		dev_err(DEV, "some backing storage is needed\n");
		drbd_force_state(mdev, NS(conn, C_DISCONNECTING));
		return FALSE;
	}

	/* just store the peer's disk size for now.
	 * we still need to figure out whether we accept that. */
	mdev->p_size = p_size;

#define min_not_zero(l, r) (l == 0) ? r : ((r == 0) ? l : min(l, r))
	if (get_ldev(mdev)) {
		warn_if_differ_considerably(mdev, "lower level device sizes",
			   p_size, drbd_get_max_capacity(mdev->ldev));
		warn_if_differ_considerably(mdev, "user requested size",
					    p_usize, mdev->ldev->dc.disk_size);

		/* if this is the first connect, or an otherwise expected
		 * param exchange, choose the minimum */
		if (mdev->state.conn == C_WF_REPORT_PARAMS)
			p_usize = min_not_zero((sector_t)mdev->ldev->dc.disk_size,
					     p_usize);

		my_usize = mdev->ldev->dc.disk_size;

		if (mdev->ldev->dc.disk_size != p_usize) {
			mdev->ldev->dc.disk_size = p_usize;
			dev_info(DEV, "Peer sets u_size to %lu sectors\n",
			     (unsigned long)mdev->ldev->dc.disk_size);
		}

		/* Never shrink a device with usable data during connect.
		   But allow online shrinking if we are connected. */
3098
		if (drbd_new_dev_size(mdev, mdev->ldev, 0) <
P
Philipp Reisner 已提交
3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111
		   drbd_get_capacity(mdev->this_bdev) &&
		   mdev->state.disk >= D_OUTDATED &&
		   mdev->state.conn < C_CONNECTED) {
			dev_err(DEV, "The peer's disk size is too small!\n");
			drbd_force_state(mdev, NS(conn, C_DISCONNECTING));
			mdev->ldev->dc.disk_size = my_usize;
			put_ldev(mdev);
			return FALSE;
		}
		put_ldev(mdev);
	}
#undef min_not_zero

3112
	ddsf = be16_to_cpu(p->dds_flags);
P
Philipp Reisner 已提交
3113
	if (get_ldev(mdev)) {
3114
		dd = drbd_determin_dev_size(mdev, ddsf);
P
Philipp Reisner 已提交
3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129
		put_ldev(mdev);
		if (dd == dev_size_error)
			return FALSE;
		drbd_md_sync(mdev);
	} else {
		/* I am diskless, need to accept the peer's size. */
		drbd_set_my_capacity(mdev, p_size);
	}

	if (get_ldev(mdev)) {
		if (mdev->ldev->known_size != drbd_get_capacity(mdev->ldev->backing_bdev)) {
			mdev->ldev->known_size = drbd_get_capacity(mdev->ldev->backing_bdev);
			ldsc = 1;
		}

3130 3131
		if (mdev->agreed_pro_version < 94)
			max_seg_s = be32_to_cpu(p->max_segment_size);
3132 3133
		else if (mdev->agreed_pro_version == 94)
			max_seg_s = DRBD_MAX_SIZE_H80_PACKET;
3134 3135 3136
		else /* drbd 8.3.8 onwards */
			max_seg_s = DRBD_MAX_SEGMENT_SIZE;

P
Philipp Reisner 已提交
3137 3138 3139
		if (max_seg_s != queue_max_segment_size(mdev->rq_queue))
			drbd_setup_queue_param(mdev, max_seg_s);

3140
		drbd_setup_order_type(mdev, be16_to_cpu(p->queue_order_type));
P
Philipp Reisner 已提交
3141 3142 3143 3144 3145 3146 3147 3148
		put_ldev(mdev);
	}

	if (mdev->state.conn > C_WF_REPORT_PARAMS) {
		if (be64_to_cpu(p->c_size) !=
		    drbd_get_capacity(mdev->this_bdev) || ldsc) {
			/* we have different sizes, probably peer
			 * needs to know my new size... */
3149
			drbd_send_sizes(mdev, 0, ddsf);
P
Philipp Reisner 已提交
3150 3151 3152 3153
		}
		if (test_and_clear_bit(RESIZE_PENDING, &mdev->flags) ||
		    (dd == grew && mdev->state.conn == C_CONNECTED)) {
			if (mdev->state.pdsk >= D_INCONSISTENT &&
3154 3155 3156 3157 3158 3159
			    mdev->state.disk >= D_INCONSISTENT) {
				if (ddsf & DDSF_NO_RESYNC)
					dev_info(DEV, "Resync of new storage suppressed with --assume-clean\n");
				else
					resync_after_online_grow(mdev);
			} else
P
Philipp Reisner 已提交
3160 3161 3162 3163 3164 3165 3166
				set_bit(RESYNC_AFTER_NEG, &mdev->flags);
		}
	}

	return TRUE;
}

3167
static int receive_uuids(struct drbd_conf *mdev, enum drbd_packets cmd, unsigned int data_size)
P
Philipp Reisner 已提交
3168
{
3169
	struct p_uuids *p = &mdev->data.rbuf.uuids;
P
Philipp Reisner 已提交
3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207
	u64 *p_uuid;
	int i;

	p_uuid = kmalloc(sizeof(u64)*UI_EXTENDED_SIZE, GFP_NOIO);

	for (i = UI_CURRENT; i < UI_EXTENDED_SIZE; i++)
		p_uuid[i] = be64_to_cpu(p->uuid[i]);

	kfree(mdev->p_uuid);
	mdev->p_uuid = p_uuid;

	if (mdev->state.conn < C_CONNECTED &&
	    mdev->state.disk < D_INCONSISTENT &&
	    mdev->state.role == R_PRIMARY &&
	    (mdev->ed_uuid & ~((u64)1)) != (p_uuid[UI_CURRENT] & ~((u64)1))) {
		dev_err(DEV, "Can only connect to data with current UUID=%016llX\n",
		    (unsigned long long)mdev->ed_uuid);
		drbd_force_state(mdev, NS(conn, C_DISCONNECTING));
		return FALSE;
	}

	if (get_ldev(mdev)) {
		int skip_initial_sync =
			mdev->state.conn == C_CONNECTED &&
			mdev->agreed_pro_version >= 90 &&
			mdev->ldev->md.uuid[UI_CURRENT] == UUID_JUST_CREATED &&
			(p_uuid[UI_FLAGS] & 8);
		if (skip_initial_sync) {
			dev_info(DEV, "Accepted new current UUID, preparing to skip initial sync\n");
			drbd_bitmap_io(mdev, &drbd_bmio_clear_n_write,
					"clear_n_write from receive_uuids");
			_drbd_uuid_set(mdev, UI_CURRENT, p_uuid[UI_CURRENT]);
			_drbd_uuid_set(mdev, UI_BITMAP, 0);
			_drbd_set_state(_NS2(mdev, disk, D_UP_TO_DATE, pdsk, D_UP_TO_DATE),
					CS_VERBOSE, NULL);
			drbd_md_sync(mdev);
		}
		put_ldev(mdev);
3208 3209 3210 3211 3212
	} else if (mdev->state.disk < D_INCONSISTENT &&
		   mdev->state.role == R_PRIMARY) {
		/* I am a diskless primary, the peer just created a new current UUID
		   for me. */
		drbd_set_ed_uuid(mdev, p_uuid[UI_CURRENT]);
P
Philipp Reisner 已提交
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 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255
	}

	/* Before we test for the disk state, we should wait until an eventually
	   ongoing cluster wide state change is finished. That is important if
	   we are primary and are detaching from our disk. We need to see the
	   new disk state... */
	wait_event(mdev->misc_wait, !test_bit(CLUSTER_ST_CHANGE, &mdev->flags));
	if (mdev->state.conn >= C_CONNECTED && mdev->state.disk < D_INCONSISTENT)
		drbd_set_ed_uuid(mdev, p_uuid[UI_CURRENT]);

	return TRUE;
}

/**
 * convert_state() - Converts the peer's view of the cluster state to our point of view
 * @ps:		The state as seen by the peer.
 */
static union drbd_state convert_state(union drbd_state ps)
{
	union drbd_state ms;

	static enum drbd_conns c_tab[] = {
		[C_CONNECTED] = C_CONNECTED,

		[C_STARTING_SYNC_S] = C_STARTING_SYNC_T,
		[C_STARTING_SYNC_T] = C_STARTING_SYNC_S,
		[C_DISCONNECTING] = C_TEAR_DOWN, /* C_NETWORK_FAILURE, */
		[C_VERIFY_S]       = C_VERIFY_T,
		[C_MASK]   = C_MASK,
	};

	ms.i = ps.i;

	ms.conn = c_tab[ps.conn];
	ms.peer = ps.role;
	ms.role = ps.peer;
	ms.pdsk = ps.disk;
	ms.disk = ps.pdsk;
	ms.peer_isp = (ps.aftr_isp | ps.user_isp);

	return ms;
}

3256
static int receive_req_state(struct drbd_conf *mdev, enum drbd_packets cmd, unsigned int data_size)
P
Philipp Reisner 已提交
3257
{
3258
	struct p_req_state *p = &mdev->data.rbuf.req_state;
P
Philipp Reisner 已提交
3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281
	union drbd_state mask, val;
	int rv;

	mask.i = be32_to_cpu(p->mask);
	val.i = be32_to_cpu(p->val);

	if (test_bit(DISCARD_CONCURRENT, &mdev->flags) &&
	    test_bit(CLUSTER_ST_CHANGE, &mdev->flags)) {
		drbd_send_sr_reply(mdev, SS_CONCURRENT_ST_CHG);
		return TRUE;
	}

	mask = convert_state(mask);
	val = convert_state(val);

	rv = drbd_change_state(mdev, CS_VERBOSE, mask, val);

	drbd_send_sr_reply(mdev, rv);
	drbd_md_sync(mdev);

	return TRUE;
}

3282
static int receive_state(struct drbd_conf *mdev, enum drbd_packets cmd, unsigned int data_size)
P
Philipp Reisner 已提交
3283
{
3284
	struct p_state *p = &mdev->data.rbuf.state;
3285
	union drbd_state os, ns, peer_state;
P
Philipp Reisner 已提交
3286
	enum drbd_disk_state real_peer_disk;
3287
	enum chg_state_flags cs_flags;
P
Philipp Reisner 已提交
3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299
	int rv;

	peer_state.i = be32_to_cpu(p->state);

	real_peer_disk = peer_state.disk;
	if (peer_state.disk == D_NEGOTIATING) {
		real_peer_disk = mdev->p_uuid[UI_FLAGS] & 4 ? D_INCONSISTENT : D_CONSISTENT;
		dev_info(DEV, "real peer disk state = %s\n", drbd_disk_str(real_peer_disk));
	}

	spin_lock_irq(&mdev->req_lock);
 retry:
3300
	os = ns = mdev->state;
P
Philipp Reisner 已提交
3301 3302
	spin_unlock_irq(&mdev->req_lock);

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
	/* peer says his disk is uptodate, while we think it is inconsistent,
	 * and this happens while we think we have a sync going on. */
	if (os.pdsk == D_INCONSISTENT && real_peer_disk == D_UP_TO_DATE &&
	    os.conn > C_CONNECTED && os.disk == D_UP_TO_DATE) {
		/* If we are (becoming) SyncSource, but peer is still in sync
		 * preparation, ignore its uptodate-ness to avoid flapping, it
		 * will change to inconsistent once the peer reaches active
		 * syncing states.
		 * It may have changed syncer-paused flags, however, so we
		 * cannot ignore this completely. */
		if (peer_state.conn > C_CONNECTED &&
		    peer_state.conn < C_SYNC_SOURCE)
			real_peer_disk = D_INCONSISTENT;

		/* if peer_state changes to connected at the same time,
		 * it explicitly notifies us that it finished resync.
		 * Maybe we should finish it up, too? */
		else if (os.conn >= C_SYNC_SOURCE &&
			 peer_state.conn == C_CONNECTED) {
			if (drbd_bm_total_weight(mdev) <= mdev->rs_failed)
				drbd_resync_finished(mdev);
			return TRUE;
		}
	}

	/* peer says his disk is inconsistent, while we think it is uptodate,
	 * and this happens while the peer still thinks we have a sync going on,
	 * but we think we are already done with the sync.
	 * We ignore this to avoid flapping pdsk.
	 * This should not happen, if the peer is a recent version of drbd. */
	if (os.pdsk == D_UP_TO_DATE && real_peer_disk == D_INCONSISTENT &&
	    os.conn == C_CONNECTED && peer_state.conn > C_SYNC_SOURCE)
		real_peer_disk = D_UP_TO_DATE;

3337 3338
	if (ns.conn == C_WF_REPORT_PARAMS)
		ns.conn = C_CONNECTED;
P
Philipp Reisner 已提交
3339 3340 3341 3342 3343 3344

	if (mdev->p_uuid && peer_state.disk >= D_NEGOTIATING &&
	    get_ldev_if_state(mdev, D_NEGOTIATING)) {
		int cr; /* consider resync */

		/* if we established a new connection */
3345
		cr  = (os.conn < C_CONNECTED);
P
Philipp Reisner 已提交
3346 3347
		/* if we had an established connection
		 * and one of the nodes newly attaches a disk */
3348
		cr |= (os.conn == C_CONNECTED &&
P
Philipp Reisner 已提交
3349
		       (peer_state.disk == D_NEGOTIATING ||
3350
			os.disk == D_NEGOTIATING));
P
Philipp Reisner 已提交
3351 3352 3353 3354 3355
		/* if we have both been inconsistent, and the peer has been
		 * forced to be UpToDate with --overwrite-data */
		cr |= test_bit(CONSIDER_RESYNC, &mdev->flags);
		/* if we had been plain connected, and the admin requested to
		 * start a sync by "invalidate" or "invalidate-remote" */
3356
		cr |= (os.conn == C_CONNECTED &&
P
Philipp Reisner 已提交
3357 3358 3359 3360
				(peer_state.conn >= C_STARTING_SYNC_S &&
				 peer_state.conn <= C_WF_BITMAP_T));

		if (cr)
3361
			ns.conn = drbd_sync_handshake(mdev, peer_state.role, real_peer_disk);
P
Philipp Reisner 已提交
3362 3363

		put_ldev(mdev);
3364 3365
		if (ns.conn == C_MASK) {
			ns.conn = C_CONNECTED;
P
Philipp Reisner 已提交
3366
			if (mdev->state.disk == D_NEGOTIATING) {
3367
				drbd_force_state(mdev, NS(disk, D_FAILED));
P
Philipp Reisner 已提交
3368 3369 3370
			} else if (peer_state.disk == D_NEGOTIATING) {
				dev_err(DEV, "Disk attach process on the peer node was aborted.\n");
				peer_state.disk = D_DISKLESS;
3371
				real_peer_disk = D_DISKLESS;
P
Philipp Reisner 已提交
3372
			} else {
3373 3374
				if (test_and_clear_bit(CONN_DRY_RUN, &mdev->flags))
					return FALSE;
3375
				D_ASSERT(os.conn == C_WF_REPORT_PARAMS);
P
Philipp Reisner 已提交
3376 3377 3378 3379 3380 3381 3382
				drbd_force_state(mdev, NS(conn, C_DISCONNECTING));
				return FALSE;
			}
		}
	}

	spin_lock_irq(&mdev->req_lock);
3383
	if (mdev->state.i != os.i)
P
Philipp Reisner 已提交
3384 3385 3386 3387 3388
		goto retry;
	clear_bit(CONSIDER_RESYNC, &mdev->flags);
	ns.peer = peer_state.role;
	ns.pdsk = real_peer_disk;
	ns.peer_isp = (peer_state.aftr_isp | peer_state.user_isp);
3389
	if ((ns.conn == C_CONNECTED || ns.conn == C_WF_BITMAP_S) && ns.disk == D_NEGOTIATING)
P
Philipp Reisner 已提交
3390
		ns.disk = mdev->new_state_tmp.disk;
3391 3392
	cs_flags = CS_VERBOSE + (os.conn < C_CONNECTED && ns.conn >= C_CONNECTED ? 0 : CS_HARD);
	if (ns.pdsk == D_CONSISTENT && is_susp(ns) && ns.conn == C_CONNECTED && os.conn < C_CONNECTED &&
3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403
	    test_bit(NEW_CUR_UUID, &mdev->flags)) {
		/* Do not allow tl_restart(resend) for a rebooted peer. We can only allow this
		   for temporal network outages! */
		spin_unlock_irq(&mdev->req_lock);
		dev_err(DEV, "Aborting Connect, can not thaw IO with an only Consistent peer\n");
		tl_clear(mdev);
		drbd_uuid_new_current(mdev);
		clear_bit(NEW_CUR_UUID, &mdev->flags);
		drbd_force_state(mdev, NS2(conn, C_PROTOCOL_ERROR, susp, 0));
		return FALSE;
	}
3404
	rv = _drbd_set_state(mdev, ns, cs_flags, NULL);
P
Philipp Reisner 已提交
3405 3406 3407 3408 3409 3410 3411 3412
	ns = mdev->state;
	spin_unlock_irq(&mdev->req_lock);

	if (rv < SS_SUCCESS) {
		drbd_force_state(mdev, NS(conn, C_DISCONNECTING));
		return FALSE;
	}

3413 3414
	if (os.conn > C_WF_REPORT_PARAMS) {
		if (ns.conn > C_CONNECTED && peer_state.conn <= C_CONNECTED &&
P
Philipp Reisner 已提交
3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430
		    peer_state.disk != D_NEGOTIATING ) {
			/* we want resync, peer has not yet decided to sync... */
			/* Nowadays only used when forcing a node into primary role and
			   setting its disk to UpToDate with that */
			drbd_send_uuids(mdev);
			drbd_send_state(mdev);
		}
	}

	mdev->net_conf->want_lose = 0;

	drbd_md_sync(mdev); /* update connected indicator, la_size, ... */

	return TRUE;
}

3431
static int receive_sync_uuid(struct drbd_conf *mdev, enum drbd_packets cmd, unsigned int data_size)
P
Philipp Reisner 已提交
3432
{
3433
	struct p_rs_uuid *p = &mdev->data.rbuf.rs_uuid;
P
Philipp Reisner 已提交
3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459

	wait_event(mdev->misc_wait,
		   mdev->state.conn == C_WF_SYNC_UUID ||
		   mdev->state.conn < C_CONNECTED ||
		   mdev->state.disk < D_NEGOTIATING);

	/* D_ASSERT( mdev->state.conn == C_WF_SYNC_UUID ); */

	/* Here the _drbd_uuid_ functions are right, current should
	   _not_ be rotated into the history */
	if (get_ldev_if_state(mdev, D_NEGOTIATING)) {
		_drbd_uuid_set(mdev, UI_CURRENT, be64_to_cpu(p->uuid));
		_drbd_uuid_set(mdev, UI_BITMAP, 0UL);

		drbd_start_resync(mdev, C_SYNC_TARGET);

		put_ldev(mdev);
	} else
		dev_err(DEV, "Ignoring SyncUUID packet!\n");

	return TRUE;
}

enum receive_bitmap_ret { OK, DONE, FAILED };

static enum receive_bitmap_ret
3460 3461
receive_bitmap_plain(struct drbd_conf *mdev, unsigned int data_size,
		     unsigned long *buffer, struct bm_xfer_ctx *c)
P
Philipp Reisner 已提交
3462 3463 3464 3465
{
	unsigned num_words = min_t(size_t, BM_PACKET_WORDS, c->bm_words - c->word_offset);
	unsigned want = num_words * sizeof(long);

3466 3467
	if (want != data_size) {
		dev_err(DEV, "%s:want (%u) != data_size (%u)\n", __func__, want, data_size);
P
Philipp Reisner 已提交
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
		return FAILED;
	}
	if (want == 0)
		return DONE;
	if (drbd_recv(mdev, buffer, want) != want)
		return FAILED;

	drbd_bm_merge_lel(mdev, c->word_offset, num_words, buffer);

	c->word_offset += num_words;
	c->bit_offset = c->word_offset * BITS_PER_LONG;
	if (c->bit_offset > c->bm_bits)
		c->bit_offset = c->bm_bits;

	return OK;
}

static enum receive_bitmap_ret
recv_bm_rle_bits(struct drbd_conf *mdev,
		struct p_compressed_bm *p,
		struct bm_xfer_ctx *c)
{
	struct bitstream bs;
	u64 look_ahead;
	u64 rl;
	u64 tmp;
	unsigned long s = c->bit_offset;
	unsigned long e;
3496
	int len = be16_to_cpu(p->head.length) - (sizeof(*p) - sizeof(p->head));
P
Philipp Reisner 已提交
3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 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
	int toggle = DCBP_get_start(p);
	int have;
	int bits;

	bitstream_init(&bs, p->code, len, DCBP_get_pad_bits(p));

	bits = bitstream_get_bits(&bs, &look_ahead, 64);
	if (bits < 0)
		return FAILED;

	for (have = bits; have > 0; s += rl, toggle = !toggle) {
		bits = vli_decode_bits(&rl, look_ahead);
		if (bits <= 0)
			return FAILED;

		if (toggle) {
			e = s + rl -1;
			if (e >= c->bm_bits) {
				dev_err(DEV, "bitmap overflow (e:%lu) while decoding bm RLE packet\n", e);
				return FAILED;
			}
			_drbd_bm_set_bits(mdev, s, e);
		}

		if (have < bits) {
			dev_err(DEV, "bitmap decoding error: h:%d b:%d la:0x%08llx l:%u/%u\n",
				have, bits, look_ahead,
				(unsigned int)(bs.cur.b - p->code),
				(unsigned int)bs.buf_len);
			return FAILED;
		}
		look_ahead >>= bits;
		have -= bits;

		bits = bitstream_get_bits(&bs, &tmp, 64 - have);
		if (bits < 0)
			return FAILED;
		look_ahead |= tmp << have;
		have += bits;
	}

	c->bit_offset = s;
	bm_xfer_ctx_bit_to_word_offset(c);

	return (s == c->bm_bits) ? DONE : OK;
}

static enum receive_bitmap_ret
decode_bitmap_c(struct drbd_conf *mdev,
		struct p_compressed_bm *p,
		struct bm_xfer_ctx *c)
{
	if (DCBP_get_code(p) == RLE_VLI_Bits)
		return recv_bm_rle_bits(mdev, p, c);

	/* other variants had been implemented for evaluation,
	 * but have been dropped as this one turned out to be "best"
	 * during all our tests. */

	dev_err(DEV, "receive_bitmap_c: unknown encoding %u\n", p->encoding);
	drbd_force_state(mdev, NS(conn, C_PROTOCOL_ERROR));
	return FAILED;
}

void INFO_bm_xfer_stats(struct drbd_conf *mdev,
		const char *direction, struct bm_xfer_ctx *c)
{
	/* what would it take to transfer it "plaintext" */
3565
	unsigned plain = sizeof(struct p_header80) *
P
Philipp Reisner 已提交
3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602
		((c->bm_words+BM_PACKET_WORDS-1)/BM_PACKET_WORDS+1)
		+ c->bm_words * sizeof(long);
	unsigned total = c->bytes[0] + c->bytes[1];
	unsigned r;

	/* total can not be zero. but just in case: */
	if (total == 0)
		return;

	/* don't report if not compressed */
	if (total >= plain)
		return;

	/* total < plain. check for overflow, still */
	r = (total > UINT_MAX/1000) ? (total / (plain/1000))
		                    : (1000 * total / plain);

	if (r > 1000)
		r = 1000;

	r = 1000 - r;
	dev_info(DEV, "%s bitmap stats [Bytes(packets)]: plain %u(%u), RLE %u(%u), "
	     "total %u; compression: %u.%u%%\n",
			direction,
			c->bytes[1], c->packets[1],
			c->bytes[0], c->packets[0],
			total, r/10, r % 10);
}

/* Since we are processing the bitfield from lower addresses to higher,
   it does not matter if the process it in 32 bit chunks or 64 bit
   chunks as long as it is little endian. (Understand it as byte stream,
   beginning with the lowest byte...) If we would use big endian
   we would need to process it from the highest address to the lowest,
   in order to be agnostic to the 32 vs 64 bits issue.

   returns 0 on failure, 1 if we successfully received it. */
3603
static int receive_bitmap(struct drbd_conf *mdev, enum drbd_packets cmd, unsigned int data_size)
P
Philipp Reisner 已提交
3604 3605 3606 3607 3608
{
	struct bm_xfer_ctx c;
	void *buffer;
	enum receive_bitmap_ret ret;
	int ok = FALSE;
3609
	struct p_header80 *h = &mdev->data.rbuf.header.h80;
P
Philipp Reisner 已提交
3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628

	wait_event(mdev->misc_wait, !atomic_read(&mdev->ap_bio_cnt));

	drbd_bm_lock(mdev, "receive bitmap");

	/* maybe we should use some per thread scratch page,
	 * and allocate that during initial device creation? */
	buffer	 = (unsigned long *) __get_free_page(GFP_NOIO);
	if (!buffer) {
		dev_err(DEV, "failed to allocate one page buffer in %s\n", __func__);
		goto out;
	}

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

	do {
3629 3630 3631
		if (cmd == P_BITMAP) {
			ret = receive_bitmap_plain(mdev, data_size, buffer, &c);
		} else if (cmd == P_COMPRESSED_BITMAP) {
P
Philipp Reisner 已提交
3632 3633 3634 3635
			/* MAYBE: sanity check that we speak proto >= 90,
			 * and the feature is enabled! */
			struct p_compressed_bm *p;

3636
			if (data_size > BM_PACKET_PAYLOAD_BYTES) {
P
Philipp Reisner 已提交
3637 3638 3639 3640 3641 3642
				dev_err(DEV, "ReportCBitmap packet too large\n");
				goto out;
			}
			/* use the page buff */
			p = buffer;
			memcpy(p, h, sizeof(*h));
3643
			if (drbd_recv(mdev, p->head.payload, data_size) != data_size)
P
Philipp Reisner 已提交
3644
				goto out;
3645 3646
			if (data_size <= (sizeof(*p) - sizeof(p->head))) {
				dev_err(DEV, "ReportCBitmap packet too small (l:%u)\n", data_size);
P
Philipp Reisner 已提交
3647 3648 3649 3650
				return FAILED;
			}
			ret = decode_bitmap_c(mdev, p, &c);
		} else {
3651
			dev_warn(DEV, "receive_bitmap: cmd neither ReportBitMap nor ReportCBitMap (is 0x%x)", cmd);
P
Philipp Reisner 已提交
3652 3653 3654
			goto out;
		}

3655 3656
		c.packets[cmd == P_BITMAP]++;
		c.bytes[cmd == P_BITMAP] += sizeof(struct p_header80) + data_size;
P
Philipp Reisner 已提交
3657 3658 3659 3660

		if (ret != OK)
			break;

3661
		if (!drbd_recv_header(mdev, &cmd, &data_size))
P
Philipp Reisner 已提交
3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691
			goto out;
	} while (ret == OK);
	if (ret == FAILED)
		goto out;

	INFO_bm_xfer_stats(mdev, "receive", &c);

	if (mdev->state.conn == C_WF_BITMAP_T) {
		ok = !drbd_send_bitmap(mdev);
		if (!ok)
			goto out;
		/* Omit CS_ORDERED with this state transition to avoid deadlocks. */
		ok = _drbd_request_state(mdev, NS(conn, C_WF_SYNC_UUID), CS_VERBOSE);
		D_ASSERT(ok == SS_SUCCESS);
	} else if (mdev->state.conn != C_WF_BITMAP_S) {
		/* admin may have requested C_DISCONNECTING,
		 * other threads may have noticed network errors */
		dev_info(DEV, "unexpected cstate (%s) in receive_bitmap\n",
		    drbd_conn_str(mdev->state.conn));
	}

	ok = TRUE;
 out:
	drbd_bm_unlock(mdev);
	if (ok && mdev->state.conn == C_WF_BITMAP_S)
		drbd_start_resync(mdev, C_SYNC_SOURCE);
	free_page((unsigned long) buffer);
	return ok;
}

3692
static int receive_skip(struct drbd_conf *mdev, enum drbd_packets cmd, unsigned int data_size)
P
Philipp Reisner 已提交
3693 3694 3695 3696 3697
{
	/* TODO zero copy sink :) */
	static char sink[128];
	int size, want, r;

3698 3699
	dev_warn(DEV, "skipping unknown optional packet type %d, l: %d!\n",
		 cmd, data_size);
P
Philipp Reisner 已提交
3700

3701
	size = data_size;
P
Philipp Reisner 已提交
3702 3703 3704 3705 3706 3707 3708 3709 3710
	while (size > 0) {
		want = min_t(int, size, sizeof(sink));
		r = drbd_recv(mdev, sink, want);
		ERR_IF(r <= 0) break;
		size -= r;
	}
	return size == 0;
}

3711
static int receive_UnplugRemote(struct drbd_conf *mdev, enum drbd_packets cmd, unsigned int data_size)
3712
{
3713 3714
	if (mdev->state.disk >= D_INCONSISTENT)
		drbd_kick_lo(mdev);
3715

3716 3717 3718
	/* Make sure we've acked all the TCP data associated
	 * with the data requests being unplugged */
	drbd_tcp_quickack(mdev->data.socket);
3719 3720 3721 3722

	return TRUE;
}

3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752
typedef int (*drbd_cmd_handler_f)(struct drbd_conf *, enum drbd_packets cmd, unsigned int to_receive);

struct data_cmd {
	int expect_payload;
	size_t pkt_size;
	drbd_cmd_handler_f function;
};

static struct data_cmd drbd_cmd_handler[] = {
	[P_DATA]	    = { 1, sizeof(struct p_data), receive_Data },
	[P_DATA_REPLY]	    = { 1, sizeof(struct p_data), receive_DataReply },
	[P_RS_DATA_REPLY]   = { 1, sizeof(struct p_data), receive_RSDataReply } ,
	[P_BARRIER]	    = { 0, sizeof(struct p_barrier), receive_Barrier } ,
	[P_BITMAP]	    = { 1, sizeof(struct p_header80), receive_bitmap } ,
	[P_COMPRESSED_BITMAP] = { 1, sizeof(struct p_header80), receive_bitmap } ,
	[P_UNPLUG_REMOTE]   = { 0, sizeof(struct p_header80), receive_UnplugRemote },
	[P_DATA_REQUEST]    = { 0, sizeof(struct p_block_req), receive_DataRequest },
	[P_RS_DATA_REQUEST] = { 0, sizeof(struct p_block_req), receive_DataRequest },
	[P_SYNC_PARAM]	    = { 1, sizeof(struct p_header80), receive_SyncParam },
	[P_SYNC_PARAM89]    = { 1, sizeof(struct p_header80), receive_SyncParam },
	[P_PROTOCOL]        = { 1, sizeof(struct p_protocol), receive_protocol },
	[P_UUIDS]	    = { 0, sizeof(struct p_uuids), receive_uuids },
	[P_SIZES]	    = { 0, sizeof(struct p_sizes), receive_sizes },
	[P_STATE]	    = { 0, sizeof(struct p_state), receive_state },
	[P_STATE_CHG_REQ]   = { 0, sizeof(struct p_req_state), receive_req_state },
	[P_SYNC_UUID]       = { 0, sizeof(struct p_rs_uuid), receive_sync_uuid },
	[P_OV_REQUEST]      = { 0, sizeof(struct p_block_req), receive_DataRequest },
	[P_OV_REPLY]        = { 1, sizeof(struct p_block_req), receive_DataRequest },
	[P_CSUM_RS_REQUEST] = { 1, sizeof(struct p_block_req), receive_DataRequest },
	[P_DELAY_PROBE]     = { 0, sizeof(struct p_delay_probe93), receive_skip },
P
Philipp Reisner 已提交
3753 3754
	/* anything missing from this table is in
	 * the asender_tbl, see get_asender_cmd */
3755
	[P_MAX_CMD]	    = { 0, 0, NULL },
P
Philipp Reisner 已提交
3756 3757
};

3758 3759 3760 3761 3762 3763
/* All handler functions that expect a sub-header get that sub-heder in
   mdev->data.rbuf.header.head.payload.

   Usually in mdev->data.rbuf.header.head the callback can find the usual
   p_header, but they may not rely on that. Since there is also p_header95 !
 */
P
Philipp Reisner 已提交
3764 3765 3766

static void drbdd(struct drbd_conf *mdev)
{
3767 3768 3769 3770 3771
	union p_header *header = &mdev->data.rbuf.header;
	unsigned int packet_size;
	enum drbd_packets cmd;
	size_t shs; /* sub header size */
	int rv;
P
Philipp Reisner 已提交
3772 3773 3774

	while (get_t_state(&mdev->receiver) == Running) {
		drbd_thread_current_set_cpu(mdev);
3775 3776 3777 3778 3779 3780
		if (!drbd_recv_header(mdev, &cmd, &packet_size))
			goto err_out;

		if (unlikely(cmd >= P_MAX_CMD || !drbd_cmd_handler[cmd].function)) {
			dev_err(DEV, "unknown packet type %d, l: %d!\n", cmd, packet_size);
			goto err_out;
3781
		}
P
Philipp Reisner 已提交
3782

3783 3784 3785 3786 3787 3788
		shs = drbd_cmd_handler[cmd].pkt_size - sizeof(union p_header);
		rv = drbd_recv(mdev, &header->h80.payload, shs);
		if (unlikely(rv != shs)) {
			dev_err(DEV, "short read while reading sub header: rv=%d\n", rv);
			goto err_out;
		}
P
Philipp Reisner 已提交
3789

3790 3791 3792
		if (packet_size - shs > 0 && !drbd_cmd_handler[cmd].expect_payload) {
			dev_err(DEV, "No payload expected %s l:%d\n", cmdname(cmd), packet_size);
			goto err_out;
P
Philipp Reisner 已提交
3793
		}
3794 3795 3796 3797

		rv = drbd_cmd_handler[cmd].function(mdev, cmd, packet_size - shs);

		if (unlikely(!rv)) {
P
Philipp Reisner 已提交
3798
			dev_err(DEV, "error receiving %s, l: %d!\n",
3799 3800
			    cmdname(cmd), packet_size);
			goto err_out;
P
Philipp Reisner 已提交
3801 3802
		}
	}
3803 3804 3805 3806 3807

	if (0) {
	err_out:
		drbd_force_state(mdev, NS(conn, C_PROTOCOL_ERROR));
	}
3808 3809 3810
	/* If we leave here, we probably want to update at least the
	 * "Connected" indicator on stable storage. Do so explicitly here. */
	drbd_md_sync(mdev);
P
Philipp Reisner 已提交
3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822
}

void drbd_flush_workqueue(struct drbd_conf *mdev)
{
	struct drbd_wq_barrier barr;

	barr.w.cb = w_prev_work_done;
	init_completion(&barr.done);
	drbd_queue_work(&mdev->data.work, &barr.w);
	wait_for_completion(&barr.done);
}

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
void drbd_free_tl_hash(struct drbd_conf *mdev)
{
	struct hlist_head *h;

	spin_lock_irq(&mdev->req_lock);

	if (!mdev->tl_hash || mdev->state.conn != C_STANDALONE) {
		spin_unlock_irq(&mdev->req_lock);
		return;
	}
	/* paranoia code */
	for (h = mdev->ee_hash; h < mdev->ee_hash + mdev->ee_hash_s; h++)
		if (h->first)
			dev_err(DEV, "ASSERT FAILED ee_hash[%u].first == %p, expected NULL\n",
				(int)(h - mdev->ee_hash), h->first);
	kfree(mdev->ee_hash);
	mdev->ee_hash = NULL;
	mdev->ee_hash_s = 0;

	/* paranoia code */
	for (h = mdev->tl_hash; h < mdev->tl_hash + mdev->tl_hash_s; h++)
		if (h->first)
			dev_err(DEV, "ASSERT FAILED tl_hash[%u] == %p, expected NULL\n",
				(int)(h - mdev->tl_hash), h->first);
	kfree(mdev->tl_hash);
	mdev->tl_hash = NULL;
	mdev->tl_hash_s = 0;
	spin_unlock_irq(&mdev->req_lock);
}

P
Philipp Reisner 已提交
3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869
static void drbd_disconnect(struct drbd_conf *mdev)
{
	enum drbd_fencing_p fp;
	union drbd_state os, ns;
	int rv = SS_UNKNOWN_ERROR;
	unsigned int i;

	if (mdev->state.conn == C_STANDALONE)
		return;
	if (mdev->state.conn >= C_WF_CONNECTION)
		dev_err(DEV, "ASSERT FAILED cstate = %s, expected < WFConnection\n",
				drbd_conn_str(mdev->state.conn));

	/* asender does not clean up anything. it must not interfere, either */
	drbd_thread_stop(&mdev->asender);
	drbd_free_sock(mdev);

3870
	/* wait for current activity to cease. */
P
Philipp Reisner 已提交
3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908
	spin_lock_irq(&mdev->req_lock);
	_drbd_wait_ee_list_empty(mdev, &mdev->active_ee);
	_drbd_wait_ee_list_empty(mdev, &mdev->sync_ee);
	_drbd_wait_ee_list_empty(mdev, &mdev->read_ee);
	spin_unlock_irq(&mdev->req_lock);

	/* We do not have data structures that would allow us to
	 * get the rs_pending_cnt down to 0 again.
	 *  * On C_SYNC_TARGET we do not have any data structures describing
	 *    the pending RSDataRequest's we have sent.
	 *  * On C_SYNC_SOURCE there is no data structure that tracks
	 *    the P_RS_DATA_REPLY blocks that we sent to the SyncTarget.
	 *  And no, it is not the sum of the reference counts in the
	 *  resync_LRU. The resync_LRU tracks the whole operation including
	 *  the disk-IO, while the rs_pending_cnt only tracks the blocks
	 *  on the fly. */
	drbd_rs_cancel_all(mdev);
	mdev->rs_total = 0;
	mdev->rs_failed = 0;
	atomic_set(&mdev->rs_pending_cnt, 0);
	wake_up(&mdev->misc_wait);

	/* make sure syncer is stopped and w_resume_next_sg queued */
	del_timer_sync(&mdev->resync_timer);
	resync_timer_fn((unsigned long)mdev);

	/* wait for all w_e_end_data_req, w_e_end_rsdata_req, w_send_barrier,
	 * w_make_resync_request etc. which may still be on the worker queue
	 * to be "canceled" */
	drbd_flush_workqueue(mdev);

	/* This also does reclaim_net_ee().  If we do this too early, we might
	 * miss some resync ee and pages.*/
	drbd_process_done_ee(mdev);

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

3909
	if (!is_susp(mdev->state))
P
Philipp Reisner 已提交
3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921
		tl_clear(mdev);

	dev_info(DEV, "Connection closed\n");

	drbd_md_sync(mdev);

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

3922 3923
	if (mdev->state.role == R_PRIMARY && fp >= FP_RESOURCE && mdev->state.pdsk >= D_UNKNOWN)
		drbd_try_outdate_peer_async(mdev);
P
Philipp Reisner 已提交
3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935

	spin_lock_irq(&mdev->req_lock);
	os = mdev->state;
	if (os.conn >= C_UNCONNECTED) {
		/* Do not restart in case we are C_DISCONNECTING */
		ns = os;
		ns.conn = C_UNCONNECTED;
		rv = _drbd_set_state(mdev, ns, CS_VERBOSE, NULL);
	}
	spin_unlock_irq(&mdev->req_lock);

	if (os.conn == C_DISCONNECTING) {
3936
		wait_event(mdev->net_cnt_wait, atomic_read(&mdev->net_cnt) == 0);
P
Philipp Reisner 已提交
3937

3938
		if (!is_susp(mdev->state)) {
3939 3940 3941 3942 3943
			/* we must not free the tl_hash
			 * while application io is still on the fly */
			wait_event(mdev->misc_wait, !atomic_read(&mdev->ap_bio_cnt));
			drbd_free_tl_hash(mdev);
		}
P
Philipp Reisner 已提交
3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962

		crypto_free_hash(mdev->cram_hmac_tfm);
		mdev->cram_hmac_tfm = NULL;

		kfree(mdev->net_conf);
		mdev->net_conf = NULL;
		drbd_request_state(mdev, NS(conn, C_STANDALONE));
	}

	/* tcp_close and release of sendpage pages can be deferred.  I don't
	 * want to use SO_LINGER, because apparently it can be deferred for
	 * more than 20 seconds (longest time I checked).
	 *
	 * Actually we don't care for exactly when the network stack does its
	 * put_page(), but release our reference on these pages right here.
	 */
	i = drbd_release_ee(mdev, &mdev->net_ee);
	if (i)
		dev_info(DEV, "net_ee not empty, killed %u entries\n", i);
3963 3964 3965
	i = atomic_read(&mdev->pp_in_use_by_net);
	if (i)
		dev_info(DEV, "pp_in_use_by_net = %d, expected 0\n", i);
P
Philipp Reisner 已提交
3966 3967
	i = atomic_read(&mdev->pp_in_use);
	if (i)
3968
		dev_info(DEV, "pp_in_use = %d, expected 0\n", i);
P
Philipp Reisner 已提交
3969 3970 3971 3972 3973 3974 3975 3976 3977 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

	D_ASSERT(list_empty(&mdev->read_ee));
	D_ASSERT(list_empty(&mdev->active_ee));
	D_ASSERT(list_empty(&mdev->sync_ee));
	D_ASSERT(list_empty(&mdev->done_ee));

	/* ok, no more ee's on the fly, it is safe to reset the epoch_size */
	atomic_set(&mdev->current_epoch->epoch_size, 0);
	D_ASSERT(list_empty(&mdev->current_epoch->list));
}

/*
 * We support PRO_VERSION_MIN to PRO_VERSION_MAX. The protocol version
 * we can agree on is stored in agreed_pro_version.
 *
 * feature flags and the reserved array should be enough room for future
 * enhancements of the handshake protocol, and possible plugins...
 *
 * for now, they are expected to be zero, but ignored.
 */
static int drbd_send_handshake(struct drbd_conf *mdev)
{
	/* ASSERT current == mdev->receiver ... */
	struct p_handshake *p = &mdev->data.sbuf.handshake;
	int ok;

	if (mutex_lock_interruptible(&mdev->data.mutex)) {
		dev_err(DEV, "interrupted during initial handshake\n");
		return 0; /* interrupted. not ok. */
	}

	if (mdev->data.socket == NULL) {
		mutex_unlock(&mdev->data.mutex);
		return 0;
	}

	memset(p, 0, sizeof(*p));
	p->protocol_min = cpu_to_be32(PRO_VERSION_MIN);
	p->protocol_max = cpu_to_be32(PRO_VERSION_MAX);
	ok = _drbd_send_cmd( mdev, mdev->data.socket, P_HAND_SHAKE,
4009
			     (struct p_header80 *)p, sizeof(*p), 0 );
P
Philipp Reisner 已提交
4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024
	mutex_unlock(&mdev->data.mutex);
	return ok;
}

/*
 * return values:
 *   1 yes, we have a valid connection
 *   0 oops, did not work out, please try again
 *  -1 peer talks different language,
 *     no point in trying again, please go standalone.
 */
static int drbd_do_handshake(struct drbd_conf *mdev)
{
	/* ASSERT current == mdev->receiver ... */
	struct p_handshake *p = &mdev->data.rbuf.handshake;
4025 4026 4027
	const int expect = sizeof(struct p_handshake) - sizeof(struct p_header80);
	unsigned int length;
	enum drbd_packets cmd;
P
Philipp Reisner 已提交
4028 4029 4030 4031 4032 4033
	int rv;

	rv = drbd_send_handshake(mdev);
	if (!rv)
		return 0;

4034
	rv = drbd_recv_header(mdev, &cmd, &length);
P
Philipp Reisner 已提交
4035 4036 4037
	if (!rv)
		return 0;

4038
	if (cmd != P_HAND_SHAKE) {
P
Philipp Reisner 已提交
4039
		dev_err(DEV, "expected HandShake packet, received: %s (0x%04x)\n",
4040
		     cmdname(cmd), cmd);
P
Philipp Reisner 已提交
4041 4042 4043
		return -1;
	}

4044
	if (length != expect) {
P
Philipp Reisner 已提交
4045
		dev_err(DEV, "expected HandShake length: %u, received: %u\n",
4046
		     expect, length);
P
Philipp Reisner 已提交
4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085
		return -1;
	}

	rv = drbd_recv(mdev, &p->head.payload, expect);

	if (rv != expect) {
		dev_err(DEV, "short read receiving handshake packet: l=%u\n", rv);
		return 0;
	}

	p->protocol_min = be32_to_cpu(p->protocol_min);
	p->protocol_max = be32_to_cpu(p->protocol_max);
	if (p->protocol_max == 0)
		p->protocol_max = p->protocol_min;

	if (PRO_VERSION_MAX < p->protocol_min ||
	    PRO_VERSION_MIN > p->protocol_max)
		goto incompat;

	mdev->agreed_pro_version = min_t(int, PRO_VERSION_MAX, p->protocol_max);

	dev_info(DEV, "Handshake successful: "
	     "Agreed network protocol version %d\n", mdev->agreed_pro_version);

	return 1;

 incompat:
	dev_err(DEV, "incompatible DRBD dialects: "
	    "I support %d-%d, peer supports %d-%d\n",
	    PRO_VERSION_MIN, PRO_VERSION_MAX,
	    p->protocol_min, p->protocol_max);
	return -1;
}

#if !defined(CONFIG_CRYPTO_HMAC) && !defined(CONFIG_CRYPTO_HMAC_MODULE)
static int drbd_do_auth(struct drbd_conf *mdev)
{
	dev_err(DEV, "This kernel was build without CONFIG_CRYPTO_HMAC.\n");
	dev_err(DEV, "You need to disable 'cram-hmac-alg' in drbd.conf.\n");
4086
	return -1;
P
Philipp Reisner 已提交
4087 4088 4089
}
#else
#define CHALLENGE_LEN 64
4090 4091 4092 4093 4094 4095 4096

/* Return value:
	1 - auth succeeded,
	0 - failed, try again (network error),
	-1 - auth failed, don't try again.
*/

P
Philipp Reisner 已提交
4097 4098 4099 4100 4101 4102 4103 4104 4105 4106
static int drbd_do_auth(struct drbd_conf *mdev)
{
	char my_challenge[CHALLENGE_LEN];  /* 64 Bytes... */
	struct scatterlist sg;
	char *response = NULL;
	char *right_response = NULL;
	char *peers_ch = NULL;
	unsigned int key_len = strlen(mdev->net_conf->shared_secret);
	unsigned int resp_size;
	struct hash_desc desc;
4107 4108
	enum drbd_packets cmd;
	unsigned int length;
P
Philipp Reisner 已提交
4109 4110 4111 4112 4113 4114 4115 4116 4117
	int rv;

	desc.tfm = mdev->cram_hmac_tfm;
	desc.flags = 0;

	rv = crypto_hash_setkey(mdev->cram_hmac_tfm,
				(u8 *)mdev->net_conf->shared_secret, key_len);
	if (rv) {
		dev_err(DEV, "crypto_hash_setkey() failed with %d\n", rv);
4118
		rv = -1;
P
Philipp Reisner 已提交
4119 4120 4121 4122 4123 4124 4125 4126 4127
		goto fail;
	}

	get_random_bytes(my_challenge, CHALLENGE_LEN);

	rv = drbd_send_cmd2(mdev, P_AUTH_CHALLENGE, my_challenge, CHALLENGE_LEN);
	if (!rv)
		goto fail;

4128
	rv = drbd_recv_header(mdev, &cmd, &length);
P
Philipp Reisner 已提交
4129 4130 4131
	if (!rv)
		goto fail;

4132
	if (cmd != P_AUTH_CHALLENGE) {
P
Philipp Reisner 已提交
4133
		dev_err(DEV, "expected AuthChallenge packet, received: %s (0x%04x)\n",
4134
		    cmdname(cmd), cmd);
P
Philipp Reisner 已提交
4135 4136 4137 4138
		rv = 0;
		goto fail;
	}

4139
	if (length > CHALLENGE_LEN * 2) {
P
Philipp Reisner 已提交
4140
		dev_err(DEV, "expected AuthChallenge payload too big.\n");
4141
		rv = -1;
P
Philipp Reisner 已提交
4142 4143 4144
		goto fail;
	}

4145
	peers_ch = kmalloc(length, GFP_NOIO);
P
Philipp Reisner 已提交
4146 4147
	if (peers_ch == NULL) {
		dev_err(DEV, "kmalloc of peers_ch failed\n");
4148
		rv = -1;
P
Philipp Reisner 已提交
4149 4150 4151
		goto fail;
	}

4152
	rv = drbd_recv(mdev, peers_ch, length);
P
Philipp Reisner 已提交
4153

4154
	if (rv != length) {
P
Philipp Reisner 已提交
4155 4156 4157 4158 4159 4160 4161 4162 4163
		dev_err(DEV, "short read AuthChallenge: l=%u\n", rv);
		rv = 0;
		goto fail;
	}

	resp_size = crypto_hash_digestsize(mdev->cram_hmac_tfm);
	response = kmalloc(resp_size, GFP_NOIO);
	if (response == NULL) {
		dev_err(DEV, "kmalloc of response failed\n");
4164
		rv = -1;
P
Philipp Reisner 已提交
4165 4166 4167 4168
		goto fail;
	}

	sg_init_table(&sg, 1);
4169
	sg_set_buf(&sg, peers_ch, length);
P
Philipp Reisner 已提交
4170 4171 4172 4173

	rv = crypto_hash_digest(&desc, &sg, sg.length, response);
	if (rv) {
		dev_err(DEV, "crypto_hash_digest() failed with %d\n", rv);
4174
		rv = -1;
P
Philipp Reisner 已提交
4175 4176 4177 4178 4179 4180 4181
		goto fail;
	}

	rv = drbd_send_cmd2(mdev, P_AUTH_RESPONSE, response, resp_size);
	if (!rv)
		goto fail;

4182
	rv = drbd_recv_header(mdev, &cmd, &length);
P
Philipp Reisner 已提交
4183 4184 4185
	if (!rv)
		goto fail;

4186
	if (cmd != P_AUTH_RESPONSE) {
P
Philipp Reisner 已提交
4187
		dev_err(DEV, "expected AuthResponse packet, received: %s (0x%04x)\n",
4188
			cmdname(cmd), cmd);
P
Philipp Reisner 已提交
4189 4190 4191 4192
		rv = 0;
		goto fail;
	}

4193
	if (length != resp_size) {
P
Philipp Reisner 已提交
4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207
		dev_err(DEV, "expected AuthResponse payload of wrong size\n");
		rv = 0;
		goto fail;
	}

	rv = drbd_recv(mdev, response , resp_size);

	if (rv != resp_size) {
		dev_err(DEV, "short read receiving AuthResponse: l=%u\n", rv);
		rv = 0;
		goto fail;
	}

	right_response = kmalloc(resp_size, GFP_NOIO);
4208
	if (right_response == NULL) {
P
Philipp Reisner 已提交
4209
		dev_err(DEV, "kmalloc of right_response failed\n");
4210
		rv = -1;
P
Philipp Reisner 已提交
4211 4212 4213 4214 4215 4216 4217 4218
		goto fail;
	}

	sg_set_buf(&sg, my_challenge, CHALLENGE_LEN);

	rv = crypto_hash_digest(&desc, &sg, sg.length, right_response);
	if (rv) {
		dev_err(DEV, "crypto_hash_digest() failed with %d\n", rv);
4219
		rv = -1;
P
Philipp Reisner 已提交
4220 4221 4222 4223 4224 4225 4226 4227
		goto fail;
	}

	rv = !memcmp(response, right_response, resp_size);

	if (rv)
		dev_info(DEV, "Peer authenticated using %d bytes of '%s' HMAC\n",
		     resp_size, mdev->net_conf->cram_hmac_alg);
4228 4229
	else
		rv = -1;
P
Philipp Reisner 已提交
4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277

 fail:
	kfree(peers_ch);
	kfree(response);
	kfree(right_response);

	return rv;
}
#endif

int drbdd_init(struct drbd_thread *thi)
{
	struct drbd_conf *mdev = thi->mdev;
	unsigned int minor = mdev_to_minor(mdev);
	int h;

	sprintf(current->comm, "drbd%d_receiver", minor);

	dev_info(DEV, "receiver (re)started\n");

	do {
		h = drbd_connect(mdev);
		if (h == 0) {
			drbd_disconnect(mdev);
			__set_current_state(TASK_INTERRUPTIBLE);
			schedule_timeout(HZ);
		}
		if (h == -1) {
			dev_warn(DEV, "Discarding network configuration.\n");
			drbd_force_state(mdev, NS(conn, C_DISCONNECTING));
		}
	} while (h == 0);

	if (h > 0) {
		if (get_net_conf(mdev)) {
			drbdd(mdev);
			put_net_conf(mdev);
		}
	}

	drbd_disconnect(mdev);

	dev_info(DEV, "receiver terminated\n");
	return 0;
}

/* ********* acknowledge sender ******** */

4278
static int got_RqSReply(struct drbd_conf *mdev, struct p_header80 *h)
P
Philipp Reisner 已提交
4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295
{
	struct p_req_state_reply *p = (struct p_req_state_reply *)h;

	int retcode = be32_to_cpu(p->retcode);

	if (retcode >= SS_SUCCESS) {
		set_bit(CL_ST_CHG_SUCCESS, &mdev->flags);
	} else {
		set_bit(CL_ST_CHG_FAIL, &mdev->flags);
		dev_err(DEV, "Requested state change failed by peer: %s (%d)\n",
		    drbd_set_st_err_str(retcode), retcode);
	}
	wake_up(&mdev->state_wait);

	return TRUE;
}

4296
static int got_Ping(struct drbd_conf *mdev, struct p_header80 *h)
P
Philipp Reisner 已提交
4297 4298 4299 4300 4301
{
	return drbd_send_ping_ack(mdev);

}

4302
static int got_PingAck(struct drbd_conf *mdev, struct p_header80 *h)
P
Philipp Reisner 已提交
4303 4304 4305
{
	/* restore idle timeout */
	mdev->meta.socket->sk->sk_rcvtimeo = mdev->net_conf->ping_int*HZ;
4306 4307
	if (!test_and_set_bit(GOT_PING_ACK, &mdev->flags))
		wake_up(&mdev->misc_wait);
P
Philipp Reisner 已提交
4308 4309 4310 4311

	return TRUE;
}

4312
static int got_IsInSync(struct drbd_conf *mdev, struct p_header80 *h)
P
Philipp Reisner 已提交
4313 4314 4315 4316 4317 4318 4319 4320 4321
{
	struct p_block_ack *p = (struct p_block_ack *)h;
	sector_t sector = be64_to_cpu(p->sector);
	int blksize = be32_to_cpu(p->blksize);

	D_ASSERT(mdev->agreed_pro_version >= 89);

	update_peer_seq(mdev, be32_to_cpu(p->seq_num));

4322 4323 4324 4325 4326 4327 4328
	if (get_ldev(mdev)) {
		drbd_rs_complete_io(mdev, sector);
		drbd_set_in_sync(mdev, sector, blksize);
		/* rs_same_csums is supposed to count in units of BM_BLOCK_SIZE */
		mdev->rs_same_csum += (blksize >> BM_BLOCK_SHIFT);
		put_ldev(mdev);
	}
P
Philipp Reisner 已提交
4329
	dec_rs_pending(mdev);
4330
	atomic_add(blksize >> 9, &mdev->rs_sect_in);
P
Philipp Reisner 已提交
4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385

	return TRUE;
}

/* when we receive the ACK for a write request,
 * verify that we actually know about it */
static struct drbd_request *_ack_id_to_req(struct drbd_conf *mdev,
	u64 id, sector_t sector)
{
	struct hlist_head *slot = tl_hash_slot(mdev, sector);
	struct hlist_node *n;
	struct drbd_request *req;

	hlist_for_each_entry(req, n, slot, colision) {
		if ((unsigned long)req == (unsigned long)id) {
			if (req->sector != sector) {
				dev_err(DEV, "_ack_id_to_req: found req %p but it has "
				    "wrong sector (%llus versus %llus)\n", req,
				    (unsigned long long)req->sector,
				    (unsigned long long)sector);
				break;
			}
			return req;
		}
	}
	dev_err(DEV, "_ack_id_to_req: failed to find req %p, sector %llus in list\n",
		(void *)(unsigned long)id, (unsigned long long)sector);
	return NULL;
}

typedef struct drbd_request *(req_validator_fn)
	(struct drbd_conf *mdev, u64 id, sector_t sector);

static int validate_req_change_req_state(struct drbd_conf *mdev,
	u64 id, sector_t sector, req_validator_fn validator,
	const char *func, enum drbd_req_event what)
{
	struct drbd_request *req;
	struct bio_and_error m;

	spin_lock_irq(&mdev->req_lock);
	req = validator(mdev, id, sector);
	if (unlikely(!req)) {
		spin_unlock_irq(&mdev->req_lock);
		dev_err(DEV, "%s: got a corrupt block_id/sector pair\n", func);
		return FALSE;
	}
	__req_mod(req, what, &m);
	spin_unlock_irq(&mdev->req_lock);

	if (m.bio)
		complete_master_bio(mdev, &m);
	return TRUE;
}

4386
static int got_BlockAck(struct drbd_conf *mdev, struct p_header80 *h)
P
Philipp Reisner 已提交
4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425
{
	struct p_block_ack *p = (struct p_block_ack *)h;
	sector_t sector = be64_to_cpu(p->sector);
	int blksize = be32_to_cpu(p->blksize);
	enum drbd_req_event what;

	update_peer_seq(mdev, be32_to_cpu(p->seq_num));

	if (is_syncer_block_id(p->block_id)) {
		drbd_set_in_sync(mdev, sector, blksize);
		dec_rs_pending(mdev);
		return TRUE;
	}
	switch (be16_to_cpu(h->command)) {
	case P_RS_WRITE_ACK:
		D_ASSERT(mdev->net_conf->wire_protocol == DRBD_PROT_C);
		what = write_acked_by_peer_and_sis;
		break;
	case P_WRITE_ACK:
		D_ASSERT(mdev->net_conf->wire_protocol == DRBD_PROT_C);
		what = write_acked_by_peer;
		break;
	case P_RECV_ACK:
		D_ASSERT(mdev->net_conf->wire_protocol == DRBD_PROT_B);
		what = recv_acked_by_peer;
		break;
	case P_DISCARD_ACK:
		D_ASSERT(mdev->net_conf->wire_protocol == DRBD_PROT_C);
		what = conflict_discarded_by_peer;
		break;
	default:
		D_ASSERT(0);
		return FALSE;
	}

	return validate_req_change_req_state(mdev, p->block_id, sector,
		_ack_id_to_req, __func__ , what);
}

4426
static int got_NegAck(struct drbd_conf *mdev, struct p_header80 *h)
P
Philipp Reisner 已提交
4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445
{
	struct p_block_ack *p = (struct p_block_ack *)h;
	sector_t sector = be64_to_cpu(p->sector);

	if (__ratelimit(&drbd_ratelimit_state))
		dev_warn(DEV, "Got NegAck packet. Peer is in troubles?\n");

	update_peer_seq(mdev, be32_to_cpu(p->seq_num));

	if (is_syncer_block_id(p->block_id)) {
		int size = be32_to_cpu(p->blksize);
		dec_rs_pending(mdev);
		drbd_rs_failed_io(mdev, sector, size);
		return TRUE;
	}
	return validate_req_change_req_state(mdev, p->block_id, sector,
		_ack_id_to_req, __func__ , neg_acked);
}

4446
static int got_NegDReply(struct drbd_conf *mdev, struct p_header80 *h)
P
Philipp Reisner 已提交
4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458
{
	struct p_block_ack *p = (struct p_block_ack *)h;
	sector_t sector = be64_to_cpu(p->sector);

	update_peer_seq(mdev, be32_to_cpu(p->seq_num));
	dev_err(DEV, "Got NegDReply; Sector %llus, len %u; Fail original request.\n",
	    (unsigned long long)sector, be32_to_cpu(p->blksize));

	return validate_req_change_req_state(mdev, p->block_id, sector,
		_ar_id_to_req, __func__ , neg_acked);
}

4459
static int got_NegRSDReply(struct drbd_conf *mdev, struct p_header80 *h)
P
Philipp Reisner 已提交
4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480
{
	sector_t sector;
	int size;
	struct p_block_ack *p = (struct p_block_ack *)h;

	sector = be64_to_cpu(p->sector);
	size = be32_to_cpu(p->blksize);

	update_peer_seq(mdev, be32_to_cpu(p->seq_num));

	dec_rs_pending(mdev);

	if (get_ldev_if_state(mdev, D_FAILED)) {
		drbd_rs_complete_io(mdev, sector);
		drbd_rs_failed_io(mdev, sector, size);
		put_ldev(mdev);
	}

	return TRUE;
}

4481
static int got_BarrierAck(struct drbd_conf *mdev, struct p_header80 *h)
P
Philipp Reisner 已提交
4482 4483 4484 4485 4486 4487 4488 4489
{
	struct p_barrier_ack *p = (struct p_barrier_ack *)h;

	tl_release(mdev, p->barrier, be32_to_cpu(p->set_size));

	return TRUE;
}

4490
static int got_OVResult(struct drbd_conf *mdev, struct p_header80 *h)
P
Philipp Reisner 已提交
4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506
{
	struct p_block_ack *p = (struct p_block_ack *)h;
	struct drbd_work *w;
	sector_t sector;
	int size;

	sector = be64_to_cpu(p->sector);
	size = be32_to_cpu(p->blksize);

	update_peer_seq(mdev, be32_to_cpu(p->seq_num));

	if (be64_to_cpu(p->block_id) == ID_OUT_OF_SYNC)
		drbd_ov_oos_found(mdev, sector, size);
	else
		ov_oos_print(mdev);

4507 4508 4509
	if (!get_ldev(mdev))
		return TRUE;

P
Philipp Reisner 已提交
4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523
	drbd_rs_complete_io(mdev, sector);
	dec_rs_pending(mdev);

	if (--mdev->ov_left == 0) {
		w = kmalloc(sizeof(*w), GFP_NOIO);
		if (w) {
			w->cb = w_ov_finished;
			drbd_queue_work_front(&mdev->data.work, w);
		} else {
			dev_err(DEV, "kmalloc(w) failed.");
			ov_oos_print(mdev);
			drbd_resync_finished(mdev);
		}
	}
4524
	put_ldev(mdev);
P
Philipp Reisner 已提交
4525 4526 4527
	return TRUE;
}

4528
static int got_skip(struct drbd_conf *mdev, struct p_header80 *h)
4529 4530 4531 4532
{
	return TRUE;
}

P
Philipp Reisner 已提交
4533 4534
struct asender_cmd {
	size_t pkt_size;
4535
	int (*process)(struct drbd_conf *mdev, struct p_header80 *h);
P
Philipp Reisner 已提交
4536 4537 4538 4539 4540 4541 4542 4543
};

static struct asender_cmd *get_asender_cmd(int cmd)
{
	static struct asender_cmd asender_tbl[] = {
		/* anything missing from this table is in
		 * the drbd_cmd_handler (drbd_default_handler) table,
		 * see the beginning of drbdd() */
4544 4545
	[P_PING]	    = { sizeof(struct p_header80), got_Ping },
	[P_PING_ACK]	    = { sizeof(struct p_header80), got_PingAck },
P
Philipp Reisner 已提交
4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556
	[P_RECV_ACK]	    = { sizeof(struct p_block_ack), got_BlockAck },
	[P_WRITE_ACK]	    = { sizeof(struct p_block_ack), got_BlockAck },
	[P_RS_WRITE_ACK]    = { sizeof(struct p_block_ack), got_BlockAck },
	[P_DISCARD_ACK]	    = { sizeof(struct p_block_ack), got_BlockAck },
	[P_NEG_ACK]	    = { sizeof(struct p_block_ack), got_NegAck },
	[P_NEG_DREPLY]	    = { sizeof(struct p_block_ack), got_NegDReply },
	[P_NEG_RS_DREPLY]   = { sizeof(struct p_block_ack), got_NegRSDReply},
	[P_OV_RESULT]	    = { sizeof(struct p_block_ack), got_OVResult },
	[P_BARRIER_ACK]	    = { sizeof(struct p_barrier_ack), got_BarrierAck },
	[P_STATE_CHG_REPLY] = { sizeof(struct p_req_state_reply), got_RqSReply },
	[P_RS_IS_IN_SYNC]   = { sizeof(struct p_block_ack), got_IsInSync },
4557
	[P_DELAY_PROBE]     = { sizeof(struct p_delay_probe93), got_skip },
P
Philipp Reisner 已提交
4558 4559 4560 4561 4562 4563 4564 4565 4566 4567
	[P_MAX_CMD]	    = { 0, NULL },
	};
	if (cmd > P_MAX_CMD || asender_tbl[cmd].process == NULL)
		return NULL;
	return &asender_tbl[cmd];
}

int drbd_asender(struct drbd_thread *thi)
{
	struct drbd_conf *mdev = thi->mdev;
4568
	struct p_header80 *h = &mdev->meta.rbuf.header.h80;
P
Philipp Reisner 已提交
4569 4570 4571 4572 4573
	struct asender_cmd *cmd = NULL;

	int rv, len;
	void *buf    = h;
	int received = 0;
4574
	int expect   = sizeof(struct p_header80);
P
Philipp Reisner 已提交
4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597
	int empty;

	sprintf(current->comm, "drbd%d_asender", mdev_to_minor(mdev));

	current->policy = SCHED_RR;  /* Make this a realtime task! */
	current->rt_priority = 2;    /* more important than all other tasks */

	while (get_t_state(thi) == Running) {
		drbd_thread_current_set_cpu(mdev);
		if (test_and_clear_bit(SEND_PING, &mdev->flags)) {
			ERR_IF(!drbd_send_ping(mdev)) goto reconnect;
			mdev->meta.socket->sk->sk_rcvtimeo =
				mdev->net_conf->ping_timeo*HZ/10;
		}

		/* conditionally cork;
		 * it may hurt latency if we cork without much to send */
		if (!mdev->net_conf->no_cork &&
			3 < atomic_read(&mdev->unacked_cnt))
			drbd_tcp_cork(mdev->meta.socket);
		while (1) {
			clear_bit(SIGNAL_ASENDER, &mdev->flags);
			flush_signals(current);
4598
			if (!drbd_process_done_ee(mdev))
P
Philipp Reisner 已提交
4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657
				goto reconnect;
			/* to avoid race with newly queued ACKs */
			set_bit(SIGNAL_ASENDER, &mdev->flags);
			spin_lock_irq(&mdev->req_lock);
			empty = list_empty(&mdev->done_ee);
			spin_unlock_irq(&mdev->req_lock);
			/* new ack may have been queued right here,
			 * but then there is also a signal pending,
			 * and we start over... */
			if (empty)
				break;
		}
		/* but unconditionally uncork unless disabled */
		if (!mdev->net_conf->no_cork)
			drbd_tcp_uncork(mdev->meta.socket);

		/* short circuit, recv_msg would return EINTR anyways. */
		if (signal_pending(current))
			continue;

		rv = drbd_recv_short(mdev, mdev->meta.socket,
				     buf, expect-received, 0);
		clear_bit(SIGNAL_ASENDER, &mdev->flags);

		flush_signals(current);

		/* Note:
		 * -EINTR	 (on meta) we got a signal
		 * -EAGAIN	 (on meta) rcvtimeo expired
		 * -ECONNRESET	 other side closed the connection
		 * -ERESTARTSYS  (on data) we got a signal
		 * rv <  0	 other than above: unexpected error!
		 * rv == expected: full header or command
		 * rv <  expected: "woken" by signal during receive
		 * rv == 0	 : "connection shut down by peer"
		 */
		if (likely(rv > 0)) {
			received += rv;
			buf	 += rv;
		} else if (rv == 0) {
			dev_err(DEV, "meta connection shut down by peer.\n");
			goto reconnect;
		} else if (rv == -EAGAIN) {
			if (mdev->meta.socket->sk->sk_rcvtimeo ==
			    mdev->net_conf->ping_timeo*HZ/10) {
				dev_err(DEV, "PingAck did not arrive in time.\n");
				goto reconnect;
			}
			set_bit(SEND_PING, &mdev->flags);
			continue;
		} else if (rv == -EINTR) {
			continue;
		} else {
			dev_err(DEV, "sock_recvmsg returned %d\n", rv);
			goto reconnect;
		}

		if (received == expect && cmd == NULL) {
			if (unlikely(h->magic != BE_DRBD_MAGIC)) {
4658 4659 4660 4661
				dev_err(DEV, "magic?? on meta m: 0x%08x c: %d l: %d\n",
				    be32_to_cpu(h->magic),
				    be16_to_cpu(h->command),
				    be16_to_cpu(h->length));
P
Philipp Reisner 已提交
4662 4663 4664 4665 4666
				goto reconnect;
			}
			cmd = get_asender_cmd(be16_to_cpu(h->command));
			len = be16_to_cpu(h->length);
			if (unlikely(cmd == NULL)) {
4667 4668 4669 4670
				dev_err(DEV, "unknown command?? on meta m: 0x%08x c: %d l: %d\n",
				    be32_to_cpu(h->magic),
				    be16_to_cpu(h->command),
				    be16_to_cpu(h->length));
P
Philipp Reisner 已提交
4671 4672 4673
				goto disconnect;
			}
			expect = cmd->pkt_size;
4674
			ERR_IF(len != expect-sizeof(struct p_header80))
P
Philipp Reisner 已提交
4675 4676 4677 4678 4679 4680 4681 4682 4683
				goto reconnect;
		}
		if (received == expect) {
			D_ASSERT(cmd != NULL);
			if (!cmd->process(mdev, h))
				goto reconnect;

			buf	 = h;
			received = 0;
4684
			expect	 = sizeof(struct p_header80);
P
Philipp Reisner 已提交
4685 4686 4687 4688 4689 4690 4691
			cmd	 = NULL;
		}
	}

	if (0) {
reconnect:
		drbd_force_state(mdev, NS(conn, C_NETWORK_FAILURE));
4692
		drbd_md_sync(mdev);
P
Philipp Reisner 已提交
4693 4694 4695 4696
	}
	if (0) {
disconnect:
		drbd_force_state(mdev, NS(conn, C_DISCONNECTING));
4697
		drbd_md_sync(mdev);
P
Philipp Reisner 已提交
4698 4699 4700 4701 4702 4703 4704 4705
	}
	clear_bit(SIGNAL_ASENDER, &mdev->flags);

	D_ASSERT(mdev->state.conn < C_CONNECTED);
	dev_info(DEV, "asender terminated\n");

	return 0;
}